December 2009 • Issue #390

TheAmst Membership Magazine of the Americana Statisticalt AssociationNews • www.amstat.org/publications/amsn

Findan INTERNSHIP

ALSO: Statistical Community Service: What Role Can Students Play?

Academic Salary Survey

Publications Agreement No. 41544521

December 2009 Amstat News A

DECEMBER 2009 • Issue #390

Executive Director Ron Wasserstein: [email protected]

Associate Executive Director and Director of Operations FEAT URES Stephen Porzio: [email protected]

Director of Education 5 President’s Corner Martha Aliaga: [email protected] 7 ’s View Director of Science Policy 11 statistical Community Service: What Role Can Steve Pierson: [email protected] students Play? Managing Editor 13 R15: The Academic Research Enhancement Award Megan Murphy: [email protected] 13 Accreditation Committee Formed Production Coordinators/Graphic Designers Melissa Muko: [email protected] 14 Academic Salary Survey Kathryn Wright: [email protected] 17 COPAFS Corner Publications Coordinator Val Snider: [email protected] 21 Developing a Science for Recording, Estimating Casualties Advertising Manager Claudine Donovan: [email protected] 23 uNC Department of Turns 60

Contributing Staff Members 24 statistical and Applied Mathematical Sciences Amy Farris • Rebecca Nichols • Cheryl Behrens Institute

Amstat News welcomes news items and letters from readers on matters 24 Committee on Nominations of interest to the association and the profession. Address correspondence to Managing Editor, Amstat News, American Statistical Association, 732 25 JASA Highlights North Washington Street, Alexandria VA 22314-1943 USA, or email [email protected]. Items must be received by the first day of the preced- 27 CHANCE Highlights ing month to ensure appearance in the next issue (for example, June 1 for the July issue). Material can be sent as a Microsoft Word document, PDF, 27 staff Spotlight or within an email. Articles will be edited for space. Accompanying art- work will be accepted in graphics file formats only (.jpg, etc.), minimum 300 dpi. No material in WordPerfect will be accepted. Amstat News (ISSN 0163-9617) is published monthly by the American Statistical Association, 732 North Washington Street, Alexandria VA 22314-1943 USA. Periodicals postage paid at Alexandria, Virginia, and additional mailing offices. POSTMASTER: Send address changes to Amstat News, 732 North Washington Street, Alexandria VA 22314-1943 USA. Send Canadian address changes to Station A, P.O. Box 54, Windsor ON N9A 6J5; [email protected]. Annual subscriptions are $50 per year for nonmembers. Amstat News is the member publication of the ASA. For annual membership rates, see www.amstat.org/join or contact ASA Member Services at (888) 231-3473. Findan American Statistical Association 732 North Washington Street Alexandria, VA 22314–1943 USA (703) 684–1221 • FAX: (703) 684-2036 INTERNSHIP p. 38 ASA GENERAL: [email protected] ADDRESS CHANGES: [email protected] AMSTAT EDITORIAL: [email protected] ADVERTISING: [email protected] Web Site: www.amstat.org Printed in USA © 2009 American Statistical Association

VISION STATEMENT To be a world leader in promoting statistical practice, applications, and research; publishing statistical journals; improving statistical education; and advancing the profession

MISSION STATEMENT Support excellence in statistical practice, research, journals, and meetings. Work for the improvement of statistical education at all levels. Promote the proper application of statistics. Anticipate and meet the needs of our members. Use our discipline to enhance human welfare. Seek opportunities to advance the statistics profession. Column Contributors Funding Opportunities Biostatistics Funding: Opportunities from NIH p. 29 This column highlights research activities that may be of interest to ASA members. These brief articles include information about new research solicitations and the federal budget for statistics. Comments or sugges- tions for future articles may be sent to [email protected]. DEPARTMENTS Contributing Editor Keith Crank has a BS in education and an MS in mathematics from Michigan State 38 Education University and a PhD in statistics from Purdue University. Prior to joining the ASA as research and Find an Internship graduate education manager, he was a program Three Interns Share Insights from NISS-NASS Projects officer at the National Science Foundation, primar- ily in the probability program. CAUSE, SERC Provide Teaching Activities

Crank Science Policy News Statistics in Defense and National Security: Lessons in Outreach to Policymakers p. 31

This column is written to inform ASA members about what the ASA is doing to promote the inclusion of statistics in policymaking and the funding of statistics research. To suggest science policy topics for the ASA to address, contact ASA Director of Science Policy Steve Pierson at [email protected].

Contributing Editors Alyson Wilson has been an associate professor of sta- tistics at Iowa State University since 2008. She moved to ISU after nine years in the statistical sciences group at Los Alamos National Laboratory, where she developed and applied methodology to assess the reliability of conventional and nuclear weapons.

Wilson

Opportunities Abound for Nancy Spruill is the director of acquisition resources and in Tech Support analysis for the undersecretary of defense for acquisi- tion at Technology & Logistics. A Fellow of the American p. 35 Statistical Association, her honors and awards include the Defense Medal for Meritorious Civilian Service, the Hammer Award, and the Presidential Rank Award.

Spruill MEMBER NEWS Master’s Notebook 55 People News Opportunities Abound for Statisticians in Tech Support p. 35 57 Award Deadlines and Information This column is written for statisticians with master’s degrees and highlights areas of employment that will benefit statisticians at the master’s level. Comments 61 Committee News and suggestions should be sent to Keith Crank, ASA research and graduate 62 Section News education manager, at [email protected]. 69 Calendar of Events 74 Professional Opportunities Contributing Editor Kathleen Kiernan is a senior statistician for SAS. She works closely with customers using SAS and JMP in sev- eral areas, including design of ; linear and ; linear, mixed, generalized mixed, and nonlinear mixed models; and . Kiernan earned her bachelor’s degree in and from Bethany College and has a master’s of science degree in statistics from Kansas State University. Kiernan ASA Institutional Members

Four-Year Colleges and Universities

American University Georgia State University Oklahoma State University

Amherst College Harvard School of Public Health Pomona College

Arizona State University Haverford College Providence College

Armstrong Atlantic State University Hunter College Purdue University Libraries TSS

Ball State University Indian Statistical Institute Real C. University ‘Escorial-Maria Cristina’

Bloomfield Library for Humanities & Social Indiana University RIT/CQAS Sciences Institute for Business and Industrial Rowan University Boise State University Statistics of the University of Amsterdam Smith College Bowdoin College Institute of Statistical Science Southern Methodist University Bowling Green State University Iowa State University St. Lawrence University/Owen D. Young Brigham Young University James Madison University Library

California State Polytechnic University The Johns Hopkins University Applied St. Mary’s College of Maryland Mathematics and Statistics Carleton University St. Olaf College Kansas State University Chalmers University State University/NY-Binghamton Kenyon College Clarkson University Stockholm University Louisiana State University/College of College of the Holy Cross Agriculture SUNY/Downstate Medical Center

Concordia College Library Louisiana State University—Shreveport Swarthmore College - Library/Periodicals Department Cornell College Marquette University—Mathematics, Statistics & Computer Services Syracuse University Dartmouth College Medical College of Wisconsin Texas A&M University Dipartimento di Statistica e Matematica per la Ricerca Economica Miami University The University of Connecticut Foundation Inc. Dortmund Statistik Minnesota State University, Mankato Tulane University E. Stroudsburg University Montana State University—Bozeman United States Naval Academy Ebsco Korea North Carolina State University University of Akron École des Mines de Saint-Étienne I 894 Northern Arizona University University of California—Library Eindhoven University of Technology Northern Illinois University University of Central Florida Ekonomski Fakultet Split Northwest Missouri State University University of Florida EP Ipswich Oakland University University of Georgia Florida State University Ohio Northern University

December 2009 Amstat News 3 University of Idaho University of Wyoming Two-Year Colleges University of Illinois—Chicago Università degli Studi di Padova-Biblioteca Butte Community College di Scienze Statistiche University of Illinois—Urbana Capilano College Universitat Jaume I University of Iowa Casper College University of Arkansas—Little Rock University of Michigan CCBC—Catonsville University of South Florida University of Michigan—Science Library Cecil Community College University of Wuerzburg University of Missouri—Rolla Edison College United States Coast Guard Academy University of Nebraska—Lincoln Johnson County Community College Vanderbilt University Library Periodicals The University of North Carolina— Joliet Junior College Department Department of Biostatistics Villanova University of Mathematics

The University of North Carolina— Virginia Commonwealth University Mercer County Community College Department of Statistics Virginia Polytechnic Institute Miami-Dade Community College University of Rochester Medical Center Western Kentucky University Montgomery College University of South Florida The W. E. Upjohn Institute Normandale Community College University of Texas Library William March Rice University North Shore Community College University of Texas School of Public Health Williams College Northcentral Technical College School University of Virginia Wright State University University of Tokyo University of Washington Seppala Library Xavier University Library University of Waterloo York University Libraries University of Wisconsin—La Crosse ASA Corporate Supporters

Amgen, Inc. MedCalc Software SPSS, Inc. AstraZeneca Pharmaceuticals MedFocus Stat-Ease Inc. Bank of America Memorial Sloan-Kettering Cancer Center StataCorp LP Department of Biostatistics Bristol-Myers Squibb Statistics of Income, IRS Minitab Inc. Bureau of Economic Analysis StatPoint Technologies, Inc. National Security Agency Cytel Software Corporation StatSoft Inc. NCSS Eli Lilly & Company The Cambridge Group Ltd. Pfizer Inc. Frontier Science & Technology The Statistics Sweden Library Pracs Institute Ltd. GE Corporate Research & Development United States Geological Survey Salford Systems IBM Corporation USDA/NASS SAS Institute J&J PRD, LLC Westat Smith Hanley Associates MacKichan Software, Inc. Wyeth Research Springer

4 Amstat News December 2009 PRESIDENT’S CORNER

There’s Strength in Numbers

ne trip overseas; two conference invita- 41% of members surveyed about voluntary accredi- tions; three presidential initiatives; four tation indicated they would apply for this distinc- American Statistical Association Board tion. Accreditation Implementation Committee meetings;O eight president’s columns; nine days at members will provide recommendations by April the Joint Statistical Meetings in Washington, DC; on how to launch and operate the program. about 10 visits to federal agencies; numerous letters During 2009, the science policy program was signed regarding federal appointments, funding, active on many fronts under the able leadership of and policy issues; 32 presidential address minutes; Steve Pierson, the ASA’s director of science policy. 57 new ASA Fellows; approximately 170 commit- On behalf of our association, I have written letters tee appointments; 6,804 attendees at JSM (a new of support for a number of government nominees, record); and lessons learned too many to count. Just stressed the importance of funding at a variety of a few statistics to sum up a year as president of the agencies, and voiced the importance of statistics American Statistical Association. And in the end, and statisticians. Our purpose is to increase the par- the realization that the president is just one of ticipation and visibility of statistics and the ASA in 18,000 members and staff who form, energize, policy. Many members, who are experts in particu- and lead the association. It has been an honor to lar policy areas, have advised the ASA and me dur- serve as president. ing the year, and I am grateful for their help. With Sally C. Morton In three Amstat News columns this year, I asked transparent self-promotion, I’ll also add that read- the 2009 presidential initiative working groups to ers interested in the interplay between statistics and report on their progress. The Financial Status group policy are encouraged to learn more about a new reported in June; the Organizational of journal titled Statistics, Politics, and Policy (www. Committees group reported in September; and the bepress.com/spp). This electronic journal will study Meetings group reported in November. All three how good statistical thinking informs matters of initiatives were motivated by the ASA strategic public policy and politics. plan. Members will see the working group recom- I’d like to say thank you to our 2008 president, mendations being put into practice in the coming Tony Lachenbruch; the ASA staff and board; and year as the association more rigorously considers its especially Ron Wasserstein, the ASA’s executive spending policy and reserves, committees form into director. I am the first president who has served as councils for increased effectiveness and communi- president-elect, president, and past president dur- cation, and the new Statistical Practice Conference ing Ron’s tenure. I can only say, “Ron, things are is advertised. I thank the members of all the work- looking up,” as I pass the baton to Sastry Pantula, ing groups for their contributions in moving the the 2010 president. We are indeed fortunate to have association forward. him as our leader in the coming year. A voluntary accreditation program was approved And, finally, I’d like to thank all the members in 2009 and is under way with the formation of an who volunteer day in and day out to keep the Accreditation Implementation Committee, chaired American Statistical Association the vibrant profes- by Iain Johnstone. Reaching out to underserved sional body it is. It has been a pleasure and delight groups in the association is a challenge identified in to serve as your president. Thank you. the ASA strategic plan. The new program is a way to provide additional services to some members, and Sincerely,

December 2009 Amstat News 5 Special Offer to All ASA Members FULL-TEXT ACCESS* to: Journal of the American Statistical Association The American Statistician Technometrics Journal of Business & Economic Statistics Journal of Computational and Graphical Statistics *Access includes all but the most recent five years.

Through a special arrangement with JSTOR, the ASA now offers its members web access to every issue of JASA, TAS, TECH, JBES, and JCGS from the inaugural year of the journal through five years prior to the current year for only $ 30 per title.

For additional information about JSTOR, see www.jstor.org. To purchase access to any of the available titles in the JSTOR database for one year, complete the form below and return it with payment to the ASA, or add JSTOR when you renew online at www.amstat.org/membersonly. (Note: Your ASA membership must be current to purchase access to JSTOR.) To join the ASA or renew your membership, see www.amstat.org/join. In purchasing access to JSTOR, ASA members agree they will use the database for their personal use only and not share their user name, password, or access with other individuals or institutions.

I have paid my ASA membership dues and want to purchase access to the JSTOR online journal database. q Yes! I understand access is limited to my personal use.

Please subscribe me to q JASA $ 30 q TAS $ 30 q TECH $ 30 q JBES $ 30 q JCGS $ 30 Total Amount Due $______

Name ______

Organization ______

Address ______

City ______State/Province ______

ZIP/Postal Code ______Country ______

o Check or Money Order Enclosed (in U.S. funds drawn from a U.S. bank)

Credit Card o VISA o MasterCard o American Express

Name on Card ______

Card # ______Exp. Date ______/______

Cardholder's Signature ______

Return this form with your payment or credit card information to ASA, Department 79081, Baltimore, MD 21279-0081, or fax to (703) 684-2037 (credit card only). Call (888) 231-3473 or email [email protected] with questions.

JSTOR is a not-for-profit organization dedicated to helping the scholarly community take advantage of advances in electronic technologies. JSTOR's primary emphases are on the creation of a trusted archive of the back files of core scholarly journals and improving access to those back files. STATISTICIAN’S VIEW

AP Statistics: Passion, Paradox, and Pressure

(PART I) Xiao-Li Meng Same Passion But Different Populations Flowing in Rossman, Peck, Franklin, Hartlaub, and Scheaffer’s letter (November, 2009, hereafter RPFHS) is passion and persuasion: passion for AP statistics and persuasion for its effectiveness. I greatly applaud their effort as passionate leaders and devoted promoters of statistical education, e.g., Professor Rossman is the current President of International Association for Statistical Education, Professor Scheaffer is a past President of ASA, and Professor Franklin’s textbook (with Professor Agresti) is actually the reference book for the Happy Course described in my op-ed (which is the piece that RPFHS commented on). The demand for sta- tistics is such that we now need significantly more I was therefore puzzled by the statement in passionate and effective statistical educators, espe- RPFHS that my “criticism” of AP statistics is “mis- cially for introductory courses, for reasons discussed directed”. My op-ed was not assessing—much less in Brown and Kass (2009) and Meng (2009). criticizing—the overall quality of AP statistics, but The same passion for the future of statistics has rather addressing a situation on cases where it had led to recent efforts at Harvard Statistics; the Happy a negative impact, as reported by students. In con- Course is just one of them (see Meng (2009) for trast, what RPFHS cited are cases where students others). Strong persuasion was also intended in have been turned on by their AP statistics experi- my op-ed for The Harvard Undergraduate Research ences, also reported by students. Journal (THURJ), persuading undergraduates to There were two sentences in my op-ed that men- take at least one course in statistics, especially those tioned AP statistics. One of them is (all emphases in who had been turned off by their AP statistics expe- the current article are added) riences. Coincidently, a colleague just forwarded an email from a Harvard undergraduate who read my “And for nearly every one of you (i.e., op-ed and whose reaction is the type that prompted undergraduates) I have spoken with, the me to acknowledge their frustration (evidently this number one reason that you did not even student made an effort to have himself “turned on” consider majoring (or concentrating, to —Stat 104 is the course taught by the protagonist be true to the Harvard spirit!) in statistics of the “Jesus” quotation in my op-ed): is because the AP statistics you took convinced you that statistics is the most “That article’s section #2 was actually one boring subject.” of my largest concerns last year because my AP Stat class was dreadfully unexciting and The other is a literal quotation from one of those just pure regurgitation (and probably why students: “AP Statistics was the most boring course I have to listen to Stat 104 lectures that a I took in high school!” I was therefore quoting from friend who took it last year downloaded students who chose to stay away from statistics. Let’s for me to refresh myself). The article was denote that population as A. By contrast, RPFHS a really fun read, unlike popular opinion was quoting from students who are already in statis- about statistics being “boring.” ” tics major/minor/courses:

December 2009 Amstat News 7 “The number of undergraduate students impossible to answer definitely, but nevertheless at Cal Poly and the University of Georgia they are essential for formulating relevant compari- choosing statistics as a major or minor has sons, designing meaningful studies, and guarding steadily increased since the advent of AP against what I called incentive bias (Meng, 2009), Statistics, with many students attesting that is, humans’ tendency, however subconsciously, that their choice was based largely on of selectively collecting and presenting evidence that their positive experience in AP Statistics. support one’s causes. Minimally, it reminds us that Similarly, the number of students enrolling given that the general demand for statistics has been in statistics courses at Kenyon College increasing rather dramatically, especially in recent has increased substantially over this time years, any type of increase in enrollments over the as well, with many students citing AP years itself cannot be taken as scientific evidence of Statistics as the reason for their interest.” the effectiveness of a particular program intended to attract students to statistics. Putting aside the issue that different institutions To see this clearly, let us use a generic binary “in” are involved, the students quoted in RPFHS belong and “out” variable; here “in” can to take a sta- C to the complement of A, A . We statisticians under- tistical course or to major in statistics, or some other stand well that conditioning on A and condition- outcome. Regardless of its actual meaning, Table 1 C ing on A are different matters, just as association is applicable to any program designed to attract (over time) and causation are not the same thing. membership. Therefore, the intended or unintended uses of such mixed arguments in RPFHS puzzled me. There is of course no puzzle whatsoever in the fact that an education program can have both sig- In Out nificant positive and negative impact, depending on Would PALWAYS POFF PWOULD how it is actually implemented. When an AP statis- tics course or any other introductory course is done well, such as those described in RPFHS, it does Would Not PON PNEVER PNOT a great service to our profession. When it is done poorly, as experienced by some Harvard undergrad- PIN POUT uates, it has a strong effect but in the opposite direc- tion. Therefore, the evidence from these different observations actually reinforce the same point: the Table 1—The row and column variables represent before first courses in statistics, regardless whether at the and after “the treatment” high school level or the college level, are absolutely critical and we need substantially more passionate and skilled educators in order to maximize their Here PALWAYS and PNEVER are respectively the positive impact. In other words, the worry discussed percentages of students (at time t) who will enter below is not about the AP program per se, which and not enter statistics regardless of whether our of course has increased awareness of statistics at the program is in place or not; POFF is the percentage of high school level by putting statistics on an equal students who would enter statistics but got turned footing with many other subjects. The worry is sim- off by the program, and PON is the percentage of ply due to the severe shortage of qualified statistical students who would not enter statistics but got teachers who can teach introductory courses in such turned on by the program. From this setup, con- a way to arouse students’ interests in statistics, or at ceptually it is clear that observing PIN = PALWAYS least not to turn them away from statistics. + PON , or even directly observing PON, large or even increase over time, says little about the overall The Off-Diagonal Paradox: Do We effectiveness of the program because POFF can also be Turn On More than We Turn Off? large and even increase over time, which can offset With the evidence of the non-emptiness of both A the gain by PON whenever POFF > PON. and AC, a scientific assessment of the overall effec- This, of course, is trivial arithmetic. But just as tiveness of any program such as AP statistics then Simpson’s paradox can be explained by trivial arith- must ask, minimally, has the program attracted more metic, yet has led to numerous erroneous conclu- students to statistics than if it were not in place? This is sions throughout the history of quantitative investi- squarely a causal inference question, one that is argu- gations, it is easy for us to focus on the “In” column ably as hard as—and therefore needs to be addressed because it is the population most easy to identify as carefully as—“does smoking cause lung cancer?” and sample from (as in RPFHS), and arrive at asser- Counterfactual causal questions as such are often tions of the benefit of the program while it actually

8 Amstat News December 2009 might be doing harm in reality. To raise awareness I perspired not because of the realization that I of this phenomenon, I suggest it be recognized as committed an elementary error of extrapolation, the “Off-Diagonal Paradox”, invoking a similar con- but rather because of the realization that if the notation of “paradox” as in Simpson’s paradox to “turn-off” phenomenon is indeed more likely for urge investigators to always keep in mind the need students at Harvard or Harvard-like institutions, for comparing the two cells along the off-diagonal then our profession has an even deeper and per- in Table 1. The word “off” should also serve as a haps more disturbing problem to worry about. reminder that the effectiveness of the overall pro- Harvard undergraduates are undoubtedly a highly gram for recruitment cannot be assessed by only selected group. But they are not so different from asking those who are already in: we need also to ask undergraduates at many of Harvard’s peer insti- those who are off or out. tutions, nor did they all come from one school For AP statistics, the inequality POFF > PON district or one state. It is, however, quite possible can hold even when PON increases as long as POUT that academically strong students have a higher remains large (which is true, for example, for major- likelihood to walk away from a poorly taught sub- ing in statistics), and when there are more poorly ject, statistics or not, than academically less able taught AP courses than well taught ones; the latter ones. Other than the fact that the former will have is one of the issues needing to be examined in any more choices at their disposal, it is not hard to assessment of the overall impact of the AP program. imagine that the former are also more likely to Not having enough well-qualified teachers is a well- be turned off by mechanical teaching emphasiz- known problem, even at the college level, a situation ing memorization for testing, as alluded to in the summarized so vividly by a college professor who aforementioned student’s email. Indeed, the latter wrote to me: may even prefer such mechanical teaching because it is less challenging than inspirational teaching “While I am not losing sleep over the which requires high-level creativity and indepen- three “puzzles” you posed in your fine dent thinking, the very traits we all look for when article in the recent issue of the Amstat we recruit students (and faculty). Therefore, if News, I am losing sleep over the very Harvard undergraduates can be viewed as a sam- serious problem of not having competent ple of high achieving high school students and if classroom instruction in lower level such students report more “turned-off” experi- undergraduate courses. In particular, the ences, then we must ask ourselves not only what first and second introductory courses are percentage of students are turned off by poorly extremely problematic, as you have pointed taught AP classes, but also what kind of students out. Unfortunately, our mathematics are more likely to be turned away. colleagues think that “anyone” can I perspired more when this was connected with teach an introductory statistics course the following anecdote, first heard from a Harvard or, that having had one or two courses undergraduate and then independently from a high with emphasis in probability rather than school student in California (the son of a friend). statistical methodologies and thought, In both cases, the student reported that his high more than meets/surpasses any possible school guidance counselor advised students that qualifying criteria to teach introductory they should consider taking AP stat courses only if stats courses. As we know, this problem is they cannot survive AP calculus courses. This sug- not new, but it is reaching critical mass.” gests that at least in some high schools AP statistics is perceived as a “softer alternative” for students An Even Harder Question: What Kind who cannot yet handle calculus. of Students Are We Turning Off? Before we all get enraged by such a condescend- An astute reader may have been wondering why ing perception, let us collectively keep a cool head I have not addressed an obvious question, that and ask a deeper question. Should we then con- is, could it be that the “turn-off” experience is sider the impact of the AP program on the overall unique to Harvard undergraduates? At the time quality of students it helps to attract in addition of writing my op-ed, Harvard undergraduates to how many it attracts? Consider two versions of were my targeted population, so this question was Table 1, one for strong students and one for weak of little interest. However, now that the “Harvard students (the dichotomy, of course, is for simplic- observation” is brought to the national level, I am ity of illustration), labeled correspondingly with indeed inspired by RPFHS to consider its general a subscript S for strong and W for weak. Then applicability. Coming with the inspiration, how- arithmetically it is possible that we have ever, is perspiration.

December 2009 Amstat News 9 POFF,S + POFF, W < PON,S + PON,W, my mis-take (or even mistake) of passion that has led to the current discussion, though I am hoping but P > P OFF,S ON,S for forgiveness if the discussion ultimately leads to That is, even if the program succeeds in attract- positive outcomes. ing more students in total, we can still end up When THURJ invited me to write an op-ed, I with a population with lower quality compared said yes immediately even though I was complete- to the population we would have attracted if the ly overwhelmed by four courses and many other program were not in place. tasks. My passion obviously took over – where else I have no on this, and sincerely hope this is could I find such an opportunity to potentially NOT true! What I have is a hunch that something reach all current Harvard undergraduates, espe- could go wrong and we cannot detect it if we only cially those who have already decided to stay away look at the “In” column. But historically, hunches from statistics? (or more formally “case studies”) have led to both The article was initially circulated within happy and miserable discoveries, when followed Harvard, but the enthusiasm from readers soon up by well-designed studies; two cases I used in encouraged me to make it available more generally. my Happy/Misery Course are the (Happy) Viagra I was well aware of the selection bias in what one Trial and the (Misery) Fen-Phen Study. It is in tends to hear, but when I read reactions such as the this spirit that I suggest that we consider the issue following, I told myself, well, why not let more stu- of quality when we design further studies on assess- dents see it? ing the effectiveness of the AP program. Such stud- “Just got a chance to read this… it’s ies are not easy at all, but if there is any profession fantastic!!! I wish we had a way to circulate which has the most, and best, experts for design- it to incoming college freshman all over ing and conducting them, it must be us. Indeed, the country—I feel like this piece alone other professions are paying high consulting fees to would substantially increase the number us for conducting these types of assessment studies of people taking statistics classes!!!” for them. It would be ironic if we could not engage our own profession, with the same rigor, to address Retrospectively, my passion for attracting as many a problem that is directly about our own future! students as possible blinded me to a completely obvi- ous fact, that once an article is printed and especially Mis-take of Passion? circulated in general, it will not be read by students My initial explanation for the lack of acknowledg- only! It simply escaped me that my intended dia- ing the “turn-off” issue in RPFHS is that they were logue with some Harvard students, that is, “I under- misled by the non-trivially edited version (with- stand you had a bad AP stat class, but please give out my knowledge) as printed in Amstat News statistics another try” could be taken as an assertion (September, 2009), where the quotation marks about the entire AP program. I of course could have were removed from the aforementioned literal said “Sorry you had a miserable experience, but AP quotation from a student on AP courses being bor- stat classes worked well for many others” – one ing. It therefore could be perceived, particularly as can imagine how persuasive that would be. But I a subtitle, as a depiction of the entire AP statistics should have added a footnote when circulating it to program. Consequently, RPFHS serves, justifiably, emphasize the intended purpose of mentioning AP as a defense of the AP program by providing posi- statistics in my op-ed. I therefore thank RPFHS for tive examples. But after I raised such a possibility, providing this opportunity for me to prevent any the editor assured me that RPFHS was written as future inappropriate quotations of my two sentences a reaction to my original op-ed (which contains on AP stat courses. In the same vein, the discussion five puzzles; see http://www.amstat.org/publications/ that will appear in the next issue of Amstat News exam- amsn/2009/september.cfm). ines the issue of potentially mis-citing the study of the That leaves me wondering if the authors of AP program by ASA and College Board (Patterson, RPFHS and I have shared a similar type of “mis- 2009; hereafter ASA/CB) in order to prevent us from take of passion”, that is, when driven by our passion making more mistakes of passion, as surely we would for wanting to see a particular outcome, we forego all love, and are eager to see, programs such as AP careful consideration or critical thinking that oth- statistics be a complete success! n erwise are quite customary to us. The phrase “mis- take” here is less a criticism of “mistake” but more an admonishment to ourselves that the human Editor’s Note: Due to space limitations, Part II will tendency of “mis-taking” passion in our effort to appear in the January issue of Amstat News. The persuade is almost innate. Indeed, in a sense, it is full piece, however, is available now at http://www. amstat.org/publications/amsn/2009/december.cfm.

10 Amstat News December 2009 Statistical Community Service: What Role Can Students Play? Cherie A. Ochsenfeld and Gayla R. Olbricht, Statistics in the Community (StatCom), Purdue University

s our society becomes more technically inte- grated, the ability to collect large volumes of data becomes more feasible for even Athe smallest companies and organizations. Unfortunately, computing power hasn’t followed and many organizations lack the knowledge to collect data that will provide them with the most information, as well as the knowledge to analyze the data once it is collected. Professional statisticians, through the ASA, have begun providing pro bono statistical consulting at the international and national levels through the Special Interest Group on Volunteerism. However, there is still a need for statistical consulting services at the community level. This is where student statisticians, through pro bono programs such as Statistics in the Community (StatCom), can help their communities while earning valuable consulting experience. Local governments and nonprofit institutions provide services to community residents and want StatCom members from several universities present posters about their pro- to know how to improve those services. To achieve grams during JSM 2008. this goal, they collect data, but do not have employ- ees trained in and analysis, or the also feel more connected to their communities and financial resources to employ statistical consulting tend to become more involved in other community services. Therefore, the information gleaned from activities and decisions. the data is minimal. Writing reports is also an essential skill for pro- Communities benefit from having the help of a fessional statisticians. Developing this skill in a statistician. They are able to extract more informa- group setting allows students to learn from each tion from their data and can make decisions based other. Working with the community also provides on statistical evidence. Community members also students with the opportunity to give presenta- learn procedures that lead to sound statistical meth- tions to both small and large audiences before they ods they can employ in the future. In turn, members graduate. Additionally, involvement in pro bono of the community feel more confident about the statistical consulting can be included on a résumé results, as a nonbiased and trained third party has or curriculum vitae. analyzed and interpreted the data. This is especially important for government and service organizations StatCom at Purdue University that need to make changes in policy based on the Graduate students in the statistics department at needs of the community. Purdue University started StatCom in 2001. It is a Students often find it difficult to get real-world graduate student–run consulting service that serves experience because examples presented during local government and nonprofit community agen- coursework are suited to teach a concept. The cies. Services often include designing surveys, using examples also avoid many issues associated with data to make informed decisions, and identifying working on an authentic problem. Through pro- trends and relationships in data. Since its inception, grams such as StatCom, students learn the commu- StatCom has worked with a of clients, includ- nication skills necessary to work with a client and ing local school districts, libraries, nonprofit arts explain statistical results in a meaningful way. This organizations, and local government entities. pro bono work allows students to make a positive The StatCom membership has included students change in their communities, see the effects of the studying graduate statistics, undergraduate statistics, statistical methods they implement, and experience psychology, and English. Students work in teams, how statistical analysis skills are valued. Students enhancing their learning while creating friendships.

December 2009 Amstat News 11 The Word Is …

The following are testimonials given by two former StatCom After finalizing the , the city was members: responsible for administering the surveys to a random To someone contemplating creating a volunteer sample of West Lafayette residents and all business owners near the parkway. Data from returned surveys student-run consulting service like StatCom, I would say two “ were entered by a city official and sent to StatCom. words: ‘Do it!’ The benefits to the university, the department, The StatCom team conducted all data analyses and and the students are great. It is my impression that StatCom provided a written report for both surveys. was a unifying force in the department. It brought the Results were presented by the group at a pub- students together, and I perceived an increase in the faculty’s lic meeting, and questions from the general public respect for the students’ contributions. A statistical consulting were addressed. The task force created a final report service that provides free service to local nonprofit groups that summarized their recommendations for the yields many tangible and intangible benefits.” Sagamore Parkway area. The StatCom reports and presentations were instrumental in prioritizing these — Craig Johnson, Professor, Mathematics Department, Brigham Young recommendations. University-Idaho and Former StatCom Director at Purdue University In 2006, StatCom conducted a follow-up study to assess outcomes of the project by interviewing six I was a member of StatCom for four semesters while an of the community leaders involved in the project. MS (applied statistics) student. It had always been my These discussions resulted in recommendations, “intention to obtain employment after my degree, and it was including the addition of street lights with banners, important for me to have a broad range of experiences in the the establishment of a farmers’ market, the improve- application of statistics for that purpose. In addition to ment of sidewalks and landscaping, and a market- strengthening my résumé, I saw StatCom as a way to gain ing effort for new sit-down restaurants. practical experience in using statistics for real-life situations.” An additional function of the StatCom program at Purdue is to provide educational outreach to the — Patricia Yoshida, Statistician, Analytics Group, Affinnova, Inc. and P–12 educational community. StatCom members Former StatCom Project Manager at Purdue University design and lead statistics-based activities for local schools and community events to educate younger students about the value of statistics. The P–12 pro- Team members conduct analyses, document their gram benefits graduate and undergraduate students results, and present their findings to clients. who wish to pursue educational careers and gives The StatCom program is run and administered them experience working with others to explain dif- by students, so the program was designed to be sec- ficult concepts. In this way, StatCom members are ondary to coursework. Clients are informed of this helping to train a more statistically educated genera- and accept it. The general commitment level for tion of students. a StatCom team member working on a project is approximately one to two hours per week. StatCom Across the Nation One of Purdue University’s StatCom projects is If you are you interested in developing a StatCom the Sagamore Parkway Task Force. The Sagamore program at your college or university, StatCom at Parkway is an economically important roadway/ Purdue University can help. In 2006, StatCom was area in West Lafayette, Indiana. In 2003, the mayor awarded an ASA member initiative grant to help appointed a task force of community members and other universities and institutions begin student- city officials to develop a plan for making improve- driven pro bono statistical consulting programs. ments to the parkway area. The task force decided a The goal is to form a StatCom network that will major part of this effort should be conducting two serve as a resource to local governmental and non- surveys—one to city residents and one to business profit community groups across the nation, as well owners adjacent to the parkway—to elicit feedback as to connect student statisticians who are devoting on how to prioritize proposed improvements. time to service-oriented consulting. So far, StatCom A StatCom team of five graduate students worked programs have been developed at the University of directly with the city and task force to conduct these Washington, University of Michigan, Iowa State surveys from start to finish. The team started by University, Virginia Tech, University of Arizona, working with task force members to write the ques- and the University of Hasselt, with continuing tionnaires. StatCom students offered guidance on interest from other institutions. question style and reviewed the for For more information, visit www.amstat.org/ bias. They also recommended Likert (1–5) scaling education/statcom or www.stat.purdue.edu/external_ to make a quantitative data analysis possible. relations/statcom. n

12 Amstat News December 2009 R15: The Academic Research Enhancement Award Michelle C. Dunn, Mathematical Statistician and Program Director, Surveillance Research Program, Division of Cancer Control and Population Sciences, National Cancer Institute

ost statisticians know the National Institutes grants may be evaluated in the same study section as of Health (NIH) is a major source of fund- traditional R01 research grants, they do not compete ing for statistical methodology research directly with R01 grants. relevantM to the health sciences through investigator- Like other research grants at NIH, the time from initiated research grants. Less well known is that NIH submission to award is about nine months. There are has a variety of mechanisms, which vary according to three standard submission due dates per year for an purpose and target audience. Broad classes of mecha- AREA/R15 grant: February 25, June 25, and October nisms are research grants (R), training awards (K), and 25. Once submitted, applications are received by the cooperative agreements (U). Cooperative agreements Center for Scientific Review and referred to a study are for collaborative projects with NIH. Training section for review and an institute for potential fund- awards generally support postdocs and early-stage ing. The study section provides the first level of review professors. Research grants are the main class of awards to judge the proposal’s scientific merit and responsive- for investigator-initiated ideas. Popular research grants ness to the goals of the mechanism. On this basis, the among statisticians are traditional research project grant receives a priority score. grants (R01), small research grants (R03), and explor- Unlike R01 grants, in which the priority score atory/developmental research grants (R21). determines a rank based on scores from all The Academic Research Enhancement Award R01 grants evaluated at the current and previous two (AREA)/R15 grant mechanism supports research meetings of the study section (e.g., BMRD), AREA/ at domestic institutions (such as U.S. colleges) that R15 grants are not percentiled. Institutes provide the receive less than $6 million in NIH funding per year, second level of review, and funding decisions are par- based on funding in the last seven years. Eligibility is tially based on an institute-established payline. Unlike determined at the time of application and can differ by the percentile payline for R01s, which makes the pro- academic component within an institution; to learn if portion of funded to received R01 grants approxi- a particular academic component is eligible, see http:// mately equal across study sections, the payline for grants.nih.gov/grants/funding/area.htm. Support is for AREA/R15 grants is based on the priority score. up to three years, with up to $300,000 per year in For more information about eligibility, criteria, and direct costs. application procedures for the AREA/R15 grant mech- The proposed research is investigator-initiated and anism, see http://grants.nih.gov/grants/funding/area.htm can be in any type of biomedical or behavioral science. or email National Cancer Institute program director, Proposed work should be well grounded and well Michelle C. Dunn, at [email protected]. n motivated by scientific problems, and collaboration with medical or behavioral researchers is encouraged. There are three stated goals of the AREA/R15 pro- gram: support meritorious research, strengthen the research environment of the institution, and expose Accreditation Committee Formed students to research. All research grants share the first The ASA’s voluntary accreditation program is under way and goal. The second and third goals are additional criteria the Accreditation Implementation Committee has been formed. for this mechanism. Members of the team include the following: AREA/R15 grant applications are evaluated by an Mary Batcher Bob Mason NIH study section, such as the Biostatistical Methods Judy-Anne Chapman David Morganstein and Research Design (BMRD) study section, which Christy Chuang-Stein Jeri Mulrow consists of prominent statisticians representing a wide Iain Johnstone (chair) Teri Utlaut range of scientific and application areas. Evaluation Nancy Kirkendall Geert Verbeke is based on all three goals. Therefore, in addition to describing the proposed research, applications should Working from guidelines approved by the ASA Board in August directly address the second and third goals. For exam- of 2009, this committee will provide recommendations for launching ple, the application can address the suitability of the and operating the accreditation program. These recommendations institution for the award and the investigator’s experi- are expected to be ready for board consideration by April of 2010. ence interacting with and engaging students (includ- For details about the voluntary accreditation program, visit http:// ing undergraduates) in research. While AREA/R15 www.amstat.org/news/VoluntaryAccreditationofStatisticians.cfm. n

December 2009 Amstat News 13 Academic Salary Survey Keith Crank, ASA Research and Graduate Education Manager

able 1 provides salary type of department. (Biostatistics about biostatistics faculty and information for statistics faculty are not included in either nonfaculty statisticians and bio- faculty, separated accord- of these tables.) All quantiles in statisticians in academic institu- Ting to the type of institution. tables 1 and 2 are based on nine- tions will be provided in a future Table 2 provides salary informa- month salaries and rounded to issue of Amstat News. tion for statistics faculty based on the nearest $100. Information

Table 1—2009–2010 Salaries of Academic Statisticians Based on Type of Institution

Years 90th Institution Type Title Count 1st Quartile 3rd Quartile in Rank Percentile

Assistant College 0 or more 18 $ 51,500 $ 55,000 $ 62,300 NA Professor

Associate 0 or more 18 $ 61,800 $ 67,600 $ 81,000 NA Professor

Professor 0 or more 21 $ 70,100 $ 85,000 $101,200 $111,700

Research Assistant 0 to 1 48 $ 65,000 $ 75,000 $ 79,200 $ 84,000 University Professor 2 32 $ 68,000 $ 75,200 $ 82,200 $ 85,000 3 53 $ 67,700 $ 75,000 $ 76,700 $ 79,700 4 40 $ 71,600 $ 76,100 $ 80,000 $ 81,400 5 25 $ 69,600 $ 74,100 $ 78,900 $ 86,800 6 or more 15 $ 61,000 $ 71,700 $ 77,300 NA

Associate 0 to 1 41 $ 76,500 $ 84,200 $ 88,900 $100,000 Professor 2 to 3 45 $ 74,900 $ 83,000 $ 91,600 $100,600 4 to 5 26 $ 71,400 $ 82,400 $ 91,700 $ 96,600 6 to 8 17 $ 74,000 $ 81,200 $ 90,400 NA 9 to 12 14 $ 66,700 $ 73,800 $ 86,300 NA 13 or more 30 $ 65,200 $ 70,500 $ 85,200 $ 93,000

Professor 0 to 1 20 $ 82,800 $ 94,400 $107,100 $117,700 2 to 3 40 $ 84,500 $106,300 $128,800 $159,000 4 to 5 26 $ 97,400 $108,600 $122,200 $137,000 6 to 7 30 $107,100 $120,100 $137,500 $164,400 8 to 9 23 $ 94,400 $118,400 $137,300 $148,000 10 to 14 63 $ 92,600 $113,800 $137,500 $167,400 15 to 19 69 $101,900 $128,300 $147,800 $171,900 20 to 24 50 $ 98,900 $114,000 $145,100 $165,600 25 to 30 22 $114,200 $136,900 $153,700 $180,500 31 or more 31 $119,200 $145,800 $165,300 $204,000

Other 0 or more 34 $ 47,100 $ 52,500 $ 61,700 $ 81,800

Other Instructor 0 or more 50 $ 40,000 $ 48,800 $ 56,900 $ 60,700

14 Amstat News December 2009 Table 2—2009–2010 Salaries of Academic Statisticians Based on Type of Department Years in 90th Institution Type Title Count 1st Quartile Median 3rd Quartile Rank Percentile Statistics Assistant 0 to 1 37 $ 72,000 $ 78,000 $ 80,000 $ 85,700 Department Professor 2 28 $ 72,800 $ 76,900 $ 83,700 $ 85,300 3 46 $ 68,800 $ 75,000 $ 77,000 $ 80,800 4 33 $ 74,200 $ 77,400 $ 80,000 $ 81,900 5 22 $ 71,000 $ 75,800 $ 79,100 $ 86,800 6 or more 13 $ 67,000 $ 71,900 $ 78,600 NA Associate 0 to 1 37 $ 80,200 $ 84,800 $ 90,000 $100,800 Professor 2 to 3 39 $ 76,400 $ 84,900 $ 91,700 $102,400 4 to 5 20 $ 76,700 $ 83,700 $ 93,200 $ 97,100 6 to 9 24 $ 73,300 $ 82,400 $ 90,700 $104,100 10 or more 28 $ 64,900 $ 72,400 $ 85,500 $ 93,200 Professor 0 to 1 19 $ 87,400 $ 94,500 $108,800 NA 2 to 5 56 $ 89,600 $109,800 $129,100 $154,400 6 to 10 60 $104,800 $120,500 $141,500 $160,500 11 to 15 55 $105,000 $124,700 $140,500 $169,500 16 to 20 64 $101,400 $128,100 $148,400 $166,700 21 to 25 39 $105,500 $120,700 $147,800 $180,800 26 or more 42 $115,300 $140,600 $169,800 $203,200 Instructor 0 or more 43 $ 40,000 $ 50,000 $ 57,800 $ 62,600 Other 0 or more 37 $ 41,000 $ 51,200 $ 60,000 $ 79,800

Not a Statistics Depart- Assistant ment (but Offering a 0 to 2 22 $ 55,000 $ 58,100 $ 67,100 $ 74,700 Professor Degree in Statistics) 3 or more 24 $ 51,700 $ 55,700 $ 68,500 $ 74,000 Associate 0 to 5 22 $ 64,400 $ 70,300 $ 75,800 $ 91,200 Professor 6 or more 14 $ 61,900 $ 69,900 $ 78,900 NA Professor 0 to 5 11 $ 79,500 $ 85,000 $101,400 NA 6 to 10 12 $ 84,600 $ 87,800 $ 97,600 NA 11 to 20 11 $ 82,500 $ 92,500 $105,900 NA 21 or more 14 $ 98,300 $108,400 $140,300 NA Instructor or 0 or more 4 NA $ 40,000 NA NA Other In a Department That Does Not Offer a Assistant 0 or more 6 NA $ 56,700 NA NA Degree in Statistics or Professor Biostatistics Associate 0 or more 7 NA $ 68,500 NA NA Professor

Professor 0 or more 11 $ 65,200 $ 72,800 $ 82,500 NA

December 2009 Amstat News 15 Beginning this year, gen- Stern Hal of courtesy Figure1 der information was requested. While tables such as 1 and 2 are possible, including the small counts of female faculty mem- bers within each category would make them of limited value. (For most categories, only the median would be reported.) As an alter- native, Figure 1 shows the impact of women’s salaries on the overall results. For assistant professors, associate professors, and full pro- fessors (in the obvious order) in statistics departments, the graph shows fitted (lowess) curves of salaries by years in rank. This is

Figure 1. Fitted (lowess) curves of salaries by years in rank show the impact of women’s salaries on the overall results.

Table 3—Quartiles for Deviations of Female Faculty Salaries from Fitted Curves for Male Faculty Salaries

Institution Title Years in Rank Count 1st Quartile Median 3rd Quartile Type Statistics Assistant 0 to 2 17 $ - 300 $ 4,700 $ 7,000 Department Professor 3 to 6 40 $ - 5,400 $ - 1,650 $ 500 Associate 0 to 6 33 $ - 5,600 $ 300 $ 6,000 Professor 7 or more 13 $ - 7,900 $ 7,700 $ 20,200 Professor 0 to 15 19 $ - 4,000 $ 7,000 $ 19,500

16 or more 10 $ - 4,000 $ 11,000 $ 21,000

done for all data for which gen- based on 319 data points, while Table 3 shows the quartiles of der was provided, as well as for the related curve for men is based the deviations of female faculty men’s salaries only. (While curves on 290 data points. Similarly, salaries from the fitted curves for could be fit for women, the lim- for associate professors, the two male faculty salaries. The breaks ited amount of data makes these curves are based on 140 and 94 in years in rank were chosen so curves less reliable.) To help in data points, and for assistant pro- the cell sizes were not too small, interpreting the curves, the com- fessors, they are based on 166 but would still allow the differ- bined curve for full professors is and 109 data points. ences to be identified. n

16 Amstat News December 2009 COPAFS Corner COPAFS Focuses on Statistical Activities Stephanie Shipp and Stephen Cohen, ASA Representatives to COPAFS

The Council of Professional Associations on Federal Statistics (COPAFS) is comprised of 60 members, including profes- sional organizations, businesses, research institutes, and others interested in federal statistics. As a member of COPAFS, the ASA has two representatives from the Government Statistics Section who attend the quarterly meetings and report back to the ASA membership. Highlights of the September 11, 2009, meeting follow. Detailed minutes can be found at www.copafs.org.

OPAFS Executive Director Ed Spar began the “index of happiness” considered by some. He the meeting by saying he would continue pointed out that BEA staff members are actively pursuing seminar opportunities. He then exploring alternatives to the basic GDP. As exam- Cdirected the audience’s attention to the upcoming ples, he cited work on measures of economic prog- FCSM conference, noting almost 300 people have ress (how people or businesses are doing relative registered for it already. to the basic GDP) and described what he called Next, he mentioned that the next COPAFS “the issue of sustainability.” meeting will feature a discussion about the U.S. Landefeld showed numerous slides illustrating Bureau’s Longitudinal Employer-Household alternative measures and the differences suggested Dynamics (LEHD) program, which is noteworthy for 2000–2007 and 2008. For example, much of for its work with synthetic estimates. the growth in liquid cash income is in supplemental On budgets, Spar said not much is happening sources, which would show a much less favorable and that a continuing resolution appears inevitable. picture of personal income if removed from the The U.S. Census Bureau is expected to be exempted basic measure. with an anomaly from flat funding, but the continu- Turning to sustainability, Landefeld described ing resolution could pose problems for NCHS and net versus gross measures, including net versus other agencies. Howard Silver of the Consortium of gross domestic income and net versus GDP. GDP Social Science Associations said a process is playing does not account for depreciation and the invest- out in which the House takes care of justice and the ments required for future production. Thus, GDP Senate takes care of commerce, with the differences measures do not indicate how sustainable economic worked out in conference. activity is over a long period of time. Landefeld pre- sented a number of graphs to illustrate his point. GDP and Beyond: Alternative One was a of household net worth and Measures of the Economic Status of savings. Savings dropped while net worth increased, Households and Business largely due to increased housing values and stock Steven Landefeld from the Bureau of Economic prices. With perceived wealth, people felt less need Analysis (BEA) explained that the notion of going to save, but the phenomenon was not sustainable. beyond the basic gross domestic product (GDP) Another graph tracked GDP, profits, and equity measure dates to the formation of the accounts in prices. Equity prices experienced dramatic increas- the 1930s. The concern is that the basic measures es without corresponding increases in profits and focus too much on economic transactions without GDP, so also were not sustainable. reference to social context. Landefeld described a Landefeld said BEA’s work on alternative mea- disconnect between the GDP and what people see sures comes at a fortuitous time, given popular as important. doubts about the value of economics and econo- Commenting that BEA has been criticized mists in the wake of the economic downturn. for dabbling in alternative measures (e.g., green Economists have been criticized for not foreseeing GDP), Landefeld said it would not go so far as the recent economic problems, and Landefeld sees

December 2009 Amstat News 17 2010 Joint Statistical Meetings, Vancouver, BC, Canada BEA’s job as providing economists with the tools ASA • ENAR • ICSA • IISA • IMS • SSC • WNAR they need to do a better job. He closed by asserting that BEA has done a good job of fulfilling its current mission with the basic measures, but acknowledged ABSTRACT the agency can provide useful additional informa- tion with alternative measures. SUBMISSION FY 2010 Initiatives at the Bureau of Justice Statistics Bureau of Justice Statistics (BJS) Acting Director OPEN Michael Sinclair commented that the agency’s staff members have been working hard to take a fresh The 2010 JSM Program Committee invites your look at the National Crime Victimization Survey participation. Submit an abstract to present one (NCVS), which accounts for most of BJS’s expendi- tures, but is just one of its many data products. of the following: Sinclair started with an overview of the NCVS, which has two major objectives: produce estimates Topic-Contributed or Contributed paper of the incidence of victimization (of both reported Topic-Contributed or Contributed poster and unreported crimes) and measure the character- istics and consequences of crime. He described these Topic-Contributed panel session objectives as competing, in that they would be best accomplished with different survey designs. BJS Submissions accepted December 1, 2009, has worked to balance these objectives, but hopes to make improvements with a redesign focusing on to February 1, 2010. restoration and renovation. Restoration includes near-term objectives such www.amstat.org/meetings/jsm/2010 as improving the base program (within budget con- straints) and increasing sample sizes to improve data Online submission is secure, convenient, and accurate. It precision. BJS also hopes to improve the U.S. Census features automated typesetting and quick transmission Bureau’s operations with upgraded laptops, additional to the program committee. staff, and field interviewer training. Long-term objec- tives include the creation of a quality improvement program and the addition of new content. 2010 “Statistics: A Key to Innovation in a Renovation objectives include small-area estima- JSM Data-Centric World” tion, research on synthetic estimates, questionnaire CANADA revisions, and different strategies. Plans call V a ncouver, British Columbia July 31–August 5, 2010 for field testing new methods in conjunction with current methods. Implementation of the program is targeted for 2013. New Requirements for Travelers from Sinclair summed up the NCVS work by noting the United States that they look to maintain the core of the current As of June 1, 2009, everyone traveling between the United survey while adding a supplemental strategy involv- States and Canada, Mexico, Central and South America, the ing new sampling methods and data collection pro- Caribbean, and Bermuda by land, sea (including cruises and cedures. The supplements could piggy-back on the ferries), or air will be required to present a valid passport existing survey, but they also are considering a parallel survey for direct measures and the use of administra- or other documents as determined by the Department of tive data for synthetic estimates. Homeland Security to cross the border. Initiatives beyond the NCVS include surveys of local sources to get an early read on changes in U.S. residents can access the following web sites for passport advance of the Uniform Crime Reports and parallel and visa information: surveys of law enforcement and the public to better understand police-public interactions. Consideration Passport: http://travel.state.gov/passport/passport_1738.html also is being given to the redesign of the State Court Processing Survey and the National Judicial Reporting Visa: http://travel.state.gov/visa/visa_1750.html Program—perhaps combining the two to reduce costs. Sinclair also described initiatives related to

18 Amstat News December 2009 indigent defense, the conversion of criminal history For 2010, the U.S. Census records into research databases, and the surveys related Bureau will revise the 2000 to the Prison Rape Elimination Act. He wrapped up DA estimates based on his presentation by describing the improved and more final 1999 and 2000 birth user-friendly BJS web site and saying they are looking and death data, then add/ forward to user input on it. subtract births/deaths for 2000–2010. Preliminary Demographic Analysis for the Census data on births and deaths for Victoria Velkoff of the U.S. Census Bureau pointed 2009 and 2010 will be used. out the long history of demographic analysis (DA) at Previous assumptions about the the bureau, but said they are working on changes for completeness of birth and death 2010 and looking for feedback. Velkoff also explained data are being reviewed. Population that the DA estimates are unique among bureau esti- age 65 and above will again be based on Medicare mates in that they are not based on census counts. She enrollment data, with adjustments made for esti- said they are important because they provide the first mated under-enrollment. measures of census coverage. When the 2000 census population count came Jason Devine, also of the U.S. Census Bureau, in higher than the DA estimate, it led to questions described DA as one of two methods the bureau uses about erroneous enumerations and the migra- to measure census coverage. The other is the micro- tion component of the DA estimates. For 2010, level, survey-based estimates that are based on case- American Community Survey (ACS) data will by-case record linkages, as in the 2000 Accuracy and contribute to the DA estimates of net international Coverage Evaluation (ACE). In contrast, DA is a migration. Pending validation, the plan is to esti- macro-level approach that compares census popula- mate immigration based on ACS data on residence tion counts with estimates based on administrative one year ago, and foreign-born emigration would be data. The DA estimates are independent of the cen- estimated with a residual method based on Census sus counts. The 2010 DA estimates will build on the 2000 and ACS data. Estimates of native migration 2000 DA estimates, not the 2000 census counts. are a challenge and still rely on previous research, The DA method tracks the size of population but this is a small component. The bureau plans cohorts based on administrative data. Specifically, a to look at IRS data for this purpose—the thinking population less than age 65 is estimated with the basic being that native-born persons who emigrate should demographic accounting equation that adds births, file a return the following April. There also has been subtracts deaths, adds immigrants, and subtracts emi- talk of a CPS question asking about family mem- grants. For a population aged 65 and above, the esti- bers who have emigrated, but Velkoff observed that mates reflect the Medicare count and an estimate of this approach does not seem to work well. persons not enrolled in Medicare. Velkoff and Devine wrapped up with a review of DA estimates measure coverage by single year of the 2010 census timeline: age, but are limited to national level and Black and non-Black race categories. The U.S. Census Bureau December 2010: Apportionment data released is researching the possibility of adding DA estimates of Hispanic and non-Hispanic, but the limited race/ December 2010: DA estimates of coverage ethnic data collected in past administrative data developed makes this a challenge for older birth cohorts. The January–March 2011: Redistricting data released survey-based coverage estimates provide greater race on flow basis and geographic detail, but involve their own chal- lenges. Divine also contrasted the core DA with 2012: Survey-based estimates of coverage Demographic Benchmark Analysis (DBA), which released compares estimates of population and housing against census counts for various geographic levels. Devine then presented a number of slides illustrat- 2010 Post-Enumeration Estimates ing 2000 DA results, such as population by age. The Using Census Coverage Measurement DA and census numbers are impressively close, but Devine pointed out differences—such as self-reported Vincent Mule of the U.S. Census Bureau stressed census age spikes for ages ending in 0 and 5—while that the purpose of Census Coverage Measurement the DA distributions are smooth. Other differences (CCM) is not to adjust the census counts, but to include the census undercount of population age 5 estimate the net coverage of the census and the and its over abundance of persons around age 20. components of census coverage for housing units

December 2009 Amstat News 19 and people in housing units. CCM does not cover Mule went on to describe the difference between group quarters. net error and components of error and elaborated The design involves a sample of the population on some definitions. For example, erroneous enu- (the P sample) and an independent sample of hous- merations can be either duplications or persons ing units in block clusters (the enumeration, or E who should not have been counted at all (e.g., those sample, from the census). The CCM program is born after census day or who died before census under way with the independent listing of address- day). There are no direct estimates of omissions, but es in the sample areas (August – December 2009). because net error is equal to omissions minus erro- Following the census, person interviewing is sched- neous enumerations, omissions are estimated as net uled for August – October 2010, person error plus erroneous enumerations. The 2010 CCM is scheduled for October 2010 – April 2011, and will identify whether omissions were in a housing final housing unit matching is scheduled for April unit that was identified. – July 2011. The timing is later than 2000, when Plans call for estimates broken out for three ACE results were required in time for potential use major domains: demographic or housing character- in adjusting the census counts. Release dates for the istics, geographic areas, and census operations. For 2010 CCM results are still under consideration, example, the intent is to produce census coverage but Mule indicated they would be out sometime measures (correct, erroneous, imputation, omission) in 2012. specific to not only race/ethnicity or age groups, but As in 1980, 1990, and 2000, CCM for the 2010 to census operations such as mail response versus census will be based on dual system estimation, but nonresponse follow up. Similarly, housing coverage use regression modeling instead of post-stratifica- will be classified by characteristics such as occupan- tion. The 2010 design also will introduce correla- cy status; tenure; type of structure; and operational tion bias adjustment for males age 18 and above. categories such as address canvassing, LUCA, or Mule explained the basics of dual-system esti- field verification. mation with the familiar 2 by 2 table with cell prop- For sub-state areas, estimates of net error would erties as follows. be released subject to statistical criteria not yet defined. For persons in housing who should have N11 Person in P sample and in E sample been counted elsewhere, an additional table has been proposed that will identify the correct resi- N12 Person in P sample, but not in E sample dence as being in the same county, different county in same state, or a different state. Another priority N21 Person not in P sample, but in E sample is to determine ways to reduce nonsampling error N22 Person not in either sample in the 2010 CCM. One possibility is to reduce the CCM sample size—reducing nonsampling error at the expense of an increase in sampling error. As Mule described it, CCM measures census A lively discussion followed. Asked how big the coverage based on numbers in the first three cells, CCM sample size was, Mule recalled it was about but is unable to account for persons (or housing) in 300,000 housing units and is planned to be the the N22 cell. same for 2010 (unless reduced as described above). The 2010 CCM will provide more on the John Thompson, who was with the U.S. Census components of census coverage. For persons in Bureau at the time, recalled the 1990 sample as housing, CCM will identify correct enumerations, about 150,000. erroneous enumerations, census imputations, and Asked if the CCM results would contribute to omissions. For housing units, CCM will identify improvements in the 2020 census, Mule described correct enumerations, erroneous enumerations, several applications related to determining the and omissions. impact of operational issues and learning more about duplications. n

Make the most of your ASA membership Visit the ASA Members Only site: www.amstat.org/membersonly Partner discounts • Member forums • Enews archive

20 Amstat News December 2009 Developing a Science for Recording, Estimating Casualties Jana Asher

s most statisticians and The population to be surveyed is might or might not be available, survey methodologists almost always traumatized and or might be in paper format and know, social data collected fearful. Often, such data must be require long hours of data entry. Aunder any circumstance can have collected in developing or transi- Qualitative or quantitative data problems associated with them. tional countries, and the popula- collected by nongovernmental , incorrect codes, tion of interest could represent organizations might or might implausible responses, and other multiple languages or culture not be of sufficient quality to be issues appear in data collected identities. useful for statistical analysis. If using even the best survey meth- After the violence has new data collection is required, ods. However, data on casualties ceased, gathering data on what it will have many of the same caused by political violence or happened—even pre-existing issues as data collection efforts war are collected under some of data—is almost as problematic. would have had during the the most trying circumstances. There might have been good actual period of violence. The best-conceived sampling media coverage (e.g., television Clearly, recording and esti- plan might fall prey to an instant- and newspaper) of local events mating casualties during political ly obsolete sample frame or sam- and episodes of violence, or violence is not easy. Many have pled clusters that have become there might have been no media attempted such estimation using unstable and are unsafe to enter. access. Administrative records methods known to them through

The ASA Community provides an online setting for like-minded statisticians to connect with peers through tools that make it easy to communicate, collaborate, and share. Visit http://community.amstat.org today!

December 2009 Amstat News 21 Burnham, and “Mortality After who participated represented an the 2003 Invasion of Iraq: A array of academic fields, includ- Cross-Sectional Cluster Sample ing statistics, demography, epide- Survey,” by Gilbert Burnham, miology, political science, history, Riyadh Lafta, Shannon Doocy, sociology, psychology, and survey Photo Photo by Jana Asher and Les Roberts. methodology. After those studies became pub- Over two days, several estab- licly available, a political and scien- lished methods for recording, esti- tific controversy that echoed across mating, and describing war-related the scientific community ensued. deaths were discussed, including Advocates of projects such as the demographic approaches, epide- Iraq Body Count and studies such miological approaches, multiple From left: Jay Aronson, Taylor Seybolt, and Baruch as the World Health Organization systems estimation, random sam- Fischhoff, organizers of a conference on casualty record- Iraq Family Health Survey raised ple surveys, repeat interviews, and ing and estimation in times of conflict questions about the validity of the complete enumerations through methods employed and suggested newspaper reports or other quali- their academic and professional different approaches. tative records. Candid discussions fields. Until recently, those diverse Partly in response to that contro- about each method demonstrated methods for recording and esti- versy and partly to understand and both strengths and weaknesses. mating casualties have not been develop a scientific consensus on The following three themes subject to much scrutiny. That the best approaches for recording seemed to emerge: changed with the release of two and estimating casualties, a group studies published in The Lancet: of researchers at Carnegie Mellon No one method is best for “Mortality Before and After the University and the University of recording and/or estimating 2003 Invasion of Iraq: Cluster Pittsburgh hosted a conference casualties. In fact, because of the Sample Survey,” by Les Roberts, on casualty recording and estima- myriad situations within which Riyadh Lafta, Richard Garfield, tion in times of conflict. The 30 casualty estimation is sought, a Jamal Khudhairi, and Gilbert experts on war-related casualties ‘toolbox’ of methods is required.

Although casualty estimation has drawn upon many aca- demic fields, the science of that estimation is complex enough to warrant the development of a unique academic field focused on its development.

The science of casualty esti- mation requires far more development. The conference organizers plan to produce a book based on the presentations given to capture the methodologies for casualty esti- mation as they exist now, but they also want to answer the call for developing better casualty estima- tion science in the future. The convening of this con- ference represents a strong first step toward developing a science for casualty recording and esti- mation; however, much work remains and statisticians and survey methodologists will play a vital role. n

22 Amstat News December 2009 UNC Department of Biostatistics Turns

he department60 of biostatistics at The University of North Carolina at Chapel Hill turned 60 in October. More than 300 fac- Tulty, students, friends, and alumni gathered at the George Watts Hill Alumni Center’s Carolina Club for a five-day celebration that included lectures on cutting-edge developments in biostatistical theory and applications; updates on the department; reflec- tions on the impact of the department on biostatis- tics, public health, and ; and a festschrift for Gary Koch. The University of North Carolina at Chapel Hill Gillings School of Global Experts in statistics and biostatistics from around Public Health Biostatistics the country presented during nine panel discussions on topics such as categorical data analysis, random- ing rigorous academic standards and producing ized trials in clinical research, data analysis using landmark papers, studies, and research programs. auxiliary and latent variables, innovative clinical In 1972, after 23 years as chair of the depart- trial design, , faculty-student ment, Greenberg became dean of the school of pub- in applied research, emerging applica- lic health. James E. Grizzle, a full professor in the tions in high-dimensional data analysis, population department, took over as chair, serving from 1972 statistics, and non- and semi-parametrics. A key theme to 1987. After a brief interim, Barry H. Margolin, that emerged was the invaluable role of the student/ then with the National Institute of Environmental mentor relationship in the department and how many Health Sciences, became the third chair. When of these relationships stay vibrant and alive beyond Margolin resigned in 1997, C. E. Davis was appoint- campus walls and graduation. ed interim chair. In October 1998, he was named A dinner banquet featured Jim Grizzle, who gave a the fourth chair. Davis retired in 2005 and, after talk on the department’s history and impact. A break- a brief interim with Jianwen Cai as chair, Michael fast in honor of Larry Kupper also was held. Kosorok, professor of statistics and biostatistics at A highlight of the festivities was a festschrift in the University of Wisconsin-Madison, became the honor of the work of Koch—a UNC-CH biostatistics fifth chair. professor, philanthropist, and co-founder of Quintiles Transnational Corp. Guest editors John S. Preisser, UNC Biostatistics Department Today Anastasia Ivanova, and William D. Johnson oversaw The mission of the department today is to forge the contribution of 23 proposed scholarly articles that advances in science that benefit human health will be published in a special volume of Statistics in through profound and paradigm-shifting innova- Biopharmaceutical Research to honor Koch. The vol- tions in biostatistical methodology and theory, as ume also will include a commentary, biography, and well as the thoughtful implementation of biostatisti- excerpts from an interview with Koch. cal methods in practice. The past decade has seen a broadening and strengthening of the faculty and a A Brief History recommitment to the fundamentals of basic statisti- Bernard G. Greenberg founded the department of cal research motivated by scientific collaboration. biostatistics in 1949 with the support of Gertrude The department encompasses more than 40 fac- Cox and . The department, initial- ulty members, 60 staff members, and 150 students ly a joint venture of the departments of mathemati- and offers bachelor’s, master’s, and doctoral degree cal statistics and experimental statistics, was created programs that provide a comprehensive and up-to- primarily to teach service courses and provide sta- date coverage of applications, methods, and theory. tistical consulting for the school of public health For more information about the depart- faculty and other components of the health affairs ment or to see pictures of the festschrift, visit division. The department quickly became a leader www.sph.unc.edu/bios/bios_60th_and_festschrift_ in the newly emerging field of biostatistics, adopt- celebration_-_october_2009_13011.html. n December 2009 Amstat News 23 Statistical and Applied Mathematical Sciences Institute Two Dynamic New Programs Planned Jim Berger, SAMSI Director, and Jamie Nunnelly, SAMSI Communications Director

under way. Fourteen research working groups meet each week, along with many workshops and classes. SAMSI’s 2010–2011 programs also are expect- ed to be popular. The Analysis of Object-Oriented Data program generalizes functional data analy- sis to the more general concept of objects as data he Statistical and Applied Mathematical points. Examples include images, shapes of objects Sciences Institute (SAMSI) is operating two in 3D, points on a manifold, tree-structured research programs this year with a record objects, and various types of movies. Program lead- Tnumber of participants. The Stochastic Dynamics and ers include Hans-Georg Müller, Jane-Ling Wang, Space-Time Analysis for Environmental Mapping, Ian Dryden, and Jim Ramsay, with local coordina- , and Climate Change programs are well tor Steve Marron. The Complex Networks program will focus on the emerging area of network science, a highly interdisciplinary field characterized by interac- tions at the interface of , sta- tistics, , and statistical physics, as Committee on Nominations well as those areas with network-oriented thrusts in biology, computer networks, engineering, and the social sciences. Program leaders include Eric WANTED: Leadership Kolaczyk and Alex Vespignani, with local coor- dinators Alun Lloyd and Peter Mucha. The sci- Nominations needed for ASA president- entific advisory committee is comprised of Pierre Degond, Stephen Fienberg, and Martina Morris. elect and vice president candidates SAMSI also will hold the Summer Program on Semiparametric : Applications he ASA needs your help. Although the 2010 elections have not in Pharmacokinetics and Pharmacodynamic July yet begun, we need to begin preparing for 2011. Nominations 12–23, 2010. The program will be led by Gary are being sought for ASA president-elect and vice president Rosner and Peter Mueller. Tcandidates for the 2011 election year. For more information or to apply for one of As a member of the ASA, you recognize the importance of lead- the programs or workshops associated with them, ership in our diverse, complex, multidisciplinary industry. You visit www.samsi.info and click on the programs or and your fellow members deserve visionary leaders, which is why workshops page. we seek your input. The president-elect will be nominated from academia, and the Education and Outreach vice president will be nominated from industry. Think about your In addition to the undergraduate workshops colleagues and associates who are members of the ASA and would held in the fall, winter, and spring, SAMSI has make good candidates for these positions. Then, nominate your a 10-day industrial research program for gradu- choices for 2011 president-elect and vice president by visiting ate students in July, which is held in conjunction www.amstat.org/committees and following the submission instruc- with the North Carolina State University Center tions. All nominations are due by March 1, 2010. for Research in Scientific Computation. Questions and suggestions may be directed to Robert Mason, Many workshop participants stay connected 2010 Committee on Nominations chair, at [email protected] or via SAMSI’s social networking outlets: Facebook, Monica Clark, ASA special projects coordinator, at monica.clark@ Twitter (@NISSSAMSI), and LinkedIn. n amstat.org. n

24 Amstat News December 2009 JASA Highlights A Peek at the December Issue David L. Banks, Len Stefanski, and Dalene Stangl

he Applications & Case Studies section starts with a discussion paper by Rob A Message from the Editor Scharpf, Håkon Tjelmeland, Giovanni TParmigiani, and Andrew Nobel titled “A Bayesian David Banks Model for Cross-Study Differential Gene It is an unalloyed delight to report that the December issue of Expression.” There are two discussions, one by Debashis Ghosh and Hyungwon Choi and the JASA is the last of my editorial duties. I have certainly enjoyed other by Xiaodan Fan and Jun Liu. this job, but it is relentless and wears one down over time. I am The section fills out with “Analysis of Multifactor deeply and completely grateful to the associate editors, Affine Yield Curve Models,” by Sid Chib and whose unflagging service makes JASA so outstanding; to the Bakhodir Ergashev ; “Bayesian Calibration of insufficiently thanked referees, who do most of the hard Microsimulation Models,” by Caroline Rutter, Diana Miglioretti, and Jim Savarino; “Option- work; and to the ASA staff, whose support has made this Pricing with Model-Guided Nonparametric journal possible. It has been a wonderful ride, and I’m very Methods,” by Jianqing Fan and Loriano glad it is over. Mancini; “Semi-Parametric Efficient Estimation for Incomplete Longitudinal Binary Data with I’d like to thank the authors, too. Partly I thank them for the Application to Smoking Trends,” by Jamie Perin, quality of their work, but even more for their professionalism John Preisser, and Paul Rathouz; and “Modeling and collegiality. Reviewing is an imperfect process, despite the and Inference for Measured Crystal Orientations best will in the world and a sincere desire on the part of all and a Tractable Class of Symmetric Distributions for Rotations in 3 Dimensions,” by Melissa Bingham, parties to find the good, rather than nit-pick the bad. It is an Daniel Nordman, and Steve Vardeman. asymmetric relationship, and few authors feel entirely well used and fully appreciated. Despite these difficulties, I treasure the Theory and Methods uniformly positive and constructive interactions I have been Paul R. Rosenbaum and Jeffrey H. Silber lead the lucky to enjoy. section with “Amplification of Sensitivity Analysis in Matched Observational Studies,” wherein they I have no concerns for the future of JASA; Hal Stern, Len develop methods for assessing the impact of an Stefanski, and Dalene Stangl have it well in hand. In the words unobserved covariate not controlled for match- Stephen Vincent Benét attributes to Daniel Webster’s nameless ing. For Bayesians at heart, Y. Chung and D. B. Dunson use a probit stick-breaking process to interlocutor regarding the United States, JASA “stands as she develop a methodology for flexibly characterizing stood, rock-bottomed and copper-sheathed.” It is one of the the relationship between a response and multiple great journals in statistics and deserves its prominence in the predictors in “Nonparametric Bayes Conditional history of our profession. Distribution Modeling with Variable Selection.” Mr. Rogers knows you can learn a lot from your neighbors and so do R. V. Craiu, J. Rosenthal, and Factor Model Approach to Multiple Testing Under C. Yang. In “Learn from Thy Neighbor: Parallel- Dependence” by C. Friguet, M. Kloareg, and D. Chain and Regional Adaptive MCMC,” these Causeur. A. Gandy’s “Sequential Implementation authors address the problem of adapting MCMC of Monte Carlo Tests with Uniformly Bounded samplers to multi-modal distribution. Risk” introduces an open-ended From multiple modes to multiple haystacks, sequential algorithm for computing the p-value of “Simultaneous Testing of Grouped Hypotheses: a test using Monte Carlo simulation that guaran- Finding Needles in Multiple Haystacks” by T. T. tees the resampling risk is uniformly bounded by an Cai and W. Sun develops a compound decision arbitrarily small constant. D. Paindaveine studies theoretic framework for testing grouped hypotheses two types of multivariate runs—an elliptical exten- and introduces an oracle procedure that minimizes sion of spherical runs and a new notion of matrix- the false nondiscovery rate subject to a constraint on valued runs—in “On Multivariate Runs Tests for the . The impact of dependence .” The Food and Drug Administration among multiple test statistics is the topic of “A will soon issue guidance on multiple endpoints.

December 2009 Amstat News 25 When they do, Y. Liu and J. Hsu have the meth- functional linear models and apply them to data from ods needed in “Testing for Efficacy in Primary the Sleep Heart Health Study. Functional predic- and Secondary Endpoints by Partitioning tors that are trajectories having certain sample-path Decision Paths.” properties in common with Brownian motion pro- Transitioning to quantile regression, A. El vide the motivation for “ with Ghouch and M. G. Genton use local-polynomial Brownian-Like Predictors” by M. A. Lindquist estimation to obtain quantile regression estimators and I. W. McKeague. In “The Analysis of Two- that transition naturally between parametric and Way Functional Data Using Two-Way Regularized nonparametric estimators according to the data Singular Value Decompositions,” J. Z. Huang, in “Local Polynomial Quantile Regression with H. Shen, and A. Buja extend one-way functional Parametric Features.” Competing for the quantile- principal component analysis to two-way functional regression crowd’s attention is “Competing Risks data via regularization of both the left and right sin- Quantile Regression” by L. Peng and J. P. Fine. gular vectors in the singular-value decomposition of C. M. Crainiceanu, A. Staicu, and C. Di the data matrix. will keep you wide awake with “Generalized Dependent sequences of motivate Multilevel Functional Regression,” in which K. Fokianos, A. Rahbek, and D. Tjøstheim’s they introduce and study generalized multilevel research in “Poisson Autoregression.” Motivated by applications to financial time series, N. Chan, S. X. Chen, C. L. Peng, and C. L. Yu author “Empirical JASA Book Reviews for December Issue Likelihood Methods Based on Characteristic Approximate Dynamic Programming: Solving the Curses of Functions with Applications to Levy Processes.” Dimensionality—Warren B. Powell In “On Nonparametric Estimation for Asymptotic Analysis of Random Walks: Heavy-Tailed Distributions—A. A. Second-Order Statistics of Inhomogeneous Spatial Borovkov and K. A. Borovkov Point Processes with a Known Parametric Intensity Bayesian Biostatistics and Diagnostic Medicine—Lyle D. Broemeling Form,” Y. Guan introduces variance estimation pro- Counterfactuals and Causal Inference: Methods and Principles for Social cedures for second-order statistics computed from a Research—Stephen L. Morgan and Christopher Winship single realization of an intensity reweighted station- The Cult of : How the Costs Us Jobs, ary spatial point process. Justice, and Lives—Stephen T. Ziliak and Deirdre N. McCloskey Rounding out the issue, H. Wang reveals Demographic Forecasting—Federico Girosi and Gary King a new use for an old algorithm in “Forward Introductory Lectures on Fluctuations of Lévy Processes with Applications— Regression for Ultra-High Dimensional Variable Andreas E. Kyprianou Screening,” showing that forward regression can Linear and Generalized Linear Mixed Models and Their Applications— identify all relevant predictors consistently, even Jiming Jiang if the predictor dimension is substantially larger Matrix Methods in Data Mining and Recognition—Lars Eldén than the sample size. In “Empirical Likelihood and Model Averaging—Gerda Claeskens and Nils Lid in Missing Data Problems,” J. Qin, B. Zhang, Hjort and D. H. Y. Leung propose a unified empiri- : Exercises and Solutions—Wolfgang Härdle and cal likelihood approach to missing data prob- Zden ˇek Hlávka lems. O. Boldea and J. R. Magnus study new Partial Differential Equations for Probabilists—Daniel W. Stroock variance estimators for mixture-model param- The Probabilistic Method (3rd ed.)—Noga Alon and Joel H. Spencer eters in “Maximum Likelihood Estimation of the C. Zou The Statistical Analysis of Functional MRI Data—Nicole A. Lazar Multivariate Normal Mixture Model.” and P. Qiu show how to use a lasso to corral produc- The Statistical Analysis of Recurrent Events—Richard J. Cook and Jerald F. Lawless tion processes in “Multivariate Statistical Process Control Using LASSO.” M. Yuan and H. Zou The Theory and Practice of Item Response Theory—R. J. de Ayala develop efficient algorithms for computing non- Applied and Generalized Linear Models (2nd ed.)— linear solution paths for general L1-regularization John Fox in “Efficient Global Approximation of Generalized Introduction to Stochastic Calculus Applied to Finance (2nd ed.)—Damien Nonlinear L1-Regularized Solution Paths and Its Lamberton and Bernard Lapeyre Applications.” Using both empirical and theoreti- Matched Sampling for Causal Effects—Donald B. Rubin cal arguments, P. Hall, D. M. Titterington, and Permutation Methods: A Distance Function Approach (2nd ed.)—Paul W. J. Xue explore the properties of classifiers based Mielke Jr. and Kenneth J. Berry on component-wise in “Median-Based Sampling of Populations: Methods and Applications (4th ed.)—Paul S. Classifiers for High-Dimensional Data.” L. Wang, Levy and Stanley Lemeshow B. Kai, and R. Li propose a novel, robust estima- Time Series Analysis: With Applications in R (2nd ed.)—Jonathan D. tion procedure for varying coefficient models based Cryer and Kung-Sik Chan on local ranks in “Local Rank Inference for Varying Coefficient Models.” n 26 Amstat News December 2009 CHANCE Highlights Diverse Topics Covered in Latest Issue Mike Larsen, CHANCE Editor

olume 22, No. 3 of CHANCE includes improved recently. Material is easier to locate and articles on a diverse set of topics. It also is PDFs of more past issues are available. Also, addi- worth noting that authors in this issue tional information about the editors and a list of all resideV in the United States, Canada, Australia, and past articles were posted. n Italy. CHANCE welcomes contributions and read- ers from around the world. Authors Shahedul Ahsan Khan, Grace Chiu, and Joel Dubin discuss statistical issues with mod- eling the concentration of chlorofluorocarbons, a primary greenhouse gas, in the atmosphere based on Staff Spotlight worldwide observations. Autar Kaw and Ali Yalcin present a new measure to quantify upsets, or unex- Cheryl Behrens pected game outcomes, in college football. Once you study their , you can watch for signs of ello, my name is Cheryl continued topsy-turvy behavior in the 2009–2010 Behrens and I am the season. Tristan Barnett analyzes expected returns ASA’s new registration and the chances of extreme outcomes in online Hcoordinator. I will be processing gambling games. How risk-adverse are you? The your conference registrations, calculations in this article could be useful illustra- coordinating badges and tickets, tions for teaching expectation, variance, and other working at the conference regis- distributional summaries. tration tables, and helping the Alberto Baccini, Lucio Barabesi, and Marzia customer service and meetings Marcheselli apply network analysis to editor- departments in any way possible. ship networks of statistical journals. In doing so, I am excited to be part of this the authors give insight into network analysis and team and want to take a minute help readers understand the field of probability to tell you a bit about myself. Behrens of statistics. Chris Bilder imagines the potential I’m originally from Califon, application of group-testing methods in a popular a small town in New Jersey. I Trust in Fresno, California; science-fiction television series. Could “Battlestar moved to Virginia to attend Green Light New Orleans; and Galactica” have benefited from having a statistician/ James Madison University (Go, Campfire USA in Lake Charles, biostatistician on board? Dukes!), where I earned a degree Louisiana. I was fortunate to see In his Visual Revelations column, Howard in communication studies and a great deal of the country and Wainer and coauthor Peter Baldwin discuss a case minored in anthropology. Upon meet some amazing people dur- in which a teacher was accused of helping students graduating, I moved to north- ing my time with AmeriCorps. cheat on a test. A careful statistical analysis was ern Virginia and worked for the I graduated from NCCC last critical in reaching a justifiable outcome. In Mark National Association of Women August and subsequently moved Glickman’s Here’s to Your Health column, Scott Business Owners (NAWBO) in back to the DC area. Evans defines and illustrates what are referred to as their member and chapter rela- In my free time, I like to noninferiority clinical trials. The purpose of such tions department. escape the city life and go hiking, trials is to study whether a new version of a drug After a year with NAWBO, camping, or canoeing. I also love is not inferior to the currently accepted treatment. I was accepted into AmeriCorps traveling; whether it is back to Read the article to learn why noninferiority trials are National Civilian Community New Jersey or across the ocean, common and how they compare to other clinical tri- Corps (NCCC) in Sacramento, I love it! als. In his Goodness of Wit Test column, Jonathan California. While serving with I enjoyed meeting many of Berkowitz offers a standard bar-type cryptic puz- NCCC, I worked for the 2009 you at the 2009 FDA/Industry zle with one constraint. The theme of the puzzle Special Olympic World Winter Statistics Workshop and I look is . Finally, Daniel Westreich Games in Boise, Idaho (which forward to meeting many more provides a little comic relief in “A Statistical was bigger than the 2002 Winter at upcoming conferences. If you Investigation of Urban Skylines in Illinois.” Olympics in Salt Lake City, have any questions or need assis- In other news, the CHANCE web site (www. Utah); the San Joaquin River tance, please feel free to contact amstat.org/publications/chance) was reorganized and Parkway and Conservation me at [email protected]. n

December 2009 Amstat News 27 28 Amstat News December 2009 Funding Opportunities Biostatistics Funding: Opportunities from NIH Keith Crank, ASA Research and Graduate Education Manager ver the past couple of months, ASA NIGMS should force NIGMS to increase the number Director of Science Policy Steve Pierson of biostatisticians on the review panel. and I have been talking with a number of It is important for biostatistics programs to com- Opeople in the academic biostatistics community. Two pete for (and receive) these training grants. The num- issues have surfaced as being of primary importance ber of U.S. citizens earning a bachelor’s degree in (in terms of the community’s interaction with the statistics from a U.S. institution increased by 40% National Institutes of Health): the need for more between 2001 and 2005. There was a 60% increase at funding to train the next generation of biostatisti- the master’s level between 2002 and 2007. Because of cians and the need for more funding for method- the longer time it takes to earn a PhD, it is too early to ological research in biostatistics. determine whether PhD production will increase, as The increasing demand for biostatisticians and well. However, it is likely to do so, if there is funding the need for the development of new methods to support for these students. understand biomedical data make these requests Encouragement to go to graduate school also is fairly obvious and worth supporting. But, according coming from the Summer Institutes for Training in to the National Institutes of Health (NIH), there are Biostatistics (SIBS) programs. Each program provides opportunities available and the biostatistics commu- training in biostatistics for approximately 20 under- nity is not applying for them. See the related article by graduate students. The students must be U.S. citizens. Michelle C. Dunn on Page 13 for information about Begun in 2004 at three institutions, this program will one of these opportunities. increase to eight institutions in the summer of 2010. As I pointed out in the sidebar to my November The original three SIBS programs have been effective Amstat News article, the National Institute for General in getting about 60% of their students to go to gradu- Medical Science (NIGMS) supports predoctoral ate school, mostly in biostatistics or epidemiology. If training through its Ruth L. Kirschstein National the additional five programs are as successful, an addi- Research Service Award (NRSA) Institutional tional 50–60 U.S. students could be added per year to Research Training Grants (T32). (Other institutes graduate programs in biostatistics. If there is no fund- also support biostatistics training grants.) In recent ing to support their graduate studies, the value of the years, there have been few, if any, applications to SIBS programs will be diminished. For more infor- NIGMS from the biostatistics community. (The mation about SIBS, visit www.nhlbi.nih.gov/funding/ next deadline is January 25, 2010.) For method- training/redbook/sibsweb.htm. ological research in biostatistics, NIH currently has a Our understanding is that there is a misconcep- study section—Biostatistical Methods and Research tion among some members of our profession regard- Design, or BMRD—that was specifically established ing how —the measures the NIH institutes to review this kind of proposal. However, over the and centers use to make funding decisions for R01 past year (maybe longer), the number of submissions and R21 research grants—are determined for grants has dropped significantly, and this study section is in reviewed by the BMRD study section. All study danger of being merged with another. sections assign a priority score (10–90) to each The existence of these ‘opportunities’ does not reviewed application reflecting the evaluation of mean all is well. There is a restriction to U.S. citizens scientific merit. For BMRD proposals, the priority or permanent residents for the training grants. This scores are converted to percentiles based on only the leaves out about 60% of the students who earn PhDs priority scores given to other applications reviewed in statistics, broadly. And it leaves out all master’s-level by BMRD in the current and previous two review students, even though there is a need (and a strong cycles. Thus, concerns that BMRD scoring may put demand) for people with that level of education. (U.S. applicants at a disadvantage when compared to that institutions award about four times as many master’s for other study sections are unfounded, as NIH will degrees in statistics as they do PhDs in statistics.) have already adjusted for any discrepancies before it The training grant proposals are reviewed by pan- makes funding decisions. While there may be good els with expertise in a range of disciplines. Since the reasons for requesting review by other study sec- panels are chosen based on the expertise needed to tions, general methodology proposals in biostatistics review the proposals submitted, few of the panelists are should be submitted to BMRD. biostatisticians. This biostatistics proposals are To contact me, send an email to keith@amstat. not reviewed by biostatisticians. Increasing the num- org. Questions or comments about this article are ber of general biostatistics training grant proposals to always welcome. n December 2009 Amstat News 29 30 Amstat News December 2009 Science Policy News Statistics in Defense and National Security: Lessons in Outreach to Policymakers Nancy Spruill, Office of the Secretary of Defense, and Alyson Wilson, Iowa State University

For this month’s column, I’m pleased to have representatives from the ASA’s Section on Statistics in Defense and National Security as guest authors. Members of this section have made out- reach to policymakers an integral part of their activities, with significant strides. After attend- ing, and being impressed by, their meeting during JSM this summer, I thought it would be helpful for them to share with other ASA members their progress to date and their plans for the future. ~ Steve Pierson, ASA Director of Science Policy, [email protected]

t JSM this summer, the Section on Statistics in Defense and National Security (SDNS) sponsored a one-day meeting that was attendedA by senior defense and homeland security officials. The meeting was one effort by SDNS to Science Policy Actions educate decisionmakers about how statistics and • ASA president sends letter to Secretary of Education Arne statisticians can address their challenges. It also Duncan regarding stature and autonomy of the National Center helped educate our fellow statisticians about the for Education Statistics many interesting and exciting opportunities in this area. We accepted the invitation to write this col- • ASA president joins leaders of 17 other science organizations umn to share our activities with you so you might in signing letter to all U.S. senators on scientific consensus of learn from our experience, but also so we can hear climate change science and learn from you. A brief history of the SDNS section is helpful to • ASA president sends letter of support for Bureau of Justice understand our efforts and illustrate the importance Statistics director nominee, James P. Lynch of persistent, incremental progress. Our inception can be traced, in part, to the 1984 JSM comments • ASA hosts meeting on election auditing attended by of former ASA President Richard Savage, who statisticians, election officials, political scientists, computer argued that statisticians should have a major role in scientists, and voting advocates defense issues because of the inherent uncertainty and the measurement of variability in so many of its topics. Through the support of many ASA presi- dents and committed ASA members, SDNS started will make statistics an integral member as a committee in 1988 and became a section in of the national and international security 2004. Former ASA President Sallie Keller-McNulty communities. was particularly helpful in assisting SDNS in iden- tifying potential outreach directions through her To answer this challenge, her task force devel- establishment of the ASA Task Force on Defense oped a long set of recommendations, many of and Security. which are the basis for SDNS’ road map. The map Keller-McNulty’s comments from the time echo is rather broad, so we’ll focus on the items most themes going back to Savage and lay out a clear relevant to policy. challenge for the ASA: Outreach to Decisionmakers National/international security is a The meeting held during JSM was planned to problem that is growing in importance take advantage of JSM being in Washington, DC, at a frightening pace, and my experience and funded by a member initiative from the ASA at Los Alamos National Laboratory has Board of Directors. A day-long event, the morn- made me aware that statistical science is ing sessions included presentations by senior offi- nearly invisible in this arena … ASA must cials of the Office of the Secretary of Defense, U.S. provide a strong and unified voice that Army, Department of Homeland Security, Defense

December 2009 Amstat News 31 One speaker noted that one of his biggest prob- lems is the data—it is usually messy and often has missing observations. We also heard about the oper- Missile Reliability ational point of view in a talk by a representative of the Joint Forces Command. He gave us interesting During engineering design, you expect to find failure modes. information about the analytical challenges in the For example, in a missile design, you might fire five missiles joint operating environment, how the forces will be and see two failures—say an engine ignition or battery failure. fighting in the future, and how he sees statisticians The engineers then try to fix the failures. After the fixes are contributing to the nation’s security. incorporated, how do you calculate the reliability? In the question-and-answer period that fol- lowed each presentation, participants asked ques- To simplify, the original approach (using the Lloyd method) tions and suggested ways statistics could help turns failures into successes if those failures don’t occur again in address the issues. the next few shots. The method is simple, direct, and easily Most speakers had a basic understanding of sta- tistics, but came away with a better appreciation for calculated. It led to a reliability estimate of about 0.93 in our the role statistics can play. We tried to impress upon case. The raw score would be the result if the failures were not them the gap between the state of the art of statis- turned into success, but retained as failures. Both methods are, tics and what they may have picked up in a gradu- in some sense, wrong. Using the raw score fails to account for ate statistics course 20–30 years ago. They learned the effort (and possible success) to fix failure modes. Yet, the about areas where their interests overlapped those Lloyd method gives too much credit to the fix, because it does of statisticians. Contact information was exchanged not recognize that observing one failure may prevent, or and follow-ups are occurring. shadow, the possibility of seeing another. The afternoon session featured remarks by SDNS members on how statistics was already being What we have here is a system that has many failure modes, used successfully on defense- and security-related each with its own , and the failure rate of the whole problems. These presentations included work on system is a combination of all failure rates. When an engineer biosurveillance, test and evaluation, and text data removes a failure , the combined failure rate will mining. Most presentations will be posted to the change. Common experience is that each failure mode SDNS web site at www.amstat.org/sections/sdns. Other activities members of SDNS have pur- follows a Poisson distribution. So, the growth in reliability is sued in an attempt to reach out to decisionmakers nonhomogeneous Poisson process (more complicated include hosting meetings between ASA presidents because the events are discrete). The method is not simple, and Department of Defense and CIA policy offices not direct, and not easily calculated. to raise the visibility of statistics. While the recep- tion has been positive, it is important that this be an In this case, the absence of a statistician in the beginning ongoing activity and that we also seek meetings with allowed both the government and contractor to be fooled officials in the Department of Homeland Security about the reliability of the system, illustrating our point and Department of Energy Office of Science. that statisticians have an important role in helping the We also have reached out to the Defense Science government determine how best to use the available data. Board (DSB), partly through ASA leadership, and have been told that statisticians will be recom- mended to DSB study panels that require statistical expertise. We continue to push for a statistician to Advanced Research Projects Agency (DARPA), and be appointed to DSB. Joint Warfare Analysis Center. Nozer Singpurwalla of DARPA gave the keynote Outreach to Fellow Statisticians address. He focused on the historical roots of statis- Recognizing the importance of having more stat- tics in defense problems, applications of statistical isticians involved in national security projects to approaches, and success stories. broaden our influence, we have undertaken many Other presentations largely focused on the chal- activities to educate the community about the many lenges the speaker’s office/organization encountered interesting problems and their potential for statis- and where they thought statistics might be able to ticians. In addition to inviting statisticians to this play a role. They addressed issues such as how good summer’s meeting, we’ve been organizing JSM ses- they are at anticipating defense needs, whether the sions that show the breadth of activity in defense systems they produce are better than what is already and security—from cyber security to biosurveillance available, and what is likely to be transforming. to more traditional areas such as reliability. We also

32 Amstat News December 2009 are organizing the third Quantitative Methods in Defense and National Security (QMDNS) confer- ence, which was established to link defense prob- lems to statistical solutions. Participants include both defense industry workers and statisticians. (See www.galaxy.gmu.edu/QMDNS2010.) SHOP SDNS also established a speakers program (see Page 63 and www.amstat.org/sections/sdns/ speakers.html), again with funding from an ASA member initiative, to provide speakers and travel funding to universities and colleges interested in hearing a presentation about statistical aspects of national security challenges. We have a dozen peo- Visit the ASA’s online marketplace at ple on the speakers list and encourage you to both invite a speaker to your institution and add your www.amstat.org/asastore name to the list. Success Stories While there is much more that statistics can con- tribute to this field, statisticians have made an impact on national security problems. One example is a major defense acquisition program that ran into reliability problems because of faulty methodology for tracking reliability improvement during devel- opment. It was a statistician who laid out the rules for estimating reliability, allowing the program to get back on track (see “Missile Reliability”). Other examples can be found at www.amstat.org/sections/ sdns/SDNS_ThePresent.pdf and www.amstat.org/ outreach/pdfs/StatSigNationalSecurity.pdf. Next Steps and Lessons Our next steps for outreach to policymakers are to continue and broaden our current activities by reaching more officials and statisticians and revisit- ing those we’ve already met. For outreach to stat- Books Apparel isticians, we hope our enthusiasm for the many interesting problems statistics can address in this field was manifest. We welcome your involvement and advice. As our history indicates, this has been a long road, but we can point to real progress for statistics in national security issues. Clearly, much remains to be done. One lesson we’ve learned is that we need to Purchase T-shirts, books, do a better job of educating decisionmakers about JSM Proceedings, and gift what statisticians do. For those who realize the value of statistics, our experience is that sometimes the items! statistics is not always done by statisticians. So, we need to communicate more convincingly that stat- isticians can bring state-of-the-art techniques to a problem, which may yield better solutions faster. For other sections exploring how to better reach policymakers, we highly recommend using the resources available from the ASA, especially fund- SAVE 10% ing through member initiatives. n on your first purchase by entering ASASTORE at checkout.

December 2009 Amstat News 33 34 Amstat News December 2009 Master’s Notebook Opportunities Abound for Statisticians in Tech Support Kathleen Kiernan

tores have an abundance SAS customers. As a result, my of T-shirts, bumper stick- day is roughly divided between ers, and greeting cards for phone duty, researching solu- doctors,S engineers, and teach- tions to customers’ questions, ers—even for horticulturists. communicating solutions But, I have never seen anything to customers, and career for statisticians. Statistics are development. used in most professions in one When a customer way or another, but it is often calls the SAS switch- an ‘invisible’ occupation. I am board with a statisti- not surprised I didn’t find out it cal software question, was an area of study until taking they are transferred to a compulsory statistics course the statistician assigned for my master’s degree in animal to phone duty. If the breeding. I admit, when asked statistician on phone what I wanted to be when I duty cannot resolve the grew up, I never said “I want to question, they either file it be a statistician.” However, I am for later research or route it glad it is where I ended up. to the statistician covering that My professors at Kansas State specific area. For my areas, I can University inspired me toward usually find the solution in my statistics. They made the mate- personal usage notes and sam- rial interesting and relevant, ple programs of explanations developers. We also help write and after my first linear models and resolutions. Other times, and review any new documen- course, I was hooked. I immedi- the questions require research tation that results from the sug- ately realized the career poten- through SAS resources, cowork- gestions. Second, we write usage tial after graduating with my ers, statistics books, or papers. notes with explanations, solu- master’s degree. I interviewed More complicated issues require tions, and sample programs that several places before accepting not only research, but possible use existing or simulated data. a position in the technical sup- consultation with a software Keeping a complete record of port division at SAS Institute. developer. The developers are information in our files goes Over time, I realized how lucky great to work with; they invite a long way in freeing up our I was to find such a fascinating questions and usually drop their time later. specialty. Not everyone is so own work to treat the question I am well suited to this career lucky, which is what prompted as a priority. for a variety of reasons. While me to share my experience. Documentation is a big part my main areas of focus in col- My team within SAS tech- of the job. SAS technical sup- lege were mathematics, statis- nical support is dedicated to port documents the questions tics, and education, I also am statistics. Although there is from each customer along with able to use my background in some overlap of responsibility, the corresponding solutions. chemistry, biology, and genetics. everyone has their own areas This documentation serves two Additionally, I am at an advan- of expertise. My focus cen- purposes. First, we keep track tage because I was a graduate ters on linear and generalized of frequently asked questions teaching assistant and taught mixed models, design of experi- so areas of concern or sugges- undergraduate statistics courses. ments, and genomics, and my tions for new features can be I am able to explain statistics to job depends on questions from communicated to the software nonstatisticians; being able to

December 2009 Amstat News 35 interpreting the results. I have opportunities to talk with engi- increased my programming and neers, researchers, physicians, … think about what you communication skills, which are scientists, and statisticians from sometimes just as important as other industries. As I help with “want to do before you start my statistical skill set. I enjoy the design or analysis of their the new and continuing chal- experiments or studies, I gain your career so you can lenges. While the number of a greater understanding and take the appropriate steps questions I am able to answer appreciation for off the top of my head has in building cars and planes and as you go along. increased over the years, I still developing new drugs. have hard problems to resolve. I My advice to someone think- ” usually find a solution within a ing of a career as a statistician speak clearly without the use of couple of hours (or days) using in a software company is to jargon or acronyms is critical to research and programming. think about what you want to communicating with customers. There is no way to know every- do before you start your career The opportunities and chal- thing, of course, but the chal- so you can take the appropriate lenges of my job are endless; lenge is always there. steps as you go along. If you are boredom is rarely a problem and Being able to learn from so interested in becoming a devel- career development is nonstop. many types of people is a truly oper, I recommend you get your Because I learn new areas and great advantage of working in PhD and experience in develop- applications as software is creat- technical support. The relation- ing software. However, a statis- ed or revised, I need to be com- ships I have built with cowork- tician with a master’s degree has fortable with the procedure syn- ers, developers, and customers many opportunities in the tech- tax, running the procedures on have made my 18 years at SAS nical support division of any different operating systems, and enjoyable. I have never-ending software company. n

36 Amstat News December 2009 The ASA Brings the Library to Your Desktop

Did you know your ASA membership includes online access to the: Journal of the American Statistical Association Journal of Business & Economic Statistics Statistics in Biopharmaceutical Research and The American Statistician?

Log in to MEMBERS ONLY today to access your journals! www.amstat.org/membersonly Findan INTERNSHIP very year, a list of internship opportunities for students is published in Amstat News. Internships benefit both the organization andE the student. The student has the opportunity to work with practicing statisticians who are profi- cient in their fields and to learn what it is like to work in an industrial, laboratory, or office setting. The organization obtains the benefit of the student’s academic and other training, contributes to the professional development of that student, and has a first-hand opportunity to evaluate the student’s potential for future employment. If your organization would like to list an intern- ship opportunity on our web site, please complete the form at www.amstat.org/education. Interested students will send a letter of inquiry and résumé directly to the contact and location you list. Additional internships will be posted as received at www.amstat.org/education. Contact Rebecca Nichols at (703) 684-1221, Ext. 1877, or [email protected] if you have any questions.

38 Amstat News December 2009 EDUCATION

Abbott direct interaction with professional staff respon- Abbott Park, Illinois sible for research and development of testing and intervention programs. Interns participate in analy- Number of Positions: Multiple sis of real or simulated data in areas such as equat- Type of Student: Pursuing MS or PhD in ing, cognitive diagnostics, computer-based testing, statistics or biostatistics validity, reliability, test theory, and score reporting. Deadline: February 15, 2010 Information and application materials are available at www.act.org/humanresources. Interns are provid- The clinical statistics department within Global ed with a $5,000 stipend, plus reimbursement for Pharmaceutical Research and Development at round-trip transportation costs. A $1,000 supple- Abbott anticipates having internships available in mental housing allowance is available for appli- May/June and lasting 10–12 weeks. Housing will cants living outside a 50-mile radius. An additional be provided to qualified applicants. Interns will program objective is to increase representation of be provided with hands-on experience and given women and minority professionals in measurement an opportunity to build their understanding of and related fields. ACT is an equal opportunity the pharmaceutical industry and Abbott. The suc- employer and values diversity in people and ideas. cessful candidate will be assigned specific projects in support of one of Abbott’s global project teams Contact: Mark Larson, Human Resources Dept., and work under the guidance of a senior statisti- ACT, Inc., 500 ACT Drive, P.O. Box 168, Iowa cian (mentor) to perform statistical analyses of City, IA 52243-0168; (319) 337-1763; (319) 341- data from clinical trials and/or conduct statistical 2450 (fax); [email protected] research in areas of interest to the clinical statistics department. The successful candidate also may have the opportunity to participate in statistical seminars and workshops. At the conclusion of the intern- American Association for the ship, interns will be expected to give a presentation Advancement of Science (AAAS) - summarizing some aspect of their work. Applicants Mass Media Science and Engineering must be enrolled in a graduate-level curriculum Fellowship leading to an MS or PhD in statistics or biostatis- Washington, DC tics, have completed at least one full year of study, be in good academic standing, and continue to be Number of Positions: 15–20 enrolled in graduate school the fall season follow- Type of Student: Exemplary senior undergraduate ing the potential internship. In addition, applicants and graduate science, engineering, and mathe- must demonstrate excellent communication, team- matics students work, and problemsolving skills. Deadline: January 15, 2010 Contact: To submit your résumé, use our online The AAAS Mass Media Science and Engineering career center at www.abbott.us/careers, U.S. Jobs, Fellowship seeks to increase communication skills in Search Keyword 69068BR. student scientists. Fellows work for 10 weeks during the summer at mass media sites nationwide, including the Los Angeles Times, Scientific American, and National Public Radio. Fellows use their academic training in ACT, Inc. the sciences as they research, write, and report today’s Iowa City, Iowa headlines, sharpening their abilities to communicate Number of Positions: Up to 10 complex scientific and technical issues to the public. Applicants must be enrolled in the natural, physical, Type of Student: Doctoral student enrolled in sta- health, engineering, computer or social sciences, or tistics, measurement, educational or quantitative mathematics to apply. Students enrolled in English, psychology, or a related doctoral program at an journalism, science journalism, or other nontechni- institution in the United States cal fields are not eligible. Candidates can apply up to Deadline: February 12, 2010 one year after graduation or defense of their thesis. ACT conducts an eight-week summer internship pro- $4,500 stipend plus travel expenses. Visit www.aaas. gram for outstanding doctoral students interested in org/programs/education/MassMedia for an application careers related to assessment and educational studies. and more information. The 2010 program will run from June 7 to July 30 Contact: Stacey Pasco, Manager, Mass Media at ACT’s headquarters in Iowa City, Iowa. The sum- Program, AAAS, 1200 New York Ave. NW, mer internship program provides practical experience Washington, DC 20003; (202) 326-6441; (202) through the completion of a project, seminars, and 371-9849 (fax); [email protected]

December 2009 Amstat News 39 Amgen Inc. only), résumé, and cover letter to the contact below. Thousand Oaks and San Francisco, California; All requested documents should be mailed or faxed. Seattle, Washington For more information about the department of pediatrics, visit www.arpediatrics.org. Number of Positions: Multiple Contact: Hannah Feild, Arkansas Children’s Type of Student: PhD Hospital Department of Pediatrics, University of Deadline: February 12, 2010 Arkansas for Medical Sciences College of Medicine, Interns will work closely with a senior-level statis- 1 Children’s Way, Slot 512–43, Little Rock, AR tician on topics related to the design and analysis 72202; (501) 364-6631; (501) 364-1431(fax); of clinical trials and/or nonclinical research. Amgen [email protected]. research and development uses science and innova- tion to dramatically improve people’s lives in various therapeutic areas, including oncology, nephrology, Axio Research LLC bone metabolism, and inflammation. At the con- Seattle, WA clusion of the internship program, interns will give Number of Positions: Two a presentation summarizing their work. Applicants Type of Student: Bachelor’s degree in math, statis- must be a current PhD student who has completed tics, or computer science; bachelor’s degree in one year of PhD work in biostatistics or statistics another field with one year of experience or and a master’s degree in biostatistics or statistics. training in statistical programming; enrolled in a Additionally, proficiency in SAS or S-Plus on either graduate degree program, preferably biostatis- a UNIX or NT platform is preferred. As an EEO/ tics; master’s-level candidate preferred AA M/F/D/V employer, Amgen values and encour- ages diversity in the workplace. To apply, visit www. Deadline: April 30, 2010 amgen.com, click on the careers link, select job Interns provide SAS testing and statistical program- search, and then enter NB50965117 in the search ming and analysis support for research projects. field. You also may search by selecting career category, They will generate SAS programs to analyze and then college job. produce reports based on clinical data and may per- Contact: Erin Doyle, Amgen Inc., University form statistical analyses (including preparations for Relations Department, One Amgen Center Drive, data monitoring committee reports, integrated sum- 19-1-A, Thousand Oaks, CA 91320; (805) 447- maries of efficacy or safety, final study reports, and 6289; (805) 498-8131 (fax); [email protected] publications). Previous experience in this or a similar position is preferred. Creativity; good oral and writ- ten communication skills; and the ability to take ini- Arkansas Children’s Hospital, tiative, balance multiple tasks, and work with others Department of Pediatrics, University are necessary. Visit www.axioresearch.com. of Arkansas for Medical Sciences Contact: Anita Richard, Human Resources Manager, Little Rock, Arkansas Axio Research LLC, 2601 - 4th Ave., Suite 200, Number of Positions: One Seattle, WA 98121; (206) 577-0278 (direct); (206) 547-2829 (main); (206) 547-4671 (fax); anitar@ Type of Student: Graduate axioresearch.com Deadline: January 31, 2010 Summer intern will work with biostatisticians and clinical investigators to provide statistical expertise Boehringer Ingelheim in the design, evaluation, and analysis of research Pharmaceuticals studies. Arkansas Children’s Hospital (ACH) is one Ridgefield, Connecticut of the largest pediatric health care centers in the Number of Positions: Four nation and the only facility in Arkansas dedicated Type of Student: PhD candidate within one year of exclusively to children. Whether an applicant will degree completion be offered a position will depend on ACH’s need and funding, as well as the applicant’s qualifications. Deadline: February 25, 2010 Ideal candidates should be proficient in SAS and R. Previous research experience is highly valuable, Interns will become familiar with the highly regu- but not required. To apply, send an undergraduate lated pharmaceutical industry, applicable standard and graduate transcript (request for undergraduate operating procedures, and programming standards transcripts may be waived for international students adhered to within the biostatistics and data manage- ment department. They also will provide support to

40 Amstat News December 2009 the biometrics and data management statistical group required to give a presentation about their project as needed. This may include writing TSAP, QC, at the conclusion of the internship. Applicants must programming, literature review, and implementa- be graduate students who are enrolled in a full-time tion of technical statistical analyses. Internships are doctoral program in one of the areas listed above 12–14 weeks in late May to August. Apply at www. and who have completed a minimum of two years boehringer-ingelheim.com/corporate/home/home.asp of coursework toward their PhD or EdD prior to for requisition # INTSRMD0109. the program start date. Contact: Sheenah Mische, 900 Ridgebury Road, Contact: ETS Summer Internship Program for Ridgefield, CT 06877; (203) 798-5767; (203) 778- Graduate Students – MS 19-T, 660 Rosedale Road, 7731 (fax); [email protected] Princeton, NJ 08541-0001; (609) 734-5543; [email protected] Boehringer Ingelheim Pharmaceuticals Eli Lilly and Company Ridgefield, Connecticut Indianapolis, Indiana Number of Positions: One Number of Positions: Two to four Type of Student: MS in biostatistics (preferable) Type of Student: PhD with two years of complet- Deadline: February 25, 2010 ed graduate work Deadline: January 31, 2010 The intern will become familiar with the highly reg- ulated pharmaceutical industry, applicable standard The global statistical sciences division of Eli Lilly operating procedures, and programming standards and Company anticipates having several intern- adhered to within the biostatistics and data man- ship positions available in May or June and lasting agement department. The intern will work closely 12 weeks. Interns will receive practical experience with a programmer to provide SAS programming and the opportunity to build an understanding support during both the conduct and reporting of the pharmaceutical industry and Eli Lilly and phases of a . He or she will assist in the Company. Ideal candidates will have completed at production of tables, listings, and figures, using least two years of graduate work and have strong both the company standard macros and custom SAS programming skills. Successful candidates will SAS code. He or she also will be involved in the be assigned specific projects to work on under the quality control of the tables, listings, and figures guidance of a research scientist/principal research and document the outcome of the testing accord- scientist (mentor). Applicants must be enrolled in ing to standard operating procedures. Internships a graduate-level curriculum leading to a PhD in are 12 weeks, from June to August. Apply at www. statistics or biostatistics. Demonstrated leadership boehringer-ingelheim.com/corporate/home/home.asp and ability to influence; excellent communication, for requisition # INTSRMD0209. teamwork, and interpersonal skills; strong problem- solving skills; creativity and innovation; and self- Contact: Sheenah Mische, 900 Ridgebury Road, management skills preferred. To apply, visit www. Ridgefield, CT 06877; (203) 798-5767; (203) 778- lilly.com/careers and refer to Job ID 400057. 7731 (fax); [email protected] Contact: Soomin Park, Eli Lilly and Company, Lilly Corporate Center, Indianapolis, IN 46285; (317) Educational Testing Service 651-2167; (317) 651-9964 (fax); park_Soomin@ Princeton, New Jersey lilly.com Number of Positions: TBD Type of Student: PhD Energy Information Administration Deadline: February 1, 2010 (EIA) Selected interns will participate in research under Washington, DC the guidance of a senior staff member in measure- Number of Positions: Many ment theory, validity, natural language processing Type of Student: Undergraduate and graduate and computational linguistics, cognitive psychol- Deadline: February 26, 2010 ogy, learning theory, linguistics, speech recognition and processing, teaching and classroom research, The EIA invites qualified undergraduate and gradu- statistics, and/or international large-scale assess- ate students to apply for a summer internship in ments. Interns also will participate in seminars and Washington, DC. Opportunities are particularly workshops on a variety of topics. Each intern is

December 2009 Amstat News 41 available to students majoring in economics, math- Genentech, Inc. ematics, statistics, engineering, operations research, South San Francisco, California business/finance, and web development. Duties and responsibilities could include assisting with data Number of Positions: Six to eight analysis and forecasting; developing and designing Type of Student: Graduate, pursuing PhD in statis- modeling systems, surveys, or reports; researching tics, biostatistics, or related field trends and issues in domestic and international ener- Deadline: January 31, 2010, but offers may be gy markets; and developing web sites. Internships made earlier are paid according to the federal government GS Biostatistics summer interns work for 10–12 weeks schedule. Salaries usually range from $5,200 to under the supervision of experienced biostatis- $9,500 for the 10-week program. To apply, visit ticians on theoretical or applied problems with www.eia.doe.gov/careers and click on internships. direct relevance to ongoing clinical or nonclinical Applications will be accepted from mid-December drug development research in oncology, immunol- 2009 to February 2010. ogy, ophthalmology, and virology. Specific topics Contact: EIA Recruitment Team, [email protected] range from problems in genomics and translational research to late-stage clinical trials and post-market- ing evaluations. At the end of the internship, stu- Geisinger Center for Health Research dents give a department-wide presentation on their Danville, Pennsylvania research topic. It is not uncommon for an intern Number of Positions: Two to summarize their work in a peer-reviewed pub- lication. Applicants must be at least 18 years old Type of Student: PhD and a current graduate student pursuing a PhD in Deadline: January 31, 2010 statistics or biostatistics who has completed at least Geisinger Center for Health Research is accepting one year of graduate work by May 2010 and who applications for funded summer graduate intern- will be returning to school in the fall of 2010. The ships. Interns will work with experienced statisti- applicant must be legally authorized to work in the cians and clinical investigators in the design and United States. In addition, applicants should have a analysis of research projects originating from special- good working knowledge of R, S-Plus, or SAS and ty areas such as childhood obesity, weight-loss sur- have good communication skills. gery, autism, stroke, cardiovascular disease, diabetes, Contact: Send CV, personal statement of interest, and hypertension, genomics, and overactive bladder. In a letter of recommendation to [email protected] some cases, interns may be able to suggest a suitable research project on which to work. Candidates with interest and/or expertise in comparative effective- GlaxoSmithKline Pharmaceuticals R&D ness research, causal inference, or machine learn- King of Prussia, Pennsylvania ing are encouraged to apply. Interns will prepare a written report and brief presentation summarizing Number of Positions: Four their work and forming a permanent record of their Type of Student: Graduate student in statistics or efforts. Qualified candidates must be enrolled in a biostatistics PhD program in statistics or biostatistics and have Deadline: December 15 to start in January 2010; completed at least two years of graduate work by May 1 to start in July 2010 May 2010. Candidates must have good commu- In our student co-op program, students will work nication skills and an eagerness to work with real- with pharmaceutical industry statisticians on exper- world data. Start dates and durations are flexible. imental design and data analysis projects in a variety A housing stipend will be provided. Applicants of drug discovery and development areas. Positions should submit a résumé/CV, cover letter detailing are available in preclinical studies and clinical phar- research interests or goals for the internship, and macology modeling (phase I trials). Positions are names and contact information for two references. targeted for 5–12 months. Starting dates are nego- Visit www.geisinger.org/professionals/intern for an tiable. Some knowledge of SAS and S-plus/R is pre- online application form. ferred. Email a cover letter and résumé with a list of Contact: Jerry Foley, Geisinger Center for Health statistics courses taken, including textbooks used. Research, Geisinger Health System, 100 N. Contact: Younan Chen, Principal Statistician, Academy Ave., Danville, PA 17822-4400; (570) GlaxoSmithKline R&D, 709 Swedeland Road 214-5529; [email protected] UW2291, King of Prussia, PA 19406; (610) 270- 7089; (610) 270-5523 (fax); [email protected]

42 Amstat News December 2009 Google, Inc. mathematical topics are offered through the Hope College Mathematics Department. Applicants Mountain View, California; New York, New York; must be U.S. citizens. Seattle Washington Contact: Nathan Tintle, Mathematics Department, Number of Positions: Four Hope College, 27 Graves Place, Holland, MI Type of Student: PhD 49423; (616) 395-7272; (616) 395-7123 (fax); Deadline: February 1, 2010 [email protected] We supply interesting problems, lots of relevant data, and a chance to work with a Google statistician Joint Program of Survey and software engineers who are building the latest and greatest Google services. You provide imagina- Methodology (JPSM) tion and analysis/modeling skills. The workplace Washington, DC environment is fun and friendly, but serious about Number of Positions: Up to 30 technical challenges and performance expectations. Type of Student: Undergraduate Applicants should be current PhD students who Deadline: February 1, 2010, 5 p.m. EST have completed at least one year of course require- ments. They should also be comfortable in data-rich JPSM is conducting a nationwide search for a lim- environments and have requisite computational ited number of junior fellows. This unique expe- skills, including high proficiency in R. Familiarity rience combines paid research assistantships with with scripting languages (e.g., shell, python, perl, ongoing educational seminars. Successful applicants gawk) also may be needed. The internship program will work in one of the federal statistical agencies is 10 weeks in duration and concludes with a poster in Washington, DC, during the summer of 2010. presentation. Applicants should submit a cover let- Interns will learn how data gathered from house- ter, CV, and letter of recommendation from a fac- holds and economic units are used to track and ulty member. identify trends. They will work on key indicators Contact: Anu Zutshi, Technical Recruiting, Room of unemployment, crime, consumer prices, popu- 303B, Bldg. MTV-41, 1600 Amphitheater Parkway, lation migration and growth, agricultural produc- Mountain View, CA 94043; [email protected] tion, educational performance of young people, and transportation trends. Successful applicants will participate in seminars on and Hope College explore career options in survey research, which may include JPSM-sponsored graduate degree programs. Holland, Michigan For application forms and more information, visit Number of Positions: Three www.jpsm.umd.edu. Type of Student: Undergraduate Contact: JPSM, 1218 Lefrak Hall, College Park, Deadline: February 26, 2010; applications MD 20742; (301) 314-7911; (301) 314-7912 (fax); reviewed as received [email protected] Undergraduate students with an interest in sta- tistical genetics are encouraged to apply to par- ticipate in Hope College’s nationally recognized Law School Admission Council (LSAC) undergraduate research program. Work with a Newtown, Pennsylvania team of undergraduate students on cutting-edge Number of Positions: One problems in statistical genetics leading to publica- Type of Student: Doctoral, preferably at disserta- tion in peer-reviewed journals and presentations tion stage at regional and national conferences. Visit http:// Deadline: March 15, 2010 math.hope.edu/reu.html for more information, a link to this year’s project descriptions, and an The summer intern is given the opportunity to carry application. Participants will receive a stipend of out independent research under the mentorship of $3,200 for the eight-week program, which runs LSAC research staff. from June 7 through July 30, 2010. Free apart- Contact: Lynda Reese, Associate Director of ment-style housing and funds for travel to/from Psychometric Research, Law School Admission Hope College will be provided. In addition to the Council, Box 40, 662 Penn St., Newtown, PA statistical genetics research group, research oppor- 18940; (215) 968-1369; (215) 504-1408 (fax); tunities in probability, topology, graph theory, [email protected] numerical analysis, dynamical systems, and other

December 2009 Amstat News 43 Los Alamos National Laboratory, problemsolving, statistical computing, and com- Statistical Sciences Group munication skills. Applicants must be enrolled in a graduate-level statistics program. If interested, Los Alamos, New Mexico visit www.lubrizol.jobs and apply for the intern Number of Positions: Multiple statistician position. Type of Student: Graduate Contact: Debbie DeRenzo, Corporate Recruiter, Deadline: Year-round; apply by February to be 29400 Lakeland Boulevard, Wickliffe, OH 44092; considered for summer positions (440) 347-1044; (440) 347-5317 (fax); debbie. [email protected] As graduate research assistant student interns, students will participate in interdisciplinary, col- laborative studies under the supervision of experi- Mayo Clinic College of Medicine enced statisticians from the Los Alamos National Rochester, Minnesota Laboratory Statistical Sciences Group. Activities Number of Positions: Six to eight will vary, but may involve data analysis, statistical programming, literature searches, and development Type of Student: Undergraduate, graduate, PhD and application of statistical methods. Students will Deadline: February 1, 2010 be expected to document their work in a technical The Mayo Clinic Division of Biomedical Statistics report or paper and will be provided opportunities and Informatics has multiple summer internship to present their work at a seminar, student poster opportunities for undergraduate students who have forum, or professional meeting. Position requires completed their junior year and graduate students graduate-level coursework in statistics, familiarity at all levels. Internships of six to nine months also with data analysis methods, and experience with may be offered. Interns will work with statisti- programming and statistical software. Excellent cians, bioinformaticists, and clinical investigators communication skills and the ability to work inde- on research projects in such areas as clinical trials, pendently also are expected. Applicants must sub- statistical genetics, and . Experience mit an online application to www.hr.lanl.gov/stuapp/ with SAS, S-PLUS, and R is preferred. Whether an default.asp. Applicants also should email a copy of applicant will be offered a position will depend on their materials to [email protected]. See www. their qualifications, the division’s need and funding, lanl.gov/education/grad/about.shtml for the graduate and the number of applicants. To apply, submit an internship program overview and requirements and up-to-date transcript, résumé, and cover letter at www.stat.lanl.gov for more information about the www.mayoclinic.org/jobs-rst. To check for current statistical sciences group. openings, enter “Intern-Biostats” as a keyword. For Contact: Statistical Sciences Student Programs more information, visit http://mayoresearch.mayo.edu/ Coordinator, Statistical Sciences Group, MS F600, mayo/research/biostat or www.mayoclinic.org. Los Alamos National Laboratory, P.O. Box 1663, Contact: Erika Wohlfiel, Administrative Assistant, Los Alamos, NM 87545; (505) 667-3308; (505) Division of Biomedical Statistics and Informatics, 667-4470 (fax); [email protected] Harwick 7, 200 First Street SW, Rochester, MN 55905; (507) 284-8763; (507) 284-9542 (fax); Lubrizol Corporation [email protected] Wickliffe, Ohio Number of Positions: One Merck Research Laboratories Type of Student: Graduate students in statistics Philadelphia, Pennsylvania, and Rahway, New Deadline: February 15, 2010 Jersey The R&D statistical sciences department is seek- Number of Positions: 15 ing applications for a three-month summer intern- Type of Student: Graduate ship. Whereas actual intern duties will depend on Deadline: February 15, 2010 the skills of the individual and current needs of the The biostatistics and research decision sciences department, possible areas of involvement include (BARDS) department has internships in biometrics performing data manipulation and analysis, assist- research (preclinical biostatistics), nonclinical statis- ing members of the department with consulting tics, clinical biostatistics, statistical programming, tasks, and programming of statistical algorithms. health economics, and epidemiology for full-time Training in regression modeling, design of experi- students pursuing an MS or PhD in statistics, biosta- ments, and data analysis is required, as are strong tistics, economics, or epidemiology. Interns will work

44 Amstat News December 2009 closely with an experienced pharmaceutical industry Type of Student: Students in a master’s degree statistician or epidemiologist to perform statistical program for statistics or persons who have analysis of data from and/or conduct statistical/epi- received a terminal master’s degree in statistics demiological research related to basic drug research, in the past 18 months clinical pharmacology, drug and vaccine develop- Deadline: Year-round internships available ment, pharmacogenomics, health economics, or epidemiology. To be considered, students must have The Mostly Math graduate intern will have the completed at least two semesters of graduate work opportunity to instruct high-school and college toward an MS or PhD in statistics, biostatistics, students in statistics, instruct K-college students in economics, or epidemiology by May 30, 2010; be math, perform data analysis of customer data, and returning to school in the fall of 2010; have effec- evaluate advertising campaigns. With respect to data tive oral and written communication skills; and analysis, the intern will develop skills in data man- have a good working knowledge of SAS, S-Plus, agement, statistical analysis, interpretation, report and/or R. Visit www.merck.com/careers/university to writing, and documentation of work. Applications create a profile and submit a résumé for requisition and information about stipends are available at #ADM003995 (statistics/biostatistics/economics) or www.mostlymath.biz. #ADM004002 (epidemiology). A letter of reference Contact: Monica Johnston, Mostly Math, 2500 from a professor is highly recommended; attach it in Camino Diablo, Suite 110, Walnut Creek, CA the same section of the profile as the résumé. Merck 94597; (415) 218-0951; [email protected] is an equal opportunity employer.

National Agricultural Statistics Monsanto Company Service (NASS) St. Louis, Missouri Fairfax, Virginia Number of Positions: One Number of Positions: Three Type of Student: Graduate Type of Student: Graduate (PhD preferred) Deadline: April 30, 2010 Deadline: March 1, 2010 The successful intern candidate will become part of a Intern positions are in NASS’ Research and fast-moving, multidisciplinary team that will assist in Development Division, which is constantly try- developing statistical meta-analyses of compositional ing to improve the agency’s ability to estimate and data generated on crops derived through modern forecast accurately using the latest developments biotechnology. The work will include data format- in , cognitive science, and ting, univariate and multivariate analyses using SAS, remote sensing. Applicants must be U.S. citizens. report preparation, and communication of results to Preference will be given to candidates having an the regulatory organization. In addition to specific interest in a future career with the agency. statistics-related work activities, the intern will gain knowledge of biochemical, nutritional, toxicological, Contact: Dale Atkinson, National Agricultural and environmental studies used in risk assessments of Statistics Service, 3251 Old Lee Highway, Room new crops. This position requires current enrollment 305, Fairfax, VA 22030-1504; (703) 877-8054; in a BS or master’s program in statistics or a related (703) 877-8042 (fax); [email protected] discipline with a concentration in statistics. Expertise in Excel and SAS is required. The research associate will have an interest in applications of modern bio- National Cancer Institute technology to sustainable agriculture. Excellent writ- Bethesda, Maryland ten and oral communication and interpersonal skills are essential. Number of Positions: Two Type of Student: Flexible Contact: Margaret A. Nemeth, Monsanto Company, 800 N. Lindberg Blvd., O3D, St. Louis, MO Deadline: Three months before prior to start 63167; (314) 694-3613; (314) 694-5925 (fax); (flexible) [email protected] Interns will be involved in clinical trials method- ological research, helping to prepare manuscripts (for publication) focusing on the design and analysis Mostly Math Education Services of clinical trials. For more information, visit http:// Walnut Creek, California prevention.cancer.gov/programs-resources/groups/b/ Number of Positions: One to four about/bergerv#Clinical-Trial-Training-Internships.

December 2009 Amstat News 45 This is an unpaid internship, but the intern will graduate students within an MS or PhD program engage in high-level research in important areas. in biostatistics, statistics, or a related area with at Contact: Vance Berger; (301) 435-5303; (301) 402- least 1.5 years of graduate work; have a working 0816 (fax); [email protected] or [email protected] knowledge of SAS, including SAS/GRAPH, and S-Plus; and have good verbal and written com- munication skills. A strong background in R and S-plus is helpful for one position. New York City Health and Hospitals, Department of Medical and Contact: Linda Finelli, 1 Health Plaza, E. Hanover, Professional Affairs, Division of NJ 07936; (862) 778-7404; (973) 781-2703 (fax); Statistics/Data [email protected] New York, New York Pfizer Global Research and Number of Positions: Three Development Type of Student: Master’s, DPh, MD, or PhD Midwest (Kalamazoo, Michigan, and St. Louis, Deadline: No deadline; interval from application Missouri); La Jolla, California; New York, New York; to approval is at least one month and Groton/New London, Connecticut We gather data from internal and external sourc- Number of Positions: One to two in Midwest; mul- es with an eye toward measuring and improving tiple in La Jolla; multiple in New York, multiple in the quality of medical care given in New York Groton/New London City’s public hospital system. The system consists Type of Student: Graduate in statistics, biostatis- of 11 acute care hospitals, two long-term hospi- tics, or a closely related field tals, six free-standing clinics, two nursing homes, two rehabilitation facilities, and an HMO. Much Deadline: January 31, 2010 of our research is for internal consumption; some The program will consist of up to 480 hours at the is presented nationally and published. Interns Pfizer Global Research and Development facilities help identify, gather, and organize data for analy- in Kalamazoo, St. Louis, La Jolla, New York City, or sis. Depending on qualifications and experience, Groton/New London, commencing as early as April interns may do some statistical analysis. A stipend and ending as late as December. The intern’s project of $7–$20 per hour may be possible. There is a maxi- will be biopharmaceutically oriented, with one-on- mum of 20 hours per week during the school year and one supervision by a senior staff statistician. It will 35 hours per week during vacations. be a hands-on learning experience involving both Contact: Ronald B. Low, HHC Room 1136, 346 statistical and related data review and data transfor- Broadway, New York, NY 10013; (212) 676-0929 mation programming tasks. The programming tasks or (212) 676 0923; [email protected] will involve use of SAS, R, and/or other statistical software on the UNIX or NT platforms. As part of the program, interns will prepare a written report Novartis Oncology, Biometrics, and and brief presentation summarizing their work and Data Management forming a permanent record of their efforts. To Cambridge, Massachusetts, Florham Park, New apply, send a cover letter and résumé. Include an Jersey anticipated date of graduation. Number of Positions: Five to six Contact: Liqiang Yang, Pfizer Global Research and Type of Student: At least 18 months of graduate Development, La Jolla Laboratories, 10777 Science work Center Drive, CB10-2332, San Diego, CA 92121; [email protected] Deadline: February 19, 2010 (858) 678-8276 (fax); The internship program is approximately 12 weeks RAND Corporation from May to August (dates flexible). Interns will work with senior-level statisticians and focus on Santa Monica, California; Washington, DC; statistical research in both early clinical develop- Pittsburgh, Pennsylvania ment using biomarkers and full clinical develop- Number of Positions: Variable ment in oncology. Topics include Type of Student: PhD including interval , Bayesian methods, Deadline: January 15, 2010 use of auxiliary variables, threshold regression mod- els, modeling, and simulation. Candidates must be RAND’s summer program is designed to provide valuable experience for PhD students interested in

46 Amstat News December 2009 applied research on important policy issues. To learn Significant Opportunities in more about statistics at RAND, visit www.rand.org/ Atmospheric Research and Science statistics. RAND has paid summer associate positions (SOARS) - UCAR available for graduate students working toward their doctoral degrees in statistics. Selected applicants are Boulder, Colorado offered opportunities to work on projects related Number of Positions: 10 to their interests and experience. Preference will Type of Student: Undergraduate be given to students who have completed most of Deadline: February 1, 2010 their course work and passed their initial qualifying exams. To submit an application, visit www.rand. SOARS, an undergraduate-to-graduate bridge pro- org/about/edu_op/fellowships/gsap. gram dedicated to increasing participation in the atmospheric and related sciences, offers summer Contact: Director, Summer Program, Summer_ internships for students. The program provides up [email protected]; Susan Paddock, Head, Statistics to four years of paid summer research, mentoring, Group, [email protected] community support, and funding for undergradu- ate and graduate education. Students from many SAS Institute disciplines are invited to apply their expertise to understanding the Earth’s atmosphere and to Cary, North Carolina use that understanding to improve life on Earth. Number of Positions: One SOARS seeks to involve more students from his- Type of Student: PhD students studying in the torically under-represented groups in the sciences, United States; students must have completed at including black or African American, American least two years of graduate work by the end of Indian or Alaska Native, Hispanic or Latino, spring semester 2010 female, students with disabilities, and first-gener- ation college students. SOARS welcomes GLBT Deadline: February 1, 2010 students. Protégés work with a team of scientists The statistical software development division at SAS at the National Center for Atmospheric Research is pleased to announce the SAS Summer Fellowship and partnering laboratories on a project matched in Statistics. Open to doctoral candidates in sta- to their interests and skills. They perform original tistics, biostatistics, and related graduate depart- research, prepare a scientific paper, and present ments in the United States, this fellowship offers their research at a colloquium. Protégés earn a com- the opportunity to work closely with professional petitive wage; housing in Boulder and transport to statisticians who develop software used through- and from Boulder is provided. Visit www.soars.ucar. out the world. The statistical fellow will contribute edu for more information. to research, numerical validation and testing, and Contact: SOARS Office, P.O. Box 3000, Boulder, documentation. The program provides the gradu- CO 80305; (303) 497-8622; (303) 497-8629 (fax); ate student with an excellent opportunity to explore [email protected] software development as a career choice. Eligible candidates must have completed at least two years of graduate work by the end of the spring semester Summer Institute for Training in of 2010 and must have demonstrated experience in Biostatistics (SIBS) statistical computing beyond the routine classroom Boston, Massachusetts; Atlanta, Georgia; Iowa use of statistical packages. We are particularly inter- City, Iowa; Raleigh/Durham, North Carolina; ested in candidates with a combination of compu- Pittsburgh, Pennsylvania; Tampa, Florida; tational and research experience in Bayesian com- Madison, Wisconsin; St. Louis, Missouri puting, structural equations modeling, functional Number of Positions: 20–25 at each site data analysis, , survey research methods, survival analysis, variable selection, clus- Type of Student: Undergraduate and beginning ter analysis, reliability analysis, or finite mixture graduate students majoring in mathematics, sta- models. We also are interested in candidates with tistics, biology, or other science who are U.S. citi- experience using distributed and parallel methods zens or permanent residents and who have an for statistical computing. The program provides a interest in quantitative methods salary and stipend for 12 weeks. Deadline: March 5, 2010 Contact: Maura Stokes, SAS Institute, SAS Campus SIBS provides a comprehensive six- to seven-week Drive, Cary, NC 27513; [email protected] program designed to expose undergraduate and begin- ning graduate students to the opportunities offered by

December 2009 Amstat News 47 a career in biostatistics and to encourage them to pur- engineering, computer science, and physics majors sue graduate study in the field. Participants will enjoy are preferred. Candidates should have evidence of instruction and lectures by recognized experts in the extracurricular involvement on campus or in the field; meet practicing biostatisticians, epidemiologists, community, strong communication skills, and lead- and statistical geneticists; and gain real-world experi- ership experiences/skills. ence working with data from internationally recog- Contact: Submit your résumé to www.travelers.com nized studies. The program covers tuition, housing, using Job ID 791650. meals, and extracurricular activities, and participants will earn college credit that can be transferred back to their home institutions. Details are available at the U.S. Census Bureau individual program web sites (see below). Applications Washington, DC, metropolitan area should be made to each program separately; there is Number of Positions: Multiple no restriction on to how many programs a student Type of Student: BS/BA/MS/MA/PhD may apply. Deadline: Continuous Contact: Boston University, http://sph.bu.edu/sibs; Emory University, www.sph.emory.edu/bios/SIBS; The U.S. Census Bureau has several summer posi- North Carolina State University/Duke Clinical tions for candidates interested in producing the Research Institute, www.stat.ncsu.edu/sibs; University nation’s official economic and demographic statis- of Iowa, www.public-health.uiowa.edu/biostat/ tics. Interns may work on a variety of applications, current_students/bsi; University of Pittsburgh, www. including survey design and analysis, evaluation of biostat.pitt.edu/sibs; University of South Florida, nonsampling errors, and coverage and measurement http://health.usf.edu/publichealth/epb/sibs/index.htm; error and analysis. These positions require excellent Washington University in St. Louis, www.biostat. communication and interpersonal skills and knowl- wustl.edu; University of Wisconsin, www.biostat. edge in one or more of the following areas: sampling wisc.edu/Educational_Resources/SIBS techniques, experimental design, times series analy- sis, regression analysis, linear models, exploratory data analysis, statistical inference, statistical analysis, Travelers Insurance Research and statistical computing, and applied probability. U.S. Development Internship Program citizenship is required. The U.S. Census Bureau is Hartford, Connecticut; St. Paul, Minnesota; an equal opportunity employer. The bureau is con- Chicago, Illinois tinuously accepting applications online at www. Number of Positions: Multiple census.gov. Click on Jobs@Census and go to student Type of Student: Graduate student pursuing mas- and research opportunities, then student temporary employment program. ter’s or PhD Deadline: January 31, 2010 Contact: Angela Jones, Human Resources Division, 4600 Silver Hill Road, Washington, DC The Travelers internship programs provide qualified 20233; (301) 763-3371; (301) 763-4706 (fax); students an excellent opportunity to gain first-hand [email protected] business experience; receive valuable on-the-job training; and work with the research and statistical modeling staff engaged in data mining, predictive Westat modeling, and other actuarial research while apply- ing advanced statistical tools. Interns will use SAS Rockville, Maryland and other software tools to retrieve and summarize Number of Positions: Two data in preparation for analysis. They also will per- Type of Student: Graduate majoring in statistics form statistical analyses using statistical software Deadline: March 15, 2010 and be expected to interpret the results and iden- tify significant outcomes, as well as produce reports Westat seeks summer interns for its statistical group. to explain findings. We offer a challenging profes- Interns will work closely with survey sampling stat- sional work experience in the insurance industry, isticians in sample design and selection, sampling business overviews and career development work- frame development, weighting, imputation, vari- shops, interaction with all levels of management, ance estimation, QC procedures, and evaluation of a mentor program, and a competitive hourly rate. statistical modeling based on survey data. Subsidized apartments are available for students Contact: Lloyd Hicks, 1600 Research Boulevard, who live beyond a commutable distance. Positions Rockville, MD 20850-3195; (301) 610-4960; are available beginning in May or early June for (301) 942-2034 (fax); [email protected] n 10-12 weeks. Math, statistics, ,

48 Amstat News December 2009 From left: Criselda Toto, Worcester Polytechnic Institute; Kenneth Lopiano, University of Florida; and Joshua Habiger, University of South Carolina

Three Interns Share Insights from NISS-NASS Projects

Last summer, three graduate students traveled to the National Institute of Statistical Sciences (NISS) in Research Triangle Park, North Carolina, to team up with postdoctoral fellows, researchers from the National Agricultural Statistics Services (NASS), and university professors. They each worked on a different, complex research problem in agricultural statistics as part of an ongoing NISS-NASS partnership. Next summer, they will return to NISS to follow up on the research they conducted. Here, each student tells of his or her internship experience.

Team 1: Multivariate Imputation of Agricultural Resource Management Survey alking up to the NISS-SAMSI building Data for Implementation in Agricultural with only a pen, note pad, and Statistical Resource Management Survey - Phase III Analysis with Missing Data by Donald RubinW and Roderick Little in hand, I was struck by Joshua Habiger, University of South an ever-so-familiar emotion. It was a mixture of ner- Carolina vousness and excitement fueled by the uncertainty of the upcoming weeks. It was the feeling I felt just sec- onds before barking the first words of the semester as What is NASS’ current imputation method? an instructor. But this time, the uncertainty had a full What kind of software do they use? What would tank of gas. I had just committed myself to work on my team members be like? Would I be able to get a a problem called Multivariate Imputation Methods publication out of the summer’s work? I was fairly for NASS’ Agricultural Resource Management certain I would be more of an office assistant than Survey—a problem I knew little about. a problemsolver. After all, I was the lowly graduate

December 2009 Amstat News 49 student on a team consisting of a postdoctoral fel- resource. Postdocs and graduate students from low, statistics professor, economics professor, math- teams 1, 2, and 3 spent many days in the “super ematical statistician, and economist. secret data room,” mulling through massive NASS It turns out my role was far from what I expect- data sets and creating graphs and summaries. We ed. It would be Michael Robbins (the postdoc) and shared the challenge of deciphering programming I who would tackle the problem full time over the problems, counter-intuitive figures, and other next 10 weeks. Other members of the team would anomalies in the data. spend several days or weeks at a time at NISS, pro- After a quick 10 weeks, the problem was start- viding guidance, suggestions, and a plan of action ed—not solved. I can’t help but think, “Wow! I can’t for the upcoming days, but would soon be drawn believe how much I learned this summer!” I find back to their busy careers. I never felt as if we were myself ready to make a dent in an additional field put on the back burner, however. Whenever we had (my dissertation topic is multiple testing, not impu- questions or concerns, everyone in the group was tation) and looking forward to next summer. While quick to respond via email, phone, or teleconfer- next summer will mark the end of the project for ence. Even NASS employees who were not assigned me, I believe this internship prompted the begin- to the project spent a great deal of time tracking ning of several relationships with future collabora- down bits of information and sorting through SAS tors: Michael Robbins (NISS-NASS), Sujit Ghosh code to help us out. (North Carolina State University), Barry Goodwin Other teams at NISS with their graduate stu- (North Carolina State University), Darcy Miller dents and postdocs also turned out to be a valuable (NASS), and Kirk White (ERS).

Team 2: Design and Estimation Methodologies for Estimating the Number of Small Farms from NASS Sampling Frames After our brainstorming sessions, I found Kenneth Lopiano, University of myself thinking about ways to improve upon each Florida approach, what the limitations were, and how these limitations could be addressed. Rather than being discouraged by an idea not panning out, Linda Young—a senior faculty adviser—emphasized that he opportunity to work as a graduate stu- research is usually two steps forward and one step dent with NISS on a project with the USDA back. For me, the take-home message was to always and NASS was priceless. As I only recently remember to build upon each step forward. Tpassed my qualifying exam, this was the first time I Once the advisers and other NASS team researched a problem without a known solution. members left me and postdoctoral fellow Patricia While working alongside statisticians from NASS, Gunning to the problem at hand, I found myself professors from the University of Florida and North coming up with ideas that took me two steps for- Carolina State University, and a postdoctoral fellow ward, but then reaching an obstacle that took me at NISS, I started to learn what questions to ask one step back. With Young’s advice in mind, I when conducting research. was able to recognize the net gain and persevere. When the project began, we expected to imple- Working as a team, we were able to come up with ment a capture-recapture methodology to reconcile viable methods to implement. disparate estimates based on two frames. However, This summer’s work gave us direction, but there once we received the data, it was clear that was not is more to be done. I look forward to thinking going to work. We had to go back to the drawing about our problem when I return to the University board and ask ourselves what alternative approaches of Florida and coming back to NISS next summer we could take. with more ideas.

50 Amstat News December 2009 Team 3: Statistical Multi-Source Predictive am at the point in my graduate student life at Models and Error Estimation in Support of which I am evaluating possible career paths, Crop Production Forecasts and Estimates and my experience as a student intern for NISS-NASSI provided me with much insight into Criselda Toto, Worcester Polytechnic what is in store for me. It made me realize that Institute research will be a major part of my career, what- ever path I decide to take. This realization gave me the enthusiasm to learn valuable research skills, while the program set-up provided me with the opportunity to develop them. Our team’s project focused on building a statis- critically, however, and to be more sensitive to the tical predictive model that mimics the forecasting pros and cons of each step we took. I believe these process for crop production conducted by NASS. are valuable lessons, not just in research, but in life. This forecasting process involves multiple sources of Learning how statistics is used in forecasting information, including the opinions of agricultural agricultural production also brought a new area experts. Our goal was to incorporate the subjectivity of interest to my list. Having been in academia for in the process into the , making the nearly my whole life, the experience I’ve had doing process more objective. research on real-life problems is limited. This expe- As the junior members of the team, postdoctoral rience opened a door for possible application in my colleague Jay Wang and I were given the major task dissertation. I also made valuable contacts and built of working on the theoretical and computational relationships with those involved in the project, aspects of the statistical modeling. Our team men- which is something I deeply appreciate. Overall, tors—both from academia and government—guid- being an intern at NISS was a wonderful learning ed us, but our perseverance and patience were put experience. I am grateful to have been part of this to test, sometimes leading to frustration and misun- research collaboration. n derstanding. These trials trained us to think more

December 2009 Amstat News 51 52 Amstat News December 2009 CAUSE, SERC Provide Teaching Activities

he Consortium for activities come with complete of the SERC modules, review and the Advancement of lesson plans, including learn- revise it, and submit it to be post- Undergraduate Statistics ing goals, context for use, and ed on the web site. Since then, TEducation (CAUSE) has collabo- teaching materials (e.g., hand- 13 activities have been reviewed, rated with the Science Education outs, teaching tips, assessment revised, and posted. To continue Resource Center (SERC) project items, and references). In addi- adding to this collection, CAUSE for the past three years to connect tion, three new modules were will incorporate items presented activities for statistics classes created to reflect instructional during the new activity webinar with details of different peda- methods that are particularly series (see www.CAUSEweb.org/ gogical methods. relevant to teaching a statistics webinar/activity), hosted by Leigh The SERC project, headed course: Making and Testing Slauson of Capital University on by Cathy Manduca of Carleton Conjectures, Teaching with Data the fourth Tuesday of each month College, has produced mod- Simulations, and Creating and at 2:30 p.m. ules for a variety of pedagogical Testing Models. The SERC modules can be methods, along with information Two years ago, in conjunction located at http://serc.carleton. about how and why to use each with the second United States edu/sp/cause/index.html or www. method. Examples of these meth- Conference on Teaching Statistics, CAUSEweb.org by selecting the ods include the following: a workshop was held in which 14 link to “switch to browse by ped- Campus-Based Learning: statistics instructors were invited agogical method.” n The campus is explicitly to bring an activity linked to one linked with education; the campus buildings and grounds are used as teaching tools Cooperative Learning: Students work in structured groups to accomplish learn- ing goals Gallery Walk: Students are actively involved in synthe- sizing important concepts, consensus building, writing, Member Spotlights and public speaking Game-Based Learning: Faculty who want to start using games to help teach WANTED are assisted Interactive Lectures: Short The managing editor of Amstat News is searching interactive activities are pro- for ASA members who are willing to put themselves vided that involve students in the spotlight and write a brief article about their and break up a lecture life, to be published in an upcoming issue. The modules are linked to The article should be 1,000 or fewer words and activities in a variety of disci- contain professional and personal information. plines, and as a result of the col- Please include a photo or two of yourself and laboration with CAUSE, statis- email it to Amstat News Managing Editor Megan tics activities are now included Murphy at [email protected]. in many of the modules. These

December 2009 Amstat News 53 54 Amstat News December 2009 PEOPLE NEWS

Karl Peace David L. Donoho Receives Georgia Southern University faculty member Karl E. Honorary Degree Peace was recently honored on the floor of the U.S. House of Representatives for his numerous professional and charitable contributions. Peace is a Georgia Cancer Coalition Distinguished Cancer Scholar, senior research scientist, and pro- fessor of biostatistics in the Jiann-Ping Hsu College of Public Health at Georgia Southern University. Peace Rep. Robert Wittman (R-VA) cited Peace’s numer- inclusion in the Cong- ous contributions to drug ressional Record,” said Peace. research and development, “This is good for the schools public health, biostatistics, with which I’ve been associat- and philanthropy. He said, ed and especially for our “Dr. Peace has a dedicated Jiann-Ping Hsu College of record of philanthropy to David Donoho and the Chicago Department of Statistics. From left: Public Health at Georgia education. He has created 21 Southern University.” Peter McCullagh, Dan Nicolae, Mathias Drton, David Wallace, Ron endowments at five institu- Thisted, David Donoho, Michael Stein, Stephen Stigler, Mary Sara Peace was recently elected tions, including three at his McPeek, Steve Lalley, Debashis Mondal, and Mei Wang as the chair-elect of the statis- alma mater—the Medical tics section of the American College of Virginia—and one n October 9, David L. Donoho received the hon- Public Health Association. at Randolph-Macon College. orary degree of Doctor of Science from The He is the founder of the He endowed the Jiann-Ping University of Chicago. The occasion was a special Biopharmaceutical Applied Hsu College of Public convocation,O the 500th in the university’s history, and Statistics Symposium and the Health, the first school of Donoho’s was one of four degrees awarded. Journal of Biopharmaceutical public health in the Univ- In presenting the degree, the university’s president— Statistics. ersity of Georgia system. His mathematician Robert Zimmer—said, “David L. Donoho Peace is the recipient of endowments have enabled is a mathematical statistician and also one of the more influ- numerous citations and hundreds of students to com- ential applied mathematicians of his generation. Building awards and is a Fellow of the plete their undergraduate or upon the discipline of statistics, Donoho has developed American Statistical graduate degrees. Dr. Peace effective new approaches to constructing low-dimensional Association. He is also the has generously donated time representations for modern high-dimensional data prob- author or editor of nine and resources to organiza- lems. His work provides new insight into some of the most books and the author or co- tions such as the American pressing scientific questions of the present day.” author of 200 articles. His Cancer Society, the Georgia Donoho is the Anne T. and Robert M. Bass Professor in autobiography, Paid in Full, Cancer Coalition, the the Humanities and Sciences and professor in the depart- was released earlier this year Southeast Georgia Cancer ment of statistics at Stanford University. and traces his life from his Alliance, and the Southwest The University of Chicago awards honorary degrees only childhood on a sharecropping Georgia Cancer Coalition for distinguished scholarship. Previously, honorary degrees farm in Georgia to his rise in that are dedicated to cancer have gone to R. A. Fisher, Harold Hotelling, Jerzy Neyman, the pharmaceutical industry research, treatments, and Maurice S. Bartlett, John W. Tukey, Fred Mosteller, Erich L. and to his work in higher cures.” Lehmann, Charles M. Stein, , , education and philanthropy. “I am grateful to con- David Aldous, Persi Diaconis, and Grace Wahba. n Read more about Peace’s gressman Wittman for his contributions at https:// acknowledgement of my my.georgiasouthern.edu/index. achievements on the floor of php?option=com_content&id= the U.S. Congress and their 364.

December 2009 Amstat News 55 Obituary “Sampling for Social statistical challenges, which Science, and the American Research Surveys 1947– Steve pursued tirelessly.” Statistical Association. He Irene Hess 1980” and “Controlled Lagakos was chair of the was awarded an honorary Selection Continued.” Her HSPH Department of doctorate from the National latest publication, “The Biostatistics from 1999 to and Kapodistrian University Practice of Survey Research 2006, during which time of Athens in 2006. He at the Survey Research the department investigated received the Spiegelman Center,” was completed in infectious diseases, psychiat- Gold Medal Award from the the fall of 2007. ric statistics, environmental American Public Health To read more about Hess’s statistics, and statistical Association in 1983 and a life, visit the ASA’s Statistic- genetics. Observed current citation for outstanding ians in History page at chair, Victor De Gruttola, teaching from HSPH in the www.amstat.org/about/ in an email to HSPH com- years 1985 to 1988. statisticiansinhistory. munity members: “Steve To read more about Lagakos played a central Lagakos’ life, visit www. leadership role in our hsph.harvard.edu/news/ Obituary department, in the school, press-releases/2009-releases/ Stephen Lagakos and among the international professor-lagakos-dies.html. Stephen Lagakos, profes- community of quantitative sor of biostatistics at the biomedical researchers. His Hess Harvard School of Public loss and that of his wife, Obituary Health (HSPH), died in Regina, and mother, Helen, Harvey Bennett a car accident on October is a terrible one for all of us. Irene Hess, 98, a survey statis- Lipman 12 in Peterborough, New Steve’s qualities of commit- Harvey Bennett Lipman, tician who trained graduate Hampshire. He was 63 years ment, passion, intellectual students in the details of age 57, died August 30 in old. His wife, Regina, and brilliance, and personal gen- Atlanta, Georgia. sampling at the Institute for his mother, Helen, also were erosity had a direct personal Social Research died July 5 Lipman earned his bache- killed in the daytime acci- impact on our lives, and his lor’s in mathematics from in Ann Arbor, Michigan, of dent, along with the driver contributions to biostatistics a cerebral hemorrhage. Knox College and his PhD in of the other car. and to AIDS research were statistics from Oregon State Hess was born in “Our School community fundamental.” Muhlenberg County, University. For more than 17 is deeply saddened by Lagakos served on the years, he worked at the Kentucky. Her father was a this unexpected and tragic Scientific Advisory Comm- mining engineer in Central Centers for Disease Control loss of Professor Steve ittee of the American and Prevention. He was a City. Her mother, who Lagakos,” said Julio Frenk, Foundation for AIDS graduated from Valparaiso member of the Phi Kappa Phi HSPH dean and T & G Research and was a partici- Society and the American College with her father, Angelopoulos professor of pant in a World Health worked at home. After grad- Statistical Association. public health and interna- Organization (WHO) con- Lipman played soccer in uating from Indiana Univ- tional development. sultation on neuropsychiat- ersity, Hess returned to high school and college and “Having joined our faculty ric aspects of HIV infection. continued to pursue his love Central City to teach math more than three decades From 1982 to 1987, he was and English at the local of the game by becoming a ago, Steve was a prominent co-director of WHO’s referee and teacher. He volun- junior high school from and respected professor, Collaborating Center for 1932 to 1942. In 1940, she teered at the 1996 Olympics cherished by those who had Cancer Biostatistics in Atlanta, performed in went to work with Leslie the benefit of working with Evaluation. He worked on Kish at the Survey Research plays, sang in choral groups, him and learning from him. several committees and pan- and played the cello. For Center. His seminal contributions els of the National Academy Hess was an active many years, he was a soloist at to the field of AIDS research of Sciences. He also served various synagogues. member of the American helped provide crucial statis- as statistical consultant to Statistical Association. She Lipman is survived by his tical foundations upon The New England Journal of wife of 21 years, Camellia was the first chair of the which we could better com- Medicine for more than a Section on Survey Research Jane; his mother, Joy; sister, bat this terrible disease. The decade. Sarah; and his brothers, Marc Methods and attended complexity of the analyses Lagakos was a member of and Mayer. n many JSMs. required to understand the Institute of Medicine, During her career, Hess HIV/AIDS and its treat- the American Association published numerous articles, ment presented enormous for the Advancement of including two monographs:

56 Amstat News December 2009 AWARD DEADLINES AND INFORMATION

Deadlines and Contact Information for ASA National Don Owen Award Awards, Special Lectureships, and COPSS Awards Each year, the San Antonio January 15, 2010 Harry Joe, chair, Presidents’ Award Committee Chapter presents the Don COPSS Presidents’ Award [email protected] Owen Award to a statisti- cian who embodies the three-fold accomplish- January 15, 2010 Michael R. Kosorok, chair, Elizabeth L. Scott COPSS Elizabeth L. Scott Award Award Committee ments of Donald B. Owen: [email protected] research, statistical consul- tation, and service to the February 1, 2010 Janice Derr, chair, W. J. Dixon Award statistical community. W. J. Dixon Award for Excellence in Committee Before his death in 1991, Statistical Consulting [email protected] Owen was distinguished professor of statistics at February 15, 2010 Eleanor Feingold, chair, Gertrude M. Cox Southern Methodist Gertrude M. Cox Scholarship Scholarship Committee University in Dallas, Texas, [email protected] and the author of seven textbooks, seven mono- February 15, 2010 Petruta C. Caragea, chair, Outstanding graphs, and more than 75 Outstanding Statistical Application Statistical Application Award articles in refereed journals. Award [email protected] He also trained 19 doctoral and master’s students, March 1, 2010 Kimberly Weems, chair, Edward C. Bryant served as an applied statis- Edward C. Bryant Scholarship for an Scholarship Committee tician for 10 years at the Outstanding Graduate Student in [email protected] Sandia Corporation, and Survey Statistics operated his own consult- ing firm that specialized in March 1, 2010 Telba Z. Irony, chair, Excellence in Statistical quality control. Owen was Excellence in Statistical Reporting Reporting Award Committee editor of Communications Award [email protected] in Statistics, associate editor of Technometrics, and asso- March 5, 2010 Jai Won Choi, chair, SPAIG Award Committee ciate editor of JASA. He SPAIG Award [email protected] edited more than 50 text- Rahul A. Parsa books, including many for [email protected] Taylor & Francis. Morteza Marzjarani [email protected] As a­­ sponsor of this award, Taylor & Francis promotes scientific March 9, 2010 Ken Goldberg, chair, Statistics in Chemistry Statistics in Chemistry Award Award Committee research, supports educa- [email protected] tional programs, and rewards outstanding aca- demic achievement in the March 15, 2010 Sally C. Morton, chair, Founders Award Founders Award Committee sciences. The San Antonio [email protected] Chapter is accepting nomi- nations for the 2010 Don March 15, 2010 Daniel Zelterman, chair, Samuel S. Wilks Award Owen Award from ASA Samuel S. Wilks Award Committee [email protected] chapters in North America. The nominee must be a member of the ASA, but is March 15, 2010 Chih-Ming Wang, chair, W. J. Youden Award not required to be a mem- W. J. Youden Award in Committee Interlaboratory Testing [email protected] ber of the nominating chapter. In addition to a cover letter that highlights March 15, 2010 June Morita, chair, Waller Education Award Waller Education Award Committee the accomplishments of [email protected]

December 2009 Amstat News 57 the nominee, the nomina- Julius Shiskin his career, he was known as For questions or more tion packet must contain Award an innovator. At the Census information, contact Steven the following: Bureau, he was instrumental Paben, Julius Shiskin Award Nominations are invited for in developing an electronic Committee secretary, at Name of the nominee the annual Julius Shiskin computer method for sea- [email protected] or (202) Memorial Award for sonal adjustment. In 1961, 691-6147. Degrees (titles, dates, Economic Statistics. The he published Signals of schools) award is given in recogni- Recession and Recovery, Waksberg Award Present position(s), fol- tion of unusually original which laid the groundwork lowed by significant for- and important contribu- for the calculation of Survey Methodology estab- mer positions (with dates) tions to the development of monthly economic indica- lished an annual invited List of major publications economic statistics or the tors, and he developed the paper series in honor of Joe having statistical content use of statistics in interpret- monthly report Business Waksberg to recognize his ing the economy. Conditions Digest to dissemi- contributions to survey List of activities related to Contributions are recog- nate them to the public. At methodology. Each year, a teaching and dissemination nized for statistical research, OMB, he developed the prominent survey statisti- of statistical knowledge development of statistical policies and procedures that cian is chosen to write a List of consulting activi- tools, application of infor- govern the release of key paper that reviews the devel- ties related to statistical mation technology tech- economic indicators and opment and current state of problems or editorial niques, use of economic originated a social indicators an important topic in survey contributions statistical programs, man- report. At BLS, he was methodology. The paper agement of statistical pro- instrumental in preserving reflects the mixture of theo- List of activities support- grams, or developing public the integrity and indepen- ry and practice that charac- ing the mission of the understanding of measure- dence of the BLS labor force terized Waksberg’s work. ASA and related profes- ment issues. data and directed the most The recipient of the sional organizations The award was established comprehensive revision in the Waksberg Award will receive To submit a nomination, in 1980 by the Washington history of the Consumer an honorarium and give the send six copies of the Statistical Society (WSS) Price Index (CPI), which 2011 Waksberg invited nomination packet by and is now cosponsored by included a new CPI for all address at the Statistics February 1 to John the WSS, National urban consumers. Canada symposium. The Schoolfield, Academic Association for Business Completed nominations paper will be published in a Technology Services, Economics, and ASA for the 2010 award must be future issue of Survey University of Texas Health Business and Economics received by March 5. Individ- Methodology. Science Center at San Statistics Section. uals and groups in the public ­The author of the 2011 Antonio, 7703 Floyd Curl Julius Shiskin, or “Julie,” or private sector from any Waksberg paper will be Drive, San Antonio, TX was the commissioner of the country can be nominated. selected by a four-person 78229-7931. Schoolfield Bureau of Labor Statistics The award will be presented committee appointed by can be contacted at (210) (BLS). Earlier, he served as with an honorarium of $750 Survey Methodology and 567-2128 or schoolfield@ the chief statistician at the and additional recognition the American Statistical uthscsa.edu with questions. Office of Management and from the sponsors. A nomina- Association. Nomination of Write “Owen Award” in the Budget (OMB) and chief tion form and list of previous individuals to be considered subject field of emails. economic statistician and recipients are available at as authors or suggestions for assistant director of the U.S. www.amstat.org/sections/ topics should be sent before Census Bureau. Throughout bus_econ/shiskin.html. February 28, 2010, to Dan Kasprzyk at DKasprzyk@ Mathematica-MPR.com. Previous Waksberg Award winners include Gad Volunteers Wanted Nathan, Wayne Fuller, Have you ever thought about serving on an ASA committee of interest to you? The success David Holt, Norman of the ASA depends on ASA committees and the volunteers who serve on them. Bradburn, J. N. K Rao, Each year, vacancies are filled in nearly all of the ASA’s 50+ committees, usually for a three- Alastair Scott, Carl-Erik year term. For more information or to volunteer or recommend another, go to www.amstat. Särndal, Mary Thompson, org/comm. Graham Kalton, and Ivan Fellegi. n

58 Amstat News December 2009 Jeanne E. Griffith Mentoring Award Nominations Sought Beth Kilss, 2010 Chair, Griffith Award Selection Committee

t is time to start thinking Award Committee about nominating an out- Emerson Elliott Beth Kilss (chair) standing supervisor, techni- calI director, team coordinator, or Carol House Stephanie Shipp other member of a governmental Dan Kasprzyk Clyde Tucker statistical staff who encourages Andy Orlin, Jeanne Griffith’s husband, serves as mentoring of junior staff in the emeritus member, thus providing continuity and federal, state, or local statistical historical perspective. system for the 2010 Jeanne E. Griffith Mentoring Award. Nominations will be accepted —Serving as a role model for junior staff through profes- beginning in January and must Griffith be submitted by March 26. The sional expertise, information, and insight; balancing colle- Photos of Cecco and Lin courtesy of Bob PeavyPhotography Bob of courtesy Lin Ceccoand of Photos award winner(s) will be deter- gial and personal roles; and including everyone across rank, mined by May 7. race, ethnicity, and seniority The award consists of a Nominations should be prepared in the form of a letter or $1,000 honorarium (to be split if memorandum summarizing the nominee’s actions that support there is more than one awardee), and encourage junior staff in the federal, state, or local statisti- a citation, and a plaque, which cal community. Nominations may be accompanied by up to will be presented at a ceremony six supporting letters, which should be attached to the nomina- in June. tion. Photo and email copies of support letters are acceptable. Winners are selected for Descriptions of what nominees actually do are the strongest their efforts to support the demonstration of candidate mentoring. Examples include “the work and develop the careers of mentor is a source of advice … counsels with long-term goals in junior staff. Examples of typical Cecco mind … thought I was well qualified even though I had some mentoring activities include the doubts … encourages staff to seek out positions that will increase following: their visibility and stretch their professional capabilities.” —Advising junior staff to The Jeanne E. Griffith Mentoring Award was established to help them create career honor Griffith, who died in August of 2001 after working for opportunities, network- more than 25 years in the federal statistical system. Throughout ing skills, and contacts for her career, and especially in her later senior management posi- growth and development tions at the National Center for Education Statistics and National Science Foundation, one of Griffith’s top priorities was to mentor —Counseling junior staff and encourage younger staff at all levels to learn, grow, and recog- and providing resources to nize and seize career opportunities as they came along. help develop their technical This year marked the first time in the award’s seven-year his- writing, analysis, presenta- tory that two winners were chosen, as well as the first time the tion, and organizational skills Lin ASA’s Government Statistics Section oversaw the award selection. and knowledge Kevin Cecco, chief of the Corporation Statistics Branch, Statistics of Income Division, IRS, and Lillian Lin, mathematical statisti- —Encouraging junior staff growth and career development cian in the Division of HIV and AIDS Prevention at the Centers through attendance and oral presentations at meetings with for Disease Control and Prevention, received their awards at a higher-level officials and the staffs of other agencies ceremony held on June 17, 2009, in Washington, DC. —Becoming involved in professional associations, training Nomination packages may be mailed or emailed to Jeanne E. courses, and conferences Griffith Mentoring Award Committee, The American Statistical Association, 732 N. Washington Street, Alexandria, VA 22314- —Motivating junior staff and building self confidence 1943; [email protected]. For more information, visit www. through feedback on their efforts, being a listener when amstat.org/sections/sgovt or contact Monica Clark at monica@ needed, and creating a caring and supportive environment amstat.org or Beth Kilss at [email protected]. n

December 2009 Amstat News 59 60 Amstat News December 2009 COMMITTEE NEWS

Professional Ethics Committee Updates Goals and Guidelines

he ASA’s Committee on guidelines for ethical practice are post- in epidemiology, law, and government Professional Ethics’ vision is to ed. The committee plans to add more described their personal ethical dilemmas increase members’ knowledge of materials, such as papers and presen- and, after some discussion and debate that ethicalT issues so they are more prepared tations dealing with ethical issues and included audience participation, revealed to face ethical challenges within their related work of other ASA committees their resolutions. professional careers. and professional associations. The session was so successful that the The committee’s activities are both The site also has an expanding list committee is planning another session on proactive and reactive. Concerning of ethical scenarios designed to increase ethical dilemmas for JSM 2010. Contact the latter, the committee is a resource sensitivity and awareness of the difficult Hurwitz at [email protected] if for ASA officers, the ASA Board of and sometimes precarious positions stat- you would like to present your ethical Directors, and ASA members. It provides isticians face. The committee aims to dilemma in a future JSM session. guidance on ethical issues that affect the continually add to this list so the sce- The committee is always looking for association or the work of statisticians narios can become an integral part of more interest and involvement from ASA worldwide. In recent years, the commit- continuing ethics education. Comments members. For example, the annual meet- tee has been asked for comments on and about the web site and ethical scenarios ing of the committee, which takes place recommendations for ethical issues con- for possible inclusion in the collection during JSM, is open to members. Also, cerning statistical dissemination, plagia- can be sent to Tom Petska, committee for members who want to stay involved rism, and accreditation. chair, at [email protected]. in ethical issues, participation in periodic On the proactive side, where the Another initiative of the committee is conference calls is welcomed. Further, as committee focuses most of its energies, to organize and sponsor sessions at the members rotate off the committee, inter- the goal is to improve the knowledge Joint Statistical Meetings, such as the est by other ASA members to join the and understanding of ethics and ethi- 2009 invited panel “Real-Life Ethical committee is encouraged. If you would cal issues among ASA members. To do Dilemmas Encountered in the Practice like to comment on the work or pri- this, several activities have been under- of Statistics: Resolution Leading to Policy orities of the committee, send a note to taken, including relaunching the ethi- Change.” This session was organized by Petska at [email protected]. n cal practices web site at www.amstat.org/ committee members Shelley Hurwitz committees/ethics/index.html, where the and Don Bentley. Eminent statisticians

Welcome to ASA Make the most of your ASA membership. Members Only Visit the ASA Members Only site!

Personalize your login ID

Access all your ASA journal, CIS, and JSTOR subscriptions with one easy login

Learn about partner discounts from Wiley, CRC Press, and others

Join the ASA Community

Read the e-news archive

www.amstat.org/membersonly

December 2009 Amstat News 61 SECTION NEWS

Biometrics Section Gears Up for JSM 2010 Edited by Page Moore, Biometrics Section Publications Officer

to present the submitted paper at JSM 2010 as a talk or poster presentation. Applicants must submit their JSM abstracts to the Biometrics Section in addition to submitting them to the ASA by February 1, 2010. They also must contact Katki at [email protected]. gov prior to the abstract deadline. The section will organize a series of topic- contributed sessions to highlight the submitted papers. By March 1, applicants should com- plete their application by submitting a Vancouver, British Columbia, Canada, where JSM 2010 will be held cover letter certifying that they meet the eligibility requirements and are not sub- mitting the paper to another ASA section bstract submission opened for best emerging work presented during student/young investigator award com- December 1 for contributed and JSM. The award commemorates the late petition, a current CV, and one copy of topic-contributed papers to be David Byar, a biostatistician who made the finished paper. All materials must be Apresented during JSM 2010, which will significant contributions to the develop- submitted electronically to Dan Heitjan, be held July 31 to August 5 in Vancouver, ment and application of statistical meth- section chair, at [email protected]. British Columbia, Canada. All abstracts ods and was esteemed as an exceptional The 2010 awards committee is com- are due February 1. mentor during his career at the National posed of the current and past section As an alternative to contributed ses- Cancer Institute. The winner will receive chairs and chair-elect, as well as three sions, topic-contributed sessions are $1,500. Additionally, the section may pro- individuals appointed by the section organized around a central topic and vide travel awards to the authors of other chairs. More information can be found include 20-minute talks and possible outstanding papers submitted to the com- on the section web page, easily accessed discussants. Typically, sessions consist of petition. by clicking on the “Section” tab at the five speakers (e.g., four speakers and one Applicants must have held a doctor- top of www.amstat.org. discussant or three speakers and two dis- ate in statistics, biostatistics, or a related cussants). JSM 2010 Biometrics Section quantitative field for three or fewer Section Officers program chair, Hormuzd Katki, is col- years as of April 1 of the current year With the arrival of 2010, we will have a lecting proposals for topic-contributed or be enrolled as a doctoral student in new set of officers. There are a number talks. If you are interested in organizing statistics or biostatistics and in active of transitions involving the past chair, a topic-contributed session, contact him pursuit of a doctoral degree. They also current chair, chair-elect, and chair-elect- at [email protected]. must be current members of the ASA elect. (The numerous chair positions are Topic-contributed panel sessions are Biometrics Section and first author of needed to distribute the work load of another alternative. They usually include the paper submitted. (Membership in the overall chair position.) Current past three to six panelists who work together the ASA does not automatically confer chair Jeremy Taylor will be replaced by to submit one abstract for all speakers. section membership. Applicants may current chair Daniel Heitjan. Heitjan See www.amstat.org/meetings/jsm/2010/ join at the time of submission for a $5 will be replaced by current chair-elect index.cfm for more information. annual membership fee.) Barry Graubard, and Graubard will be The paper may be submitted to a jour- Nominations Sought replaced by current chair-elect-elect nal or under review, but may not have Jack Lee. The remaining officer transi- Do you know a young investigator who appeared online or in print at the time of tions are as follows: Mousumi Banerjee is planning to submit an abstract for the application or have been accepted for replaces Diana Miglioretti as one of JSM? If so, you might mention that publication as of January 1, 2010. Also, three Council of Sections representa- the ASA Biometrics Section is seeking the paper may not have been submitted tives; Liang Li replaces Jinbo Chen as applications for the 2010 David P. Byar to any other ASA section student/young program chair for ENAR; and Hormuzd Young Investigator Award. This annual investigator award competition. Katki replaces Wensheng Guo as JSM award is given to a young investigator Finally, applicants must be scheduled program chair. n

62 Amstat News December 2009 Statistics in Defense and National Security Speakers Program Offered Alyson Wilson, SDNS Speaker Committee Chair

ense & N ef atio n D n i al cs S ti e Distinguished Achievement Award s c i u t r a i Each year, the Section on Statistics in Defense and National Security

t

t y

S SDNS presents the Distinguished Achievement Award to a member of the statistical community. The next presentation of the award will be at the 2010 Joint Statistical Meetings in Vancouver, British Columbia, ave you ever wondered what Canada. The purpose of the award is to recognize an outstanding kind of statistical research accomplishment or a record of sustained contributions at the helps keep the nation safe from intersection of the statistical profession and national defense or Hbiological attacks or helps officials national security. understand terrorist networks? Are you interested in learning what a defense A nomination should include a short description of the basis for the statistician’s job is like and what kind award, contact information for both the nominator and nominee, of problems they face? The ASA and suggested text for the certificate. A maximum of five seconding Section on Statistics in Defense and letters submitted in PDF format are welcome. This recognition does National Security (SDNS) has a speak- not include a financial award. Please be aware that unsuccessful ers program that allows experienced nominations from previous years are not, and will not be, carried researchers to answer these and other forward to the next year; therefore, new nomination packages questions. Statisticians working in defense and security are available to should be prepared for previous nominees. For more information or speak at your college or university and to send an electronic nomination, email Myron Katzoff at mjk5@cdc. describe their work while sharing their gov. The deadline for nominations is March 15. enthusiasm for this field. The SDNS speakers program aims to foster communication between statisticians and familiarize students with the role of statisticians in defense and national security. Speakers discuss Young University spoke at Iowa State Nova Southeastern University about topics such as biosurveillance, cyber University (ISU), proposing a flexible a number of statistical methodologies defense, military force structure, dis- class of models and an adaptive design for computer intrusion detection and tributed sensor networks, reliability, approach to better assess chemical and proposed a framework that incorpo- and experimental design. biological threat detection systems. rated everything from the analysis of Students and faculty acquire access Reese also guest lectured during ISU’s raw packet flows to the analysis of to experts in a field to which they graduate Bayesian analysis course, dis- user behavior. His talk was included might otherwise have little exposure, cussing some of his research on Bayesian as part of Nova Southeastern’s math and academic statisticians gain insight inference in hierarchical models. awareness month. into current statistical issues in defense Alyson Wilson of ISU spoke at Texas If you are interested in having an and security. Throughout their inter- A&M University (TAMU) about the SDNS speaker visit your university, visit action, students and faculty are intro- use of Bayesian networks in system reli- www.amstat.org/sections/sdns/speakers. duced to a new point of contact that ability assessment and the development html. Choose a speaker and contact the can lead to internships, employment, of reliability assurance test plans. Her SDNS speaker committee chair, Alyson and other career opportunities. lecture was recorded as part of TAMU’s Wilson, at [email protected] with a pro- The initial funding for the speakers online learning seminar series. posal. If your proposal is selected, SDNS program was provided through a 2008 David Marchette of the Naval will supply up to $500 for expenses ASA member initiative that sponsored Surface Warfare Center and The related to the visit. n three talks. Shane Reese of Brigham Johns Hopkins University spoke at

December 2009 Amstat News 63 Statistics and the Environment Student Paper Submissions Wanted Jun Zhu, ENVR Publications Chair JSM 2010 Vancouver, British Columbia, Canada, July 31 to August 5 he Section on Statistics in the Environment (ENVR) is spon- If you have ideas about topic-contributed sessions, contact ENVR program soring a student paper competi- chair, Petrutza Caragea, at [email protected]. Ttion on the topic of environmental sta- tistics. We encourage students to submit clear application to an environmental Joint Statistical Meetings in August of papers on their research in this area. statistical issue, or application of statis- 2010 and receive a stipend toward reim- The paper may consist of novel tics to environmental problems. The bursing the cost of attending JSM. approaches to the analysis of environ- selected winner will present his/her Anyone who is a student in the fall mental data, new methodology with a paper in a contributed session at the of 2009 (undergraduate, master’s, or PhD) is eligible to participate. The applicant must be the first author Biopharmaceutical of the paper. In addition, a letter must be submitted that verifies the applicant’s stu- dent status from a faculty member famil- Going to JSM 2010? Consider iar with the student’s work and, in the case of joint authorship, indicates what Section’s Poster Competition fraction of the contribution is attributable f you plan to attend JSM 2010 and Posters must focus on methodological to the applicant. The applicant also must present a poster, consider participat- issues in preclinical or clinical trials, epi- submit an abstract by February 1, 2010, ing in the poster competition spon- demiology studies of drug safety (device to the ASA and request a presentation in Isored by the ASA Biopharmaceutical or biological), genetic studies predicting an ENVR session. Applicants must follow Section. All authors who present posters drug (or biological) response, laboratory all rules required for paper submission and sponsored by the section are eligible to and toxicological data analyses, methods attendance at JSM. compete for these awards. for high-dimensional data from high- The paper must be entirely double- throughput screening, or nonlinear phar- spaced (abstract, main body, references, footnotes, and appendices) and no lon- 2009 Award Winners macokinetic modeling. Posters will be evaluated on innova- ger than 26 pages (inclusive). Use at least Best Contributed Poster tion, applicability in pharmaceutical 11-point type with at least 1-inch margins First Place – Kelly H. Zou and Martin O. research, appropriate example(s), and all around. Materials must be submitted Carlsson for “Beta-Mapping and Beta- effectiveness of presentation (well-written, electronically in Postscript or PDF format. Regression for Changes of Ordinal- well-organized, etc.). All materials must be in English. Rating Measures on Likert Scales: A All JSM attendees can participate in The deadline to submit materials is January 4, 2010, by 5 p.m. PST. Comparison Among Multiple Treatment the competition; however, authors who Papers will be reviewed by the Student Groups” compete for the awards cannot also com- pete for the student paper awards. Paper Competition Award commit- Second Place – Arminda Lucia Siqueira Three awards with prizes of $1,000, tee of the Section on Statistics and the and Daniela Monteiro Braga for “Making $500, and $300 will be given for first, Environment. Selection will be at the a Decision in Bioequivalence Studies: A second, and third place, respectively. discretion of the committee and based on the innovation and significance of the Statistical Contribution” To enter, submit an abstract to the ASA with the Biopharmaceutical Section contribution. Awards will be announced Third Place – William Coar, Darrin as sponsor by February 1, 2010. Also, in early 2010. The decision of the selec- Despain, and Brian L. Wiens for email your poster to Yongming Qu, chair tion committee will be final. This award “Estimation of Treatment Retention: The for the poster awards, at [email protected] will recognize an environmental statistics Peak-Trough Ratio” by May 1, 2010. Two judges will review contribution with a certificate and recog- each poster and an average score will be nition at the ASA ENVR section meeting Student Paper Award assigned. Posters with the highest scores during JSM. Violeta G. Hennessey for “A Bayesian will be the winners. Winners will be Email Alix I. Gitelman at gitelman@ Approach to Dose-Response Assessment announced and receive their certificates science.oregonstate.edu if you have any and Synergy and Its Application to In during the JSM 2010 Biopharmaceutical questions or would like application n Vitro Dose-Response Studies” Section mixer. n materials.

64 Amstat News December 2009 Statistics in Epidemiology Applications, Nominations Sought Jing Cheng, Publications Officer

he Statistics in Epidemiology session. The name of the session orga- $1,000 and a plaque, which will be pre- Section invites applications nizer must be included at the time of sented by the section at JSM. from young investigators who submission. Individuals who wish to The nominee should be a person who Twill be presenting papers at the 2010 organize a session should contact the is widely known and has an established Joint Statistical Meetings in Vancouver, section’s 2010 program chair, Ruth record of developing statistical methods British Columbia, Canada, for the Pfeiffer, at [email protected]. for epidemiology. Consideration is not Young Investigator Award. The award limited to candidates who are mem- honors the best papers in statistics in Nathan Mantel Award bers of the ASA Section on Statistics epidemiology presented at JSM. The Nominations are being accepted for the in Epidemiology. competition is open to current gradu- Nathan Mantel Award for lifetime con- To submit a nomination, send a ate students in statistics, biostatistics, tributions to the development and appli- CV and cover letter to Satagopan at and epidemiology and graduates who cation of statistical science to problems [email protected] by March 1. Questions received their degree within the past and issues in epidemiology. The award can be addressed to Brookmeyer at two years. Award recipients receive is in honor of Nathan Mantel (1919– [email protected]. $500 to help defray travels costs to the 2002) and in recognition of his seminal Previous recipients of the Nathan meetings, and a reception is held in and pivotal contributions to statistics Mantel Award include Norman Breslow, their honor. in epidemiology. The award consists of Ross Prentice, and Clarice Weinberg. n Preference will be given to papers with both methodologic contribu- tions and substantive epidemiological applications. Jointly authored papers are acceptable, but the applicant is expected to be the lead author and presenter. The JSM presentation does not have to be in a session sponsored by the epidemiology section, nor must applicants be current section members. To apply for the award, submit an abstract to the ASA by February 1 and the paper and a cover letter to Jaya Satagopan, section secretary/trea- sury, at [email protected] by June 1. Include with your paper where you are a current student. If you are a recent graduate, include your year of gradu- ation. Questions about the award should be sent to Ron Brookmeyer, section chair, at [email protected]. Topic-Contributed Sessions The section welcomes submissions for JSM topic-contributed sessions. These five 20-minute presentations (one of which can be a discussant) are organized around a common theme. Each speaker must submit an abstract to the ASA by February 1 and indi- cate it is part of a topic-contributed

December 2009 Amstat News 65 Physical and Engineering Sciences Message from the Outgoing Chair Tom Loughin, SPES Chair, Kansas State University

has engaged in the past year, as well as … well, it was a blast as always, although some of what you can expect in 2010. I still don’t have a dough boy (but you The Spring Research Conference should have seen Jen Van Mullekom in was in a suburb of Vancouver this year her stripey new overalls). and attracted a good crowd, despite the At the Fall Technical Conference distance and expense for some. Boxin this year, Cheryl Dingus represented us Tang superbly organized the confer- well on the program committee, help- ence and a special celebration for Jeff ing to assemble an interesting confer- Wu, and many participants made time ence. SPES organized an invited session to visit some of the scenic wonders in on variable selection, featuring Hugh Loughin the area (something I highly recom- Chipman and Chris Nachtsheim. We mend for those going to JSM 2010). also sponsored a short course by Bobby have mixed feelings as I write this Mee and hosted a luncheon talk by note in late September, realizing Good news for students who want to attend next year’s SRC: Scholarship ASA President Sally Morton. my term as chair is almost up. In other conference news, SPES ChairingI this section has been a lot of amounts will increase in 2010 to help make the conference more afford- will be cosponsoring the International work: It seems every week has brought Society for Business and Industrial projects to be organized, tasks to be able for students presenting research. Additionally, SPES will sponsor stu- Statistics (ISBIS) biannual conference, taken care of, requests to be made or to be held in Slovenia, July 6–9, 2010. handled, or discussions to lead or fol- dents’ ASA memberships the year they receive a scholarship. See www.action-m.com/isbis2010 for low. So, on the one hand, it will be details. In particular, if you’d like to nice to not have as many responsibili- JSM 2009 set an attendance record, and SPES had a strong presence there. organize a session of invited talks for ties. On the other hand, I feel as if­— SPES, let me know before the end of with apologies to The Carpenters— Jeff Luner and George Ostrouchov put together an excellent program, 2009. (Unfortunately, neither SPES “I’ve Only Just Begun.” nor ISBIS can provide travel funds for The section officers worked hard featuring 14 sessions of talks, a poster competition, and six roundtables. Our speakers.) this year, investigating a number of Our Marquardt Industrial Speakers potential initiatives that would provide Continuing Education entries, assem- bled by Tena Katsaounis, were well Program continues to be popular. even more value to SPES members. We I highly recommend academic and have some ideas ready to go and will received. In particular, John Cornell and Greg Piepel won the Excellence- industrial statisticians look into it as a be rolling them out soon. Others need way to better educate the next crop of further development and will take lon- in-CE Award for JSM 2009 based on attendee feedback for their course, statisticians and to build relationships ger to get started. I want to highlight that may yield future returns. Starting some of the activities in which SPES “Methods for Designing and Analyzing Mixture Experiments.” And the mixer in 2010, we will offer a number of free ASA and SPES memberships for students at institutions that host Marquardt speakers. SPES also will help defray the costs of social func- Attention Section Officers tions, such as pizza parties, to give stu- dents and the visiting speaker a greater Promote your meetings and events through opportunity to interact. the ASA’s online Calendar of Events. This past year saw a rise in non- conference networking opportunities, as SPES developed a LinkedIn group Visit the ASA’s web site: (thanks to Fred Hulting) and the ASA rolled out their new social networking www.amstat.org/dateline tool, the ASA Community. I encour- age you to use these tools as you see fit to develop relationships and discuss

66 Amstat News December 2009 issues with people who share com- The­­ 8th International mon interests. (Note: If you are a joint SPES/QP member and logged into the Conference on Health ASA Community early, you may have Policy Statistics found that your SPES community was limited to other joint members. The Quantitative insights and advances in ASA technical staff have fixed this bug, health policy analysis so you should now have access to all The 8th International Conference on Health Policy Statistics (ICHPS), members of both SPES and QP.) organized by the Health Policy Statistics Section, will be held at the The reality of being chair, or any Fairmont Hotel in Washington, DC, January 20–22. The deadline to register other officer, is that it is much like being for the conference is January 4, 2010. in a relay race. Just as I had the baton smoothly passed to me by Bill Notz, In line with the American Statistical Association’s recent initiatives to who got it from Jen Van Mullekom, further its efforts at engaging policymakers and other stakeholders in the I will hand it off soon to Russ Lenth, health policy arena, ICHPS 2010 will focus entirely on quantitative analysis who will pass it to Phil Scinto. This is of data related to policy issues. To view the program or to register, visit good news for all of us, because Russ www.amstat.org/meetings/ichps/2010. Highlights include the following: and Phil are both excellent people who have served the profession often Plenary Speaker—January 21 and well. They come from different Carolyn Clancy, Director, Agency for Healthcare Research and Quality backgrounds and will bring diverse Invited Sessions—January 21–22 experiences and perspectives into the leadership of SPES. I look forward to Mixed-Treatment Meta-Analysis for Promoting Comparative Effectiveness working with both of them next year Research (and then watching them both work Novel Methods for Using Decision Models in Economic Evaluation and from a safe distance). Research Priority Setting in Health Care While I’m on the subject of offi- cers, I want to heartily thank those who Statistical Issues in Drug Safety served with me this year. Special person- Incorporating Adaptive/Dynamic Treatment Strategies in Clinical Trial Designs al thanks go to Bill Notz, who endured The Magic with Missing Data Methods: Is There More to the Prestige? frequent contacts from me early in my term as I worked to get my bearings. Data Confidentiality: Do We Really Want to Disturb a Sleeping Bear? Bill, along with every other officer, Beyond Simple Randomized Trials: Health Services Research Within the VA does this job on a volunteer basis. All Healthcare System of the officers I’ve known are atten- tive to the requirements of their posi- Modeling Efforts to Inform Healthcare Initiatives and Policy tions, and many willingly take on extra Topic-Contributed Sessions—January 21 responsibilities as issues come up that don’t fall naturally into someone’s job Modern Methods in Health Disparities Research description. If you like what we’ve been Quantitative Models for Health Care Reform doing for you, check out the officer list at www.amstat.org/sections/spes and zip Symposium on Comparative Effectiveness Research— one of us a note of thanks. If you don’t January 22 like what we’ve been doing for you, zip Putting the Research Into Comparative Effectiveness Research me a note and suggest what we could do better. We’re here for you, after all, Workshops—January 20 and all of us would like to make this Bayesian Adaptive Methods for Clinical Trials section serve its members in the best way possible. Better still, volunteer Estimating Treatment Effects Using Longitudinal Observational Data to serve the section in some capacity. Reducing the Impact of Selection Bias with Propensity Scores We are always looking to inject fresh ideas into the section executive team Microsimulation Modeling and have lots of roles that can be filled, Cluster Randomized Trials in Health Policy Research from entry-level to leadership. (FREE) The Medical Expenditure Panel Survey (MEPS): A National Data Thank you for giving me the oppor- Resource to Inform Health Policy tunity to serve the section. I wish you all the best of luck in 2010. n

December 2009 Amstat News 67 JSM PROCEEDINGS ORDER FORM

CD-ROM INDIVIDUAL ORGANIZATION QUANTITY TOTAL

2009 COMPLETE SET $50 $295 ______2008 COMPLETE SET $50 $295 ______2007 COMPLETE SET $50 $295 ______

2006 COMPLETE SET $50 $295 ______

2005 COMPLETE SET $50 $295 ______

2004 COMPLETE SET $50 $295 ______

2003 COMPLETE SET $50 $295 ______

2002 COMPLETE SET $50 $295 ______

PAYMenT inforMATion Total Amount Due $

orDer MUST Be PrePAiD. Please make check or money order payable to the American Statistical Association in U.S. funds drawn on a U.S. bank. Return this form with your credit card information or payment to ASA, Department 79081, Baltimore, MD 21279-0081, or fax to (703) 684-2037 (credit card only).

PLEASE INDICATE THE ADDRESS WHERE YOU WOULD LIKE TO RECEIVE YOUR ORDER .

❑ Dr. ❑ Mr. ❑ Mrs. ❑ Ms. ASA Customer ID (if applicable)______

First Name______MI______Last Name______Organization______Address (No P.O. Boxes)______City______State/Province______Country______ZIP+4/Postal Code______Phone______Fax______Email______

❑ Check/Money Order enclosed Credit Card: ❑ American Express ❑ MasterCard ❑ VISA

Name on Card______

Card #______

Exp. Date______/______Signature of Cardholder______CALENDAR OF E

or more information about these events, visit www.amstat.org/dateline.

Announcements are accepted from educational and not-for-profit V E N TS organizations only. Commercial enterprises should contact the ASA FAdvertising Department at [email protected]. more information, visit www.causeweb.org/ * Indicates events sponsored by the American Statistical Association or one of workshop or contact Jean Scott, The Ohio its sections, chapters, or committees State University, Dept. of Statistics, 1958 Neil Ave., Columbus, OH 43210; (614) ›› Indicates events posted since the previous issue 688-5913; [email protected].

››13–16—Mini-Course on Remodeling Data Analysis, San Francisco, California Danny Kaplan and Victor Addona of ››12—Become a Catalyst for Change Macalester College will present this 2010 in , San Francisco, course during JMM. It is a data analysis California course that complements and builds on Joan Garfield, Bob delMas, and Andy majors’ math aptitudes, reinforcing an January Zieffler of the University of Minnesota understanding of linear algebra while pro- *4–8—International Indian Statistical and Allan Rossman and Beth Chance of viding advanced applied statistical skills. Association Joint Statistical Meetings Cal Poly-San Luis Obispo will present this Modeling, computation (using R), and and International Conference on MAA ancillary workshop the day before simulation are used extensively. For more Statistics, Probability, and Related Areas, JMM. It will feature materials developed information, contact Jean Scott, The Ohio Visakhapatnam, India by the CATALST project that focus on State University, Dept. of Statistics, 1958 The Joint Statistical Meetings, organized important ideas of statistical inference and Neil Ave., Columbus, OH 43210; (614) by the International Indian Statistical the use of simulation. There is no registra- 688-5913; [email protected]. Association in partnership with the tion fee, but registration is required. For American Statistical Association and sta- tistical associations in India, will be held at Andhra University. For more information, visit www.stat.osu.edu/~hnn/IISA.html or contact Naranyanswamy Balakrishnan, Department of Mathematics and Statistics, McMaster University, Hamilton, Ontario L85 4K1, Canada; (905) 525-9140, Ext. 23420; [email protected].

››12—Teaching Introductory Statistics, San Francisco, California Carolyn Cuff of Westminster College and Michael Posner of Villanova University will present this MAA ancillary work- shop the day before JMM. The workshop will address implementing the GAISE guidelines in a first-level statistics course. Internet sources of real data, activities, and best practices articles will be examined. There is no registration fee. For more infor- mation, visit www.causeweb.org/ workshop or contact Jean Scott, The Ohio State University, Dept. of Statistics, 1958 Neil Ave., Columbus, OH 43210; (614) 688-5913; [email protected].

December 2009 Amstat News 69 VENTS 15–16—University of Florida Twelfth February ››16–19—SIMMAC International Annual Winter Workshop: Categorical Symposium on Mathematical Methods Data Analysis, Gainesville, Florida 1–4—Statistical Modelling and Applied to the Sciences, San Jose, Costa This workshop will focus on recent devel- Inference Conference to Celebrate Rica

CALENDAR OF E opments in methodology for categorical Murray Aitkin’s 70th Birthday, Brisbane, SIMMAC will cover data analysis, mul- data analysis, including high-dimensional Australia tivariate statistics, clustering and classifi- data, Bayesian inference, and clustering The purpose of this conference is to dis- cation, probability, stochastic processes, and missing data, as well as applications cuss the current and future state of statisti- financial mathematics, stochastic con- to rapidly developing disciplines such as cal modeling and inference. It is also to trol, optimization, operations research, statistical genetics. For more information, celebrate Murray’s involvement in these approximation, numerical analysis, visit www.stat.ufl.edu or contact Robyn fields. All contributions are welcome, as dynamic systems, differential equations, Crawford, P.O. Box 118545, 103 Griffin- either read papers, posters, or short presen- modeling, biomathematics, and applica- Floyd Hall, Gainesville, FL 32611; (352) tations in the final open session. Preference tions. For more information, visit www. 392-1941; [email protected]. may be given to historical surveys of the cimpa.ucr.ac.cr/simmac.html or contact development of modeling and/or infer- Javier Trejos, C.U. Rodrigo Facio, San 27–29—2010 Bayesian Biostatistics ence; surveys of current methods and their Jose, International 02060, Costa Rica; Conference, Houston, Texas advantages and limitations; reports of 00.506.2511-5889; simmac.cimpa@ Current and prospective users of Bayesian current work in these fields; predictions ucr.ac.cr. biostatistics are invited to join experts in of future trends (with credibility bands); the field for a three-day conference that and discussion of foundational issues in includes short courses and invited presen- likelihood, Bayes, frequentist, and sur- March tations. For more information, visit vey sampling inference. Contributions 17–19—IAENG International biostatistics.mdanderson.org/BBC2010 or related to Murray’s involvement in these Conference on Data Mining and contact Lydia Davis, 1515 Holcombe fields are also welcome. For details, visit Applications 2010, Hong Kong, China Blvd., Unit 1409, Houston, TX 77030; www.aitkinconference.scitech.qut.edu.au This conference will be held under (713) 794-4142; [email protected]. or contact Clair Alston, GPO Box 2434, Brisbane, International 4001, Australia; the International MultiConference of +61 731381287; [email protected]. Engineers and Computer Scientists 2010. The IMECS 2010 is organized by the International Association of Engineers (IAENG) and serves as a good platform for researchers. For more information, visit www.iaeng.org/IMECS2010/ICDMA2010. html or contact IAENG Secretariat, Unit 1, 1/F, 37-39 Hung To Road, Hong Kong, International HK, Hong Kong; (852) 3169-3427; [email protected].

17–20—Conference on Frontier of Statistical Decisionmaking and Bayesian Analysis This conference consists of plenary, invit- ed, and poster sessions. Plenary speakers include Donald Berry, Lawrence Brown, Persi Diaconis, Stephen Fienberg, and Alan Gelfand. The conference will provide an overview of the past, present, and future developments of statistical decisionmaking and Bayesian analysis. Prior to the confer- ence, short courses on various statistical topics will be offered. For more informa- tion, visit http://bergerconference2010.utsa. edu or contact Keying Ye at Keying.Ye@ utsa.edu.

70 Amstat News December 2009 CALENDAR OF E

››22—A Celebration of the April and government. The areas are broadly Contributions of Donald A. Berry, New defined, with nonparametrics encompass-

Orleans, Louisiana 7–9—MAF2010 - Mathematical ing distribution-free statistics, rank-based V E N TS In honor of Donald A. Berry and his and Statistical Methods for Actuarial and , Bayesian nonpara- contributions to the statistics and health- Sciences and Finance, Ravello, Italy metric methods, permutation-based related research communities, two invited The aim of this conference is to provide methods, , and sessions and a dinner will be held during new theoretical and methodological results . There also will be ENAR 2010. Invited speakers include Jim and significant applications in actuarial eight contributed paper sessions and two Berger, Janet Wittes, Steven Goodman, sciences and finance by the capabilities of contributed poster sessions where junior Giovanni Parmigiani, Michael Krams, the interdisciplinary mathematical and investigators and graduate students are Telba Irony, and Dalene Stangl. The ses- statistical approach. For more information, expected to participate. For more informa- sions will overview Berry’s contributions visit maf2010.unisa.it or contact Marcella tion, visit www.stat.osu.edu/~nssl2010 or and discuss the future of clinical trials. Niglio, Via Ponte Don Melillo, Fisciano, contact Steven MacEachern, Department For more information or tickets for the International 84084, Italy of Statistics, The Ohio State University, dinner, contact Dalene Stangl, 212 Old 1958 Neil Ave., Cockins Hall, Rm. 404, Chemistry, Box 90251, Durham, NC 25–27—22nd Annual Kansas State Columbus, OH 43210-1247; (614) 292- 27708; (919) 684-4263; dalene@stat. University Conference on Applied 5843; [email protected]. duke.edu. Statistics in Agriculture, Manhattan, Kansas 23–26—38th Annual Meeting of the 23–26—DAGStat2010: Statistics Under This conference will bring together statisti- Statistical Society of Canada, Québec One Umbrella, Dortmund, Germany cians from academia, industry, and govern- City, Québec DAGStat is a network of scientific and ment to discuss ideas and advances in the This conference will bring together professional organizations that develop application of statistics to solve agricultural academic, government, and industrial and promote and meth- research problems. For more information, researchers as well as users of statistics and odology. The aim of the working group visit www.ksu.edu/stats/agstat. probability. Featured will be workshops is to offer a panel for shared activities conference or contact John Boyer, and invited and contributed sessions and public relations to reach a stronger Department of Statistics, Dickens Hall, on all areas of statistics and probability. cognition of statistics. For more informa- Kansas State University, Manhattan, KS About 450 statisticians are expected to tion, visit www.statistik.tu-dortmund. 66506; (785) 532-0518; [email protected]. participate. For details, contact Thierry de/DAGStat2010/en or contact Jörg Duchesne, Universityersité Laval, Rahnenführer, Vogelpothsweg 87, 29–5/1—2010 SIAM International Département de mathématiques et de Dortmund, International 44227, Conference on Data Mining, Columbus, statistique, Pavillon Vachon, Québec, Germany; +49 231 755 3121; Ohio Quebec G1K 7P4, Canada; (418) 656- [email protected]. This conference will provide a venue for 2131, Ext. 5077; thierry.duchesne@mat. researchers to present their work in a peer- ulaval.ca. 25–26—Conference on Resampling reviewed forum. A set of focused work- Methods and High-Dimensional Data, shops will be held on the last day of the 25–27—Joint Research Conference College Station, Texas conference. The proceedings of the confer- on Statistics in Quality, Industry, and This conference aims to bring together ence will be published in archival form Technology, Gaithersburg, Maryland researchers working in resampling meth- and made available on the SIAM web site. The Quality and Productivity Research ods and high-dimensional data. It will For more information, visit www.siam.org/ Conference and the Spring Research provide a unique platform for taking stock meetings/sdm10 or contact Amol Ghoting, Conference on Statistics in Industry of recent developments in each area and 1101 Kitchawan Road, RT 134, Yorktown and Technology will be held jointly at exploring the limits of resampling methods Hts., NY 10598; (914) 945-2193; the National Institute of Standards and in a high-dimensional setting. Keynote [email protected]. Technology (NIST). The goal of the con- speakers are Peter Bickel, Jianqing Fan, ference is to stimulate interdisciplinary Peter Hall, and Bin Yu. For more informa- research among statisticians, engineers, tion, visit www.stat.tamu.edu/ May and physical scientists in quality and pro- Spring-Conf-2010 or contact Soumendra ductivity, industrial needs, and the physical Lahiri, Dept. of Statistics, Texas A&M 19–22—Conference on Nonparametric sciences. For more information, contact University, College Station, TX 77845; Statistics and Statistical Learning, Will Guthrie, 100 Bureau Drive, Stop (979) 845-3141; [email protected]. Columbus, Ohio 8980, Gaithersburg, MD 20899-8980; This conference will bring together (301) 975-2854; [email protected]. researchers in nonparametrics and statis- tical learning from academia, industry,

December 2009 Amstat News 71 VENTS June Jana Jureckova, Department of Statistics, services, health services, quality and pro- Sokolovska 83, Prague 8, International ductivity improvement, and decisionmak- CZ-186 75, Czech Republic; icors2010@ 5–8—IWMS 2010 - 19th International ing in business and industry. For more karlin.mff.cuni.cz. Workshop on Matrices and Statistics, information, visit www.action-m.com/

CALENDAR OF E Shanghai, China isbis2010 or contact Milena Zeithamlova, This conference will stimulate research 29–7/1—International Conference on Vrsovicka 68 101 00, Prague, International and foster the interaction of researchers Probability Distributions and Related 10, Czech Republic; +420 267 312 333; in the interface between statistics and Topics in Conjunction with NZSA [email protected]. matrix theory. There will be invited and Conference, Palmerston North, New contributed papers. Potential participants Zealand 12–23—SAMSI: 2010 Summer Program should visit www1.shfc.edu.cn/iwms/index. This international conference is devoted on Semiparametric Bayesian Inference: asp for online registration and submis- to all aspects of distribution theory and its Applications in Pharmacokinetics and sion of abstracts. For details, visit www1. applications, including discrete, univariate, Pharmacodynamics, Research Triangle shfc.edu.cn/iwms/index.asp or contact and multivariate continuous distributions; Park, North Carolina Yonghui Liu, Shanghai Finance University, copulas; extreme values; skewed distribu- The aims of the program and workshop Shanghai, International 201209, China; tions; conditionally specified distributions; are to identify the critical new develop- [email protected]. and life distributions in engineering and ments of inference methods for pharma- survival analysis. For more information, cokinetics (PK) and pharmacodynamics visit http://nzsa_cdl_2010.massey.ac.nz or ››16–18—45th Scientific Meeting of (PD) data, determine open challenges, contact Narayanaswamy Balakrishnan, the Italian Statistical Society, Padua, and establish inference for PK and PD Department of Mathematics and Statistics, Italy as an important motivating applica- Hamilton, International L8S 4K1, The 2010 conference will include plenary, tion area of nonparametric Bayes. For Canada; (905) 525-9140, Ext. 23420; specialized, contributed, and poster ses- more information, visit www.samsi.info/ [email protected]. sions. These can be in any area of interest programs/2010bayes-summer-program. relevant to theoretical and applied statis- shtml or contact Jamie Nunnelly, P.O. Box tics. For details, visit www.sis-statistica. 30–7/2—2010 International Conference 14006, RTP, NC 27709; (919) 685-9350; it/meetings/index.php/sis2010/sis2010 or of and Data [email protected]. contact Patrizia Piacentini, Department Engineering, London, United Kingdom of Statistical Sciences, via C. Battisti 241, For details, visit www.iaeng.org/WCE2010/ 27–31—LinStat 2010, Tomar, Portugal Padova, International I-35121, Italy; ICCSDE2010.html or contact IAENG The aim of this conference is to bring [email protected]. Secretariat, Unit 1, 1/F, 37-39 Hung To together researchers with an interest in Road, Hong Kong, International, China; a variety of aspects of statistics and its (852) 3169-3427; [email protected]. 20–23—ISF2010 - 30th International applications. There will be plenary talks Symposium on Forecasting, San Diego, and sessions with contributed talks. For California July more information, visit www.linstat2010. This conference will include keynote ipt.pt or contact Francisco Carvalho, speaker presentations, academic ses- 4–9—IWSM 2010, Glasgow, United Estrada da Serra - Quinta do Contador, sions, workshops, and social programs. Kingdom Tomar, International 2300-313, Portugal; For details, visit www.forecasters.org or The 25th International Workshop on +351249328100; [email protected]. contact Pam Stroud, 53 Tesla Avenue, Statistical Modeling (IWSM 2010) will Medford, MA 02155; (509) 357-5530; be hosted by the University of Glasgow in *31–8/5—2010 Joint Statistical [email protected]. Scotland. For more information, visit or Meetings, Vancouver, British Columbia, contact Claire Ferguson, Department of Canada 28–7/2—ICORS 2010, Prague, Czech Statistics, 15 University Gardens, Glasgow, JSM (Joint Statistical Meetings) is the Republic International G12 8QW, Scotland; 0141 largest gathering of statisticians held in The International Conference on Robust 330 5023; [email protected]. North America. Attended by more than Statistics aims to be a forum for the 5,500 people, activities include oral pre- development and application of robust *5–9—ISBIS-2010 (International sentations, panel sessions, poster presenta- statistical methods. It is an opportunity Symposium on Business and Industrial tions, continuing education courses, an to meet, exchange knowledge, and build Statistics), Slovenia exhibit hall, a placement service, society scientific contacts with others interested The key themes of this conference are and section business meetings, committee in the subject. For more information, visit industrial applications of statistical image meetings, social activities, and network- icors2010.karlin.mff.cuni.cz or contact analysis, future directions for handling ing opportunities. For more information, large and complex data sets, financial visit www.amstat.org/meetings or contact

72 Amstat News December 2009 CALENDAR OF E

ASA Meetings Department, 732 North Fajfrova, Pod Vodarenskou vezi 4, Prague May Washington Street, Alexandria, VA 22314; 8, International 18208, Czech Republic;

(888) 231-3473; [email protected]. [email protected]. 10–13—International Conference V E N TS on (ICODOE-2011), Memphis, Tennessee August September The goal of this conference is to bring together leading researchers in design and 5–7—16th ISSAT International 12–15—SAMSI: 2010–11 Program analysis of experiments, including com- Conference on Reliability and Quality on Analysis of Object Oriented Data binatorial design, and practitioners in the in Design, Washington, DC Opening Workshop, Research Triangle pharmaceutical, , physical, Calling for papers, due February 15, Park, North Carolina biological, medical, social, psychological, 2010. For more information, visit www. Modern science is generating a need economic, engineering, and manufactur- issatconferences.org or contact Conference to understand and statistically analyze ing sciences. The conference will focus on Secretary, P.O. Box 1504, Piscataway, NJ populations of increasingly complex emerging areas of research in experimental 08855; [email protected]. types. Analysis of object oriented data design and novel innovations in traditional (AOOD) is aimed at encompassing areas. For more information, visit www. ››22–27—COMPSTAT 2010, Paris, an array of such methods. For more msci.memphis.edu or contact Manohar France information, visit www.samsi.info/ Aggarwal, 373 Dunn Hall, University of This conference will cover the develop- programs/2010aoodprogram.shtml or con- Memphis, Memphis, TN 38152; (901) ment of new statistical ideas, user experi- tact Terri Nida, 19 TW Alexander Drive, 678-3756; [email protected]. n ences, and software evaluation. The pro- RTP, NC 27709; (919) 685-9350; info@ gram should appeal to software developers samsi.info. and anyone working in statistics who uses computers. For more information, visit www.compstat2010.fr or contact December Gilbert Saporta, 292 rue Saint Martin, 6–10—Australian Statistical Conference Paris, International 75003, France; 2010, Fremantle, West Australia +33140272268; [email protected]. Delegates from all areas of work in statis- tics will be encouraged to communicate 29–9/1—SAMSI: 2010–11 Program on their knowledge and expertise and join See you in 2010 at the Complex Networks, Research Triangle world-class Australian and international Park, North Carolina statisticians to discuss new work. For more Joint Statistical Meetings This program is built around network information, visit www.statsoc.org.au or in Vancouver, British Columbia modeling and interference, flows on contact Promaco Conventions, Unit 10 networks, network models for disease 22 Parry Avenue, Bateman, International transmission, and dynamics of networks. 6150, Australia; +61 8 9332 2900; For more information, visit www.samsi. [email protected]. July 31–August 5, 2010 info/workshops/index.shtml or contact Terri Nida, 19 TW Alexander Drive, RTP, NC Vancouver Convention Centre 27709; (919) 685-9350; [email protected]. 2011 30–9/3—Prague Stochastics 2010, For information, email Prague, Czech Republic January [email protected] Prague Stochastics 2010 is next in a series *5–7—2011 Living to 100 Symposium, or call toll-free (888) 231-3473. of international conferences on stochas- Orlando, Florida tics organized in Prague since 1956. This conference, held by the Society of The scientific program will be aimed Actuaries, will include thought lead- 2010 at covering a wide range of stochastics, ers from around the world who will with special emphasis on the topics of share ideas and knowledge about aging, this lively field that have been pursued in CAJSMNADA changes in survival rates and their impact V a ncouver, British Columbia Prague. For more information, visit www. on society, and observed and projected utia.cas.cz/pragstoch2010 or contact Lucie increases in aging populations. For more information, visit http://livingto100.soa.org or contact Jan Schuh, 475 N. Martingale Road, Suite 600, Schaumburg, FL 60173; [email protected].

December 2009 Amstat News 73 rofessional Opportunity listings may not exceed 65 words, plus equal opportunity information. Ads must be received by the first of the pre- ceding month to ensure appearance in the next issue (i.e., September Arizona P1 for the October issue). Ads received after the deadline will be held until the n The School of Mathematical and following issue. Statistical Sciences (SoMSS) at Arizona Listings are shown alphabetically by state, followed by international listings. State University (ASU) has openings for Vacancy listings may include the institutional name and address or be identi- three tenure-track or tenured positions fied by number, as desired. to start August 16, 2010. One position is

OPPORTPROFESSIONAL UNITIES Professional Opportunities vacancies also will be published on the ASA’s in probability or statistics, one is in core web site (www.amstat.org). Vacancy listings will appear on the web site for the mathematics, and one is open in terms entire calendar month. Ads may not be placed for publication in the magazine of fields. Applications must be submitted only; all ads will be published both electronically and in print. online through www.mathjobs.org, where Rates: $320 for nonprofit organizations (with proof of nonprofit status), full ads for each position may be found. $475 for all others. Member discounts are not given. A URL link may be EOE. included in display ads in the online version of Amstat News for an additional $100. Display advertising rates are at www.amstat.org/ads. Listings will be invoiced following publication. All payments should be California made to the American Statistical Association. All material should be sent to Amstat News, 732 North Washington Street, Alexandria, VA 22314- n RAND statistics group is seeking PhD- 1943; fax (703) 684-2036; email [email protected]. level statisticians interested in exciting Employers are expected to acknowledge all responses resulting from publica- opportunities to collaborate on multidis- tion of their ads. Personnel advertising is accepted only with the understanding ciplinary public policy research projects. that the advertiser does not discriminate among applicants on the basis of race, Openings exist for recent graduates and sex, religion, age, color, national origin, handicap, or sexual orientation. experienced statisticians. See our ad in the Also look for job ads on the ASA web site at www.amstat.org/jobweb. September Amstat News for description or go to www.rand.org/statistics. Application deadline December 15, 2009. Applications must be submitted online following the instructions at www.rand.org/statistics/ jobs.html (Job ID #2368). Send ques- tions to [email protected]. EO/AA Employer.

n Monsanto is currently seeking a research associate to join the statistical/quantitative genetics team located in Woodland, CA. The associate will be responsible for sup- porting the onsite statistical geneticist in analyzing and developing statistical and computational tools for building genetic maps and conducting QTL-mapping in a variety of vegetable crop species. For more information please visit www.monsanto.com and to apply online select req. # 000NS. EOE.

Connecticut n Yale University invites applications for assistant professor beginning 7/01/2010. Excellence in statistics with a significant data-driven component in research and teaching activities. Each applicant should send a letter of application, curriculum vita, and statements of research and

74 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT teaching interests to [email protected] or [email protected]. Applicants should also arrange for three letters of refer- ence to be sent. Yale University is an affir- mative action/equal opportunity employer. The university greatly values diversity among its faculty, students, and staff and strongly encourages applications from women and under-represented minorities. www.stat.yale.edu.

District of Columbia n RAND statistics group is seeking PhD- level statisticians interested in exciting opportunities to collaborate on multidis- ciplinary public policy research projects. Openings exist for recent graduates and experienced statisticians. See our ad in the September Amstat News for description or go to www.rand.org/statistics. Application deadline December 15, 2009. Applications must be submitted online following the instructions at www.rand.org/statistics/ jobs.html (Job ID #2368). Send ques- tions to [email protected]. EO/AA Employer.

Georgia n The mathematics and statistics depart- ment of Georgia State University invites applications for anticipated tenure-track assistant/associate professor position in biostatistics beginning August 2010 pend- ing budgetary approval. PhD in biostatis- tics, statistics, or fields related to statistics is required. Duties include teaching, research, service, and directing doctoral students. Visit our web site at www2.gsu. edu/~wwwmat/. Georgia State University is an EEO/AA employer. Offer of employ- ment will be conditional upon background verification.

Illinois n Department of mathematical sciences, DePaul University, invites applications for the position of director of gradu- ate programs in applied statistics and

December 2009 Amstat News 75 Faculty Position in Biostatistics Group Health Research Institute, Seattle, WA Grant Program The Biostatistics Unit, Group Health Research Institute, is seeking candidates for a faculty po- sition in Biostatistics at the Assistant, Associate, or Senior level. The biostatistician will have the opportunity to collaborate with epidemiological and health services researchers in a va- The American Statistical Association riety of areas including cancer, women’s health, preventive care, and/or behavioral medicine. (ASA) Committee on Law and Justice The position also includes the opportunity to pursue independent research. Statistics announces a small grant program for the analysis of Bureau The Institute (www.grouphealthresearch.org/) is an internationally recognized academic

OPPORTPROFESSIONAL UNITIES of Justice Statistics (BJS) and other research organization that primarily conducts government funded clinical, epidemio- justice-related data. logic, and health services research. It includes 35 MD and PhD investigators, 15 biostat- isticians, and over 250 staff members. The Institute and surrounding research centers are part of a vibrant statistical community. Current areas of statistical research conducted at This program is designed to encour- the Institute include biased sampling schemes, longitudinal and clustered data analysis, age the creative and appropriate use of evaluation of diagnostic and screening tests, microsimulation modeling, spatial statis- these data to inform substantive and tics, multistate disease modeling, latent class analysis, and methods for drug/vaccine methodological issues. safety and effectiveness studies. The Institute is the research division of Group Health Cooperative, a non-profi t, consumer-governed, integrated health care organization and Awards are generally to be completed an affi rmative action/equal opportunity employer. within a two-year period and are typically in the range of $25,000 to Applicants should hold a PhD in Biostatistics or Statistics. Excellent oral and written commu- $40,000. nication skills and a strong interest in active collaboration on public domain interdisciplinary research studies are required. Experience with methods for missing data, causal inference, Proposals must be emailed to and/or survival analysis is desirable. Appointees will be encouraged to explore affi liation with [email protected] the Department of Biostatistics at the University of Washington once they are established. by January 15, 2010. For more information, go to Review of applications will continue until the position is fi lled. Submit letter of interest, http://www.amstat.org/careers/bjs.cfm CV, and three letters of recommendation at http://www.ghc.org/careers (job#091878). Group Health is an Equal Opportunity Employer committed to a diverse and inclusive workforce.

Chair, Department of Biostatistics The University of Pittsburgh Graduate School of Public Health (GSPH) is seeking nominations and applications for the position of Professor and Chair of the Department of Biostatistics.

The Department of Biostatistics was founded in 1949 and is one of seven departments in the Graduate School of Public Health. The Department is highly rated among programs nationally and offers MS, MPH, DrPH and PhD degrees. The Biostatistics Chair provides scientific and administrative leadership to 30 primary faculty, 17 secondary and adjunct faculty, and more than 100 gradu- ate students. Currently, the Department has more that $12 million annually in external research funding while GSPH as a whole ranks third in NIH funding among the nation’s 40 accredited schools of public health. The National Surgical Adjuvant Breast and Bowel Project Biostatistical Center and the Center for Occupational Biostatistics and Epidemiology are both currently located within the Department.

Candidates should have a distinguished record of research, teaching, publication, and service as well as experience with externally funded collaborative research projects. Candidates must have academic accomplishments that meet criteria for appointment at the tenured professor level, including an advanced degree (PhD, or equivalent) in statistics, biostatistics or a closely related area.

Review of applications will begin immediately and continue until the position is filled. Candidates should submit a letter of appli- cation stating professional accomplishments; curriculum vitae; and the names, mailing addresses, e-mail addresses, and telephone numbers of five professional references. Electronic applications and nominations are preferred and should be sent to bioschr@ pitt.edu. Applications and nominations may also be submitted by mail and should be sent to the search committee chair: Sheryl Kelsey, PhD, Biostatistics Chair Search Committee, Department of Epidemiology, University of Pittsburgh, A525 Crabtree Hall, 130 DeSoto Street, Pittsburgh, PA 15261. For further information and details about the Department of Biostatistics, go to http:// www.biostat.pitt.edu/.

The University of Pittsburgh is an equal opportunity, affirmative action employer. Women and minority candidates are encouraged to apply.

76 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT applied mathematics at the associate professor rank. Must have a PhD in sta- tistics, graduate teaching experience, and excellent communication and admin- istrative skills. To apply, go to https:// facultyopportunities.depaul.edu/applicants/ Central?quickFind=50625. Deadline December 31, 2009, or until position is filled. EOE. n Faculty biostatistician, Rush Section of Nutrition and Nutritional Epidemiology, Department of Internal Medicine. PhD in biostatistics or related field. Background in longitudinal analysis, field epidemiologic studies and prior supervisory/consulting experience desirable. Excellent communi- cation/computing skills required. Letter, curriculum vitae, and 3 references: Martha Clare Morris, Medical Services Building, 610 S. Maple, Ste. 4700, Oak Park, IL 60304. Rush University Medical Center is an EOE.

December 2009 Amstat News 77 Indiana n Purdue University department of sta- tistics faculty position screening starts 12/01/2009, until position is filled. Salary, rank, benefits commensurate with quali- fications. PhD in statistics or related field.

OPPORTPROFESSIONAL UNITIES Purdue is an Equal Opportunity/Equal Access/Affirmative Action employer fully committed to achieving a diverse work force. For further information, see www. stat.purdue.edu/hiring.

Iowa n The Holden Comprehensive Cancer Center (HCCC) at the University of Iowa, a National Cancer Institute-designated comprehensive cancer center, is seeking a biostatistician to provide statistical support for cancer research programs. For more information, please see www.uihealthcare. com/depts/cancercenter/welcome/position.html To apply, please see requisition #57260 at http://jobs.uiowa.edu/jobSearch/index.php.

78 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT INDIANA UNIVERSITY PURDUE Rutgers UNIVERSITY INDIANAPOLIS Applicable background checks will be con- The State University of New Jersey Tenure Track Faculty Positions in Biostatistics Department of Management Science ducted. The University of Iowa is an equal and Information Systems The IUPUI Department of Mathematical opportunity affirmative action employer. The Department of Management Science and Sciences invites applications for one or Women and minorities are strongly Information Systems (MSIS) has a tenure-track more tenure track faculty positions in Bio- encouraged to apply. opening starting Fall 2010 Semester at either statistics, with rank open, to begin 8/1/10. the Assistant or Associate Professor level. Candidates should have expertise in applied The appointment will be made in support n statistics. A candidate must be an active re- Statistical Geneticist-Trait Integration. searcher and have a strong record of scholarly of Indiana University’s Life Sciences Ini- Ankeny, IA. Monsanto is currently seeking excellence. Special consideration will be given tiative and the recently established Biosta- a highly motivated statistical geneticist to to candidates with knowledge of statistical ap- tistics Ph.D. program administered by the plications in business. Teaching and curricu- Department. A Ph.D. in statistics/biostatis- join the global trait integration organiza- lum development at the undergraduate, MBA, tion to develop, promote, and implement and Ph.D. levels will be expected. tics and a demonstrated strong interest in strategies for efficient stacking of multiple the development of statistical methods, col- biotechnology traits into elite germplasm Rutgers University is an affi rmative action laborative scientifi c research and in quality equal opportunity employer. Applications teaching at all levels, are required. and to evaluate the performance of biotech received by January 18, 2010 are guaranteed crops in agricultural field trials. For more full consideration. All applicants should have Applicants at the Associate or Full Profes- www.monsanto.com completed a Ph.D. degree in a relevant subject information, visit and area by the Fall-2010 Semester. Applicants sor level must have a record of signifi cant to apply online select req. #000QZ. EOE. should send curriculum vitae, cover letter, and research accomplishments and external the names of three references to: funding. Ms. Carol Gibson Kentucky ([email protected], pdf fi les only) For more information on the position and Department of Management Science and n application, visit: http://www.math.iupui. The department of statistics, University Information Systems edu/employment/. of Kentucky, is seeking an assistant pro- Rutgers Business School fessor, beginning August 2010. The suc- Rutgers, The State University of New Jersey 94 Rockafeller Road IUPUI is an EEO/AA Employer, M/F/D. cessful candidate is expected to teach Piscataway, NJ 08854-8054 undergraduate and graduate courses and

December 2009 Amstat News 79 conduct independent and collaborative research with investigators from the biologi- cal sciences. Send CV, research statement, and at least three reference letters to Kert Viele, Statistics Department, University of Kentucky, Lexington, KY 40506-0027. See http://web.as.uky.edu/statistics. UK is an AA/

OPPORTPROFESSIONAL UNITIES EOE.

Massachusetts n Abt Bio-Pharma Solutions is seeking entry-level PhD statisticians/biostatisticians interested in participating in exploratory analyses of data from clinical trials; meta- analyses using frequentist and Bayesian methods; and design, analysis, and report- ing of clinical trials, registries, and epidemi- ological investigations. The position offers the opportunity to work with experienced mentors on a variety of interesting projects. Please email cover letter and CV to peter. [email protected]. ABS is an EO/ AA Employer.

n Biostatisticians, faculty, and staff. Children’s Hospital Boston, Harvard seeks: a) instructor/assistant professor-pediatric cancer clinical trials, methodology, teach- ing. Requirements: PhD and commitment to pediatric cancer research; b) two biostat- isticians-statistical analysis of pediatric can- cer clinical trials; maintenance and analyses of international neuroblastoma database. Required: master’s degree and SAS. Send letter, CV, and three reference letters to Wendy B. London, c/o elise.porter@ childrens.harvard.edu. To apply online, see AutoReqId 20525BR at www. childrenshospital.org/careers/Site2115/ mainpageS2115P0.html. Children’s Hospital Boston is an Equal Opportunity Employer. Minorities and women are especially encouraged to apply. Children’s Hospital Boston offers a competitive com- pensation and benefits package.

n Boston University mathematics and sta- tistics invites applications for tenure-track assistant professor stochastic processes; all applications, statistics, bioinformat- ics, physics, and mathematical finance.

80 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT

Begins September 2010 pending budgetary approval. Strong commitment to research and teaching essential, interest in inter- disciplinary research preferred. Submit CV, research statement, and three letters of recommendation: Stochastic Processes Search, Mathematics and Statistics, Boston University, 111 Cummington St., Boston, MA 02215. Deadline 01/02/10. AA/EOE n Postdoctoral associate at the five col- lege consortium (Amherst, Hampshire, Mount Holyoke, and Smith Colleges and the University of Massachusetts Amherst). Duties include teaching at the liberal arts colleges, research at the University of Massachusetts, and consulting throughout the five colleges. Three years. Ideal for a new PhD to explore careers in large and small academic institutions. See www. mathjobs.org for details. UMass Amherst is an Affirmative Action/Equal Opportunity Employer. Women and members of minor- ity groups are encouraged to apply. n MS Biostatistician. Collaborate with medical and scientific researchers in design, analysis, and publication of cancer clinical trials and related research. Requirements: strong background in statistical principles, data analysis, computing (especially SAS and R), communication skills, and 1–2 Tenure-Track Associate/Full Professor of Biostatistics years of experience. Send CV, names of The University of South Carolina’s Arnold School of Public Health is seeking applicants for a tenure- three references to: MS Biostatistician Job track faculty position at the rank of Associate or Full Professor in Biostatistics in the Department of Search, Biostatistics & Computational Epidemiology and Biostatistics, with the possibility for leading the Health Sciences Research Core. The Arnold School of Public Health has national prominence in Epidemiology and Biostatistics, with research Biology, Dana-Farber Cancer Institute, funding from NIH, CDC, other federal and state agencies, private foundations and industry. There is sub- 44 Binney Street, Boston, MA 02115; stantial collaborative research with other entities on and off campus, and we expect signifi cant growth in [email protected]. the biostatistics faculty over the next several years. AA/EOE. The successful candidate is expected to have a strong record of publications in biostatistics, of teaching, and of biomedical collaboration. Areas of interest include, but are not limited to, design and analysis of clinical research, longitudinal and survival modeling, community-based studies, semi-parametric model- n The department of biostatistics, Harvard ing, Bayesian methods, robust methods, structural equation models, and spatial biostatistics. School of Public Health, is seeking candi- The successful candidate will have an interest in the application of statistical methodologies to the Health dates for tenure-track faculty positions in Sciences and is expected to develop and maintain an active research program and lead or participate in biostatistics. The successful candidates are externally funded grants, teach biostatistics courses primarily to graduate students in Biostatistics, Epi- expected to teach, conduct research, hold demiology, and other fi elds, chair thesis committees of students in our Master’s and doctoral programs in a doctoral degree with research interests in biostatistics, and mentor junior faculty in the Division of Biostatistics. environmental health or HIV. See www. Additional information about the school and department can be found at www.sph.sc.edu. Applications biostat.harvard.edu/people/jobs.html for will be considered until the position is fi lled. Applicants should send a cover letter stating career goals and the relevance of the candidate’s training and experience to described needs, a current CV, and names more information. HSPH is committed and contact information for three references to: to increasing representation of women and minority members among its faculty and Biostatistics Search Committee particularly encourages applications from Arnold School of Public Health, University of South Carolina, 800 Sumter Street, Columbia, SC 29208 such candidates. [email protected] The University of South Carolina is an affi rmative action/equal opportunity institution. Women and minorities are encouraged to apply.

December 2009 Amstat News 81 WORCESTER POLYTECHNIC INSTITUTE APPLIED STATISTICS POSITION n Postdoctoral fellowships are available Worcester Polytechnic Institute (WPI) invites applications for the position of Assistant in the department of biostatistics at Professor, tenure-track, in biostatistics and/or applied statistics, beginning 2010. the Harvard School of Public Health. Applicants with teaching and scholarly interest in the areas of biostatistics, computa- Fellows will engage in methodological tional statistics, experimental design, Bayesian methods are especially encouraged. The research and participate in ongoing col- Mathematical Sciences Department has 25 tenured/tenure-track faculty and supports laborative projects. View details at www. BS, MS, and Ph.D. programs in applied, fi nancial and industrial mathematics and applied statistics.WPI is on the Chronicle of Higher Education’s 2009 list of “Great Colleges to hsph.harvard.edu/departments/biostatistics/

OPPORTPROFESSIONAL UNITIES Work For.” Further information about WPI and the department can be accessed at http:// fellowship-opportunities. Applications from www.wpi.edu/+math. minority and female candidates are espe- cially encouraged. Harvard University is an An earned Ph.D. or equivalent degree is required. Successful candidates must be able to contribute strongly to both the department’s research activities and its innovative, AA/EOE. project-based educational programs.

Founded in 1865, WPI is one of the nation¹s oldest technological universities. Today, WPI is a highly selective private university with an undergraduate student body of over 3,200 Michigan and 1,100 full-time and part-time graduate students enrolled in more than 50 Bachelor’s, n Master’s, and Ph.D. programs. WPI is consistently ranked among the top national univer- University of Michigan-Ann Arbor. The sities in U.S. News & World Report. Its innovative project-enriched curriculum engages department of statistics invites applications students and faculty in real-world problem solving, often at one of WPI’s project centers. for a tenure-track position at the assistant The university is located in the heart of Massachusetts and an hour away from Boston. professor level, starting 09/10. Doctorate

Qualifi ed applicants should send a detailed curriculum vitae, a brief statement of specif- in statistics or a related field, excellence in ic teaching and research objectives, and three letters of recommendation at least one of research and teaching required. See www. which addresses teaching potential, to: Math Search Committee, Mathematical Sciences stat.lsa.umich.edu regarding materials to Department, WPI, 100 Institute Road, Worcester, MA 01609-2280, USA. Applicants will be be provided. Competitive salary/fringe considered on a continuing basis until the position is fi lled. Review of applications will benefits. Review of applications will com- start December 1, 2009. mence on December 15, 2009. Women To enrich education through diversity, WPI is an affi rmation action, equal opportunity employer.

82 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT

Department of Health and Human Services and minorities are encouraged to apply. National Institutes of Health The university is supportive of the needs National Heart, Lung, and Blood Institute (NHLBI) of dual-career couples. Affirmative Action/ Equal Opportunity Employer. MATHEMATICAL STATISTICIAN (BIOMEDICAL) GS/AD-1529-13/14, HHS/NIH-2010-0032 2009 Salary range: $86,927 - $133,543 Minnesota Closing date: January 15, 2010 n University of Minnesota has an assistant The Office of Biostatistics Research (OBR), NHLBI invites applications for a professor position effective fall 2010. Visit position as a mathematical statistician (biomedical). OBR has broad inter- www.stat.umn.edu for details. Submit ests in clinical studies, including early stopping and extending of clinical tri- letter of application and CV online at als, multiplicity issues, survival analysis, longitudinal data analysis, statistical https://employment.umn.edu (req#163071). genetics. The successful applicant will be responsible for research/consul- Send graduate transcript, no more than tation/collaboration in clinical studies. 5 reprints/preprints, arrange for three reference letters to: Faculty Search, School Applicants must meet the minimum education and experience requirements of Statistics, 313 Ford Hall, 224 Church for a mathematical statistician as defined by the U.S. Office of Person- Street SE, Minneapolis, MN 55455. nel Management manual, Qualifications Standards for General Schedule Review begins 01/01/2010. University of Positions. Position requirements and detailed application procedures are Minnesota is an equal opportunity employ- provided on the vacancy announcement (HHS/NIH-2010-0332) at http:// er and educator. usajobs.opm.gov/. Applications can be faxed to 301-402-2232, e-mailed to [email protected] or mailed to Office of Human Resources, 2115 East Jefferson Street, Room 1-E142, Bethesda, MD 20892-8502. Inquiries Missouri to N. Geller, [email protected]. n A tenure-track assistant or associ- DHHS/NIH are Equal Opportunity Employers. ate professor of biostatistics at the Saint Louis University School of Public Health.

December 2009 Amstat News 83 Chair, Department of Informatic Medicine and Personalized Health

The School of Medicine at the University of Missouri-Kansas City (UMKC) is seeking a Applicants must have a PhD degree in dynamic individual to lead the development of a new Department of Informatic Medicine and biostatistics or applied statistics or a related Personalized Health. Because of the rapid growth of its translational research programs in field. Applications sent to: http://jobs.slu. bioinformatics, health outcomes, quantitative genetics, genetic epidemiology, health services edu (Job# 20090553). Inquiries: John Fu, research, and related fi elds, the school is establishing this department and has embarked on a major development plan to further build its research and educational programs. The new Director, Division of Biostatistics, qjfu@ chair will have an exceptional opportunity to lead these efforts, recruit new faculty, and to slu.edu. Review of applications will begin in galvanize and expand emerging internal and external partnerships that can attain national February 2010 and continue until the posi-

OPPORTPROFESSIONAL UNITIES recognition for excellence. tion is filled. AA/EOE.

Candidates for this position should have a PhD, MD or equivalent degree, and a distinguished record of research productivity, a commitment to teaching and education, and the vision and n leadership skills to successfully build a dynamic new department. Preference will be given to Tenure-track position in the department candidates with experience in bioinformatics, epidemiology/health services research, biosta- of mathematics and statistics, beginning tistics, health informatics or a related discipline. Additional desirable qualifi cations include: fall 2010. Strong research and teaching (1) demonstrated leadership in developing and administering academic and interdisciplinary potential, applied interests, and PhD in sta- research programs; (2) an established track record of external grant support; (3) ability to col- tistics by 8/15/2010 required. Details laborate and work in teams that cross disciplines and institutions, and (4) demonstrated ability at http://math.mst.edu/department/ to recruit nationally known faculty and to mentor junior faculty. The successful candidate employment.html. Submit research plan, is expected to qualify for appointment at the level of full professor with tenure. UMKC is a comprehensive university with a strong focus on the health sciences, which in addition to teaching philosophy, CV, three refer- the School of Medicine, includes schools of dentistry, nursing, , arts and sciences, ence letters, and transcripts to: Human computing and engineering, biological sciences, law, and business and public administra- Resource Services, Reference Number tion. Partnerships with other institutions in the region, and throughout the country, provide 29318, Missouri University of Science additional opportunities for building centers of excellence. Review of applications will begin and Technology, Rolla, MO 65409-1050. immediately and continue until the position is fi lled. UMKC is an AA/EOE institution. Review begins 12/01/2009 and will con-

Please send a letter of interest, CV, and the names of three references to Amy Gilmore, tinue until filled. Missouri University of UMKC School of Medicine Business Offi ce, 2411 Holmes Street Kansas City, MO 64108 or Science and Technology is an AA/EEO [email protected] institution. Women, minorities, and

84 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT persons with disabilities are encouraged to apply. Missouri S&T participates in E-Verify. For more information on E-Verify, please contact DHS at (888) Junior Tenure Track Positions 464-4218. The Department of Statistics at North Carolina State University invites applications for one or more junior tenure track faculty (Assistant Professor) New Hampshire positions. Appointments are to begin in August 2010. n Statistical analyst and post-doctoral fel- The Department is one of the oldest and largest in the country and provides lows, NCI Comprehensive Cancer Center. a dynamic environment for teaching, research and collaborations across Analyst/programmer w/MS in biostatistics disciplines. The Department is a partner in the Center for Quantitative to support statistical consulting/comput- Sciences in Biomedicine and the Bioinformatics Research Center. The ing/data management/database develop- Department’s location in the Research Triangle provides rich opportunities ment in active clinical/population research for interactions with industry; other universities, including Duke University programs; multiple post-docs in com- and the University of North Carolina at Chapel Hill; and government parative effectiveness and interdisciplinary agencies. Faculty enjoy collaborations with medical researchers at Duke, research, requires PhD/MD, biostatistics environmental scientists at the EPA research facility, pharmaceutical correlated quantitative sciences. Additional researchers at GlaxoSmithKline, and software developers at SAS Institute, information available upon request. Full among many others. The Department also is a founding cooperator of Dartmouth benefits. Email: Biostatistics. the National Institute of Statistical Sciences (NISS) and the NSF funded [email protected]. CV Statistical and Applied Mathematical Sciences Institute (SAMSI). Both plus 3 references to: Andrea Tillotson/ NISS and SAMSI provide excellent research opportunities. The Department Biostatistics Search/H7920/Dartmouth moved into a newly constructed SAS Hall in May 2009, offering state-of- Medical School/One Medical Center the-art offi ces and instructional facilities. It is an exciting time to be in the Drive, Lebanon, NH 03756. Dartmouth Research Triangle area and an exciting time to join a department that is College is an equal opportunity, affirmative looking to expand signifi cantly on its strengths. action employer. Women and minorities are encouraged to apply. www.cancer. All applicants must have completed all requirements for a PhD in Statistics dartmouth.edu. or Biostatistics by the time of employment. Responsibilities include teaching and research. The department seeks applications from candidates from ALL areas of statistics. Preference will be given to applicants with a New York background in sampling methods, analytics and computational statistics, n Memorial Sloan-Kettering Cancer and a research interest in health, energy or environment. Center has positions available for mas- ter’s-level biostatisticians. The successful Please visit https://jobs.ncsu.edu/applicants/Central?quickFind=84432 applicant will engage in wide variety of for more information and to apply. All applicants should complete an collaborative projects w/medical investi- Applicant Profi le and attach a letter of application and curriculum vitae. In gators and statisticians. Projects involve addition to submitting those materials online, applicants should also submit the design, analysis and publication of recent transcripts and arrange for three letters of references to be sent clinical, laboratory, or cancer prevention directly to the Department to [email protected] or as hard copy to research. Qualifications include excellent the address below. All reference letters will be made available for review programming skills, proficiency in database by the departmental voting faculty. Processing of applications will begin manipulation, and good verbal and written December 10, 2009 and continue until the positions are fi lled. communication skills. Please email cover letter and CV to EPIBIOSTATS@mskcc. Mailing Address: Chair, Statistics Search Committee, Campus Box 8203, org. Memorial Sloan-Kettering Cancer NCSU, Raleigh, NC 27695-8203 Center is an AA/EOE. For more information about the department, see: http://www.stat.ncsu. edu/. Please do not hesitate to contact Sastry Pantula, Head [(919) 515-1949, [email protected] to discuss your potential interest in the North Carolina position. n VP or director of statistics. Specialty AA/EOE. In addition, NC State University welcomes all persons without regard to sexual orientation. CRO seeking executive-level statistician Individuals with disabilities desiring accommodations in the application process should contact Felicia Harris, voice: (919) 515-1944; email: [email protected]; fax: (919)515-7591. We welcome the opportunity to work with candidates to identify suitable employment opportunities for spouses or partners.

December 2009 Amstat News 85 Assistant/Associate Professors of Biostatistics Department of Biostatistics Harvard School of Public Health to join our team. The position requires 10 years experience in statistical support of The Department of Biostatistics at the Harvard School of Public Health (HSPH) seeks outstanding candi- dates for two positions of assistant or associate professor of biostatistics. These are tenure-ladder positions, clinical trials. Medical device experience with the academic rank to be determined in accordance with the successful candidates’ experience and desired. Demonstrated management skills a productivity. plus. Master’s or PhD in statistics required. The new faculty members will focus on methodological and collaborative statistical research motivated Contact [email protected]. EOE. by biomedical collaborations in the areas of environmental health sciences or AIDS research. No specific type of statistical expertise is sought, and applicants need not have prior experience in these collaborative OPPORTPROFESSIONAL UNITIES areas, but should be interested in developing a research agenda that is related to one of them. Regarding the environmental health position, relevant areas of expertise may include, but are not limited to, quantitative n The Statistical and Applied Mathematical methods for high-dimensional data, including methods for analyzing “omics” and gene-by-environment- Sciences Institute (SAMSI), a national insti- interaction data; exposure measurement error; novel analytic and computational methods for analyzing tute in North Carolina, seeks postdoctoral large environmental epidemiological databases; and Bayesian data methods for complex models of environ- mental health effects. For the AIDS position, all statistical areas related to observational and clinical trials fellows for 2010–2011. Fellows are typically research are relevant, including those required for analysis of high-dimensional data on human and/or viral appointed for two years, earn a competitive genetics. For both positions, a strong track record in the pursuit of innovative methodological research is salary, and receive exceptional mentoring. required. Candidates are expected to hold a doctoral degree in biostatistics or statistics. See www.samsi.info for further information. Please send a letter of application, including a statement of current and future research interests, curriculum Members of under-represented groups are vitae, sample publications, and the names of four referees to the following address. Applicants should ask their four referees to write independently to this address. The electronic submission of application docu- particularly encouraged to apply. Statistical ments to the email below is welcome. and Applied Mathematical Sciences Chair, Search Committee for Assistant/Associate Professors of Biostatistics Institute is an AA/EOE. c/o Vickie Beaulieu Department of Biostatistics Harvard School of Public Health 655 Huntington Avenue, 4th Floor Boston, MA 02115 Oklahoma Email: [email protected] n Tenure-track assistant professor posi- Harvard University is committed to increasing representation of women and minority members among its faculty and particularly tion beginning August 2010. PhD in encourages applications from such candidates. statistics, demonstrated excellence in teaching, and research potential required.

86 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT

Bureau of Justice Statistics, Department of Justice Mathematical Statistician GS-1529-13/14

The Bureau of Justice Statistics (BJS) is the nation’s primary source for criminal justice statistical information. As the principal federal statistical agency of the Department of Justice, BJS is responsible for the collection, analysis, publication, and dissemination of timely and accurate statistical information on crime, criminal offenders, victims of crime, and the operation of justice systems at all levels of government.

Although a relatively small agency, BJS has a nationally-recognized professional staff which has pioneered numerous criminal justice statistical projects. The vast majority of the staff hold advanced academic degrees. Many of the staff actively participate in profes- sional associations, present papers at national and international conferences, and author articles and books on criminal justice and related topics.

This position, located in BJS’s Victimization Unit, provides a unique and challenging op- portunity to work on the redesign of the National Criminal Victimization Survey, BJS’s premier criminal justice survey program, and to improve the quality of national data about crime and its victims. The incumbent will contribute to the development of study plans and methodologies, sampling strategies, survey instrumentation, data analyses, and other key technical components. The incumbent will help identify and resolve methodological problems and operational challenges, evaluate results and prepare documentation and re- ports for public release. In addition, the incumbent will participate and/or serve as a team lead on internal and external working groups to advise on technical aspects of BJS’s law enforcement, corrections, prosecution and adjudication data collections.

Salary Range The salary range is $86,927 to $133,543. Salary will be set to commensurate with educa- tion and experience.

How to Apply This is an online application process. Even if you have already developed a resume in USAJOBS, you will need to access this on-line system to complete the application process by December 29, 2009. To obtain information about this position and TO APPLY, please click on http://www.avuecentral.com/vacancy.html?ref=UVDWJ.

If you have any further questions, please contact Lisa Price-Grear at (202) 616-3561. For more information about BJS, visit our website at http://bjs.ojp.usdoj.gov.

December 2009 Amstat News 87 Review of applications begins 01/15/2010 and continues until filled. Send letter of application, CV, transcripts, and arrange to have three recommendation letters to: DEPARTMENT OF BIOSTATISTICS Chair, Search and Hiring Committee, Statistics Dept., 301 MSCS, Oklahoma State University, Stillwater, OK 74078-

OPPORTPROFESSIONAL UNITIES 1055. For information, visit our web site Junior Tenure-Track Faculty Positions at http://statistics.okstate.edu. Oklahoma State University is an AA/EEO/E-Verify The Department of Biostatistics at the Johns Hopkins Bloomberg employer committed to diversity. Woman School of Public Health seeks applications to join our tenure-track and minorities are encouraged to apply. faculty at the rank of Assistant Professor. Candidates should have a PhD or equivalent in statistics, biostatistics, or a comparable fi eld, or in computer science and, like the Department, a commit- Oregon ment to education and research to advance statistical and quantita- n To develop an accredited school of tive reasoning, methods and discovery in the health sciences. public health and in support of the Environmental Health Sciences Center, the department of public health at Oregon State University seeks 2 to 3 tenure-track Senior Tenure-Track Faculty Position assistant/associate professors of biostatistics. To see full position announcement and The Department also welcomes applications to join our tenure- to apply, go to www.hhs.oregonstate.edu/ track faculty at the rank of Associate or Full Professor. Candi- jobs. To be considered, you must apply dates should have a record of leadership in education and research online at Oregon State University posting #0004931. Oregon State University is an to advance statistical and quantitative reasoning, methods and dis- Affirmative Action/Equal Opportunity covery in the health sciences. Employer and has a policy of being respon- sive to dual-career needs. The Hopkins Department of Biostatistics, founded in 1918, was the fi rst degree-granting department of statistical science in the US Pennsylvania and has ranked among the best throughout its history. The Johns Hopkins Health Institutions (Schools of Public Health, Medicine, n Temple University Department of and Nursing, and the Johns Hopkins Hospital) are among the top Statistics invites applications for a depart- ment chair and at least one senior associate worldwide and provide a research environment in which energetic professor for tenure-track faculty positions. faculty can promulgate scientifi c excellence. Today, the Depart- Candidates must have a PhD in statistics, ment comprises 19 tenure track faculty members, 11 research publications in top-tier journals, teaching track faculty members, 31 PhD students, and 17 full-time master excellence, and strong theory/application background. Strong candidates in any degree students. area of statistics will be considered. Apply electronically to Sanat Sarkar, stat@ temple.edu. Include cover letter, CV, and three letters of recommendation. Temple TO APPLY University is an Equal Opportunity/ Email cover letter, CV, contact information for three references, Affirmative Action Employer and specifi- and statement of research interests and goals to: Faculty Search cally invites applications from women Committee at [email protected]. EOE/AA and minorities.

Women and under-represented minority candidates are particu- n Possible tenure-track, lecturer, visit- larly encouraged to apply. The Johns Hopkins University is an ing positions. Collegial environment affi rmative action/equal opportunity employer. emphasizing disciplinary and cross- disciplinary research and teaching. All

88 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT areas of statistics welcome. Joint appoint- ments possible with other units in the Pittsburgh area. See www.stat.cmu.edu UNIVERSITY OF SOUTH CAROLINA DEPARTMENT OF STATISTICS (email: [email protected]). Send CV, Assistant and Associate Professor Positions research papers, relevant transcripts, The Department of Statistics at the University of South Carolina invites applications for three tenure- and three recommendation letters to: track faculty positions. Two of these positions are at the rank of Assistant Professor, while the other posi- Faculty Search Committee, Statistics, tion could be up to the rank of Associate Professor. Applicants for the Assistant Professor positions must Carnegie Mellon University, Pittsburgh, have strong potential for excellence in research and teaching, while applicants for the Associate Professor position must have excellent research and teaching credentials. PA 15213. Application screening begins immediately, continues until positions The department currently consists of ten tenure-track faculty and three full time instructors. We en- closed. Women and minorities are courage applications in any specialty area of statistics which will enhance or complement our current expertise (see www.stat.sc.edu/research/). Individuals having a PhD in statistics with research focus in encouraged to apply. AA/EOE. /actuarial science or in areas applicable to the University’s research initiatives in bioinfor- matics or nanotechnology are also encouraged to apply.

Appointments will commence August 2010. For full consideration, applications for Assistant Professor Texas must be received by December 1, 2009 while applications for Associate Professor must be received by January 4, 2010. Curriculum vita, at least three letters of reference, and a copy of graduate transcripts n The department of epidemiology (for the Assistant Professor level) are required. Materials should be sent to: and biostatistics at the School of Rural Faculty Search Committee Public Health, Texas A&M Health c/o Ms. Tina Ormenisan Science Center, is seeking candidates Department of Statistics University of South Carolina for two open-rank, 12-month, state- Columbia, SC 29208 USA funded, tenure-track faculty positions. Qualifications include a PhD or equiva- Inquiries about these positions should be sent to Professor Edsel A. Peña, Chair of the Faculty Search lent in biostatistics or statistics. See http:// Committee, using the e-mail address [email protected]. srph.tamhsc.edu/epidemiology-biostatistics/ The University of South Carolina is an affi rmative action, equal opportunity employer. Women and minorities are encouraged to apply. The University of South Carolina does not discriminate in educational or employment opportunities or decisions for qualifi ed persons on the faculty-positions.html for more informa- basis of race, color, religion, sex, national origin, age, disability, sexual orientation or veteran status. tion. Send cover letter, CV, and three

December 2009 Amstat News 89 NORC conducts high quality social science references to [email protected]. research in the public interest from its head- Review of applications will begin on quarters at the University of Chicago and January 8, 2010, until positions filled. from its offices in Chicago, IL, Washington, Texas A&M Health Science Center is an DC, Bethesda, MD, and Berkeley, CA. EEO/AA Employer. We conduct research in economics, demo- graphics, education and child development, health, substance abuse, mental health, OPPORTPROFESSIONAL UNITIES justice, and survey quality both in the U.S. and internationally. We offer full-service Virginia survey design and operations as well as n Manager, Biostatistics & Epidemiology. strengths in analysis, information technol- ogy, and technical assistance. NORC sup- Responsibilities: create, implement, and ports the research needs of government in manage a program of biostatistical and the U.S. and abroad, international donor epidemiological services that promote agencies, foundations, academic research- research on the clinical and outcomes. ers, and private organizations. Requirements include: master’s degree, NORC is actively seeking statisticians, preferably in biostatistics or a bachelor’s survey methodologists, statistical program- degree in biostatistics; professional mers, data managers, survey directors, and social scientists with advanced training experience in a research environment; or experience in survey research or survey and preparing analytical methods/results operations. New staff will be based in our for publication in professional journals. Chicago, IL or Washington, DC offices. To Call: (703) 776-2796, or visit: www. learn more about NORC and to apply for employment, visit our website at: inova.org/careers. EOE/Pre-employment drug screening required. Tobacco-free http://www.norc.org/careers environment. AA/EOE. NORC is an affirmative action, equal opportunity employer that values and actively seeks diversity in the workforce.

n The department of statistics (http:// statistics.gmu.edu), George Mason University (GMU), Fairfax, Virginia, Yale School of Public Health has an open-rank faculty position (ten- Yale University School of Medicine ured or tenure-track). The candidate should have a PhD in statistics or bio- RESEARCH TRACK FACULTY POSITIONS statistics, be prepared to conduct inde- pendent and collaborative research, and e Yale Center for Analytic Sciences (YCAS) is seeking multiple academically trained, professional bio- statisticians to join the biostatistical team as Research Scientists with appointments in the Yale School to teach and mentor at the advanced of Public Health. One Research Scientist will collaborate with clinical investigators at the Yale Cancer graduate level. Research areas include Center and the others will collaborate with Yale School of Medicine on biostatistical and epidemiologic biostatistics, biometric identification, methods. e positions involve consultation, collaboration and support for clinical researchers as well as data exploration, and statistical comput- supervision of master’s levels statisticians and the teaching of statistical principles to young investigators. ing. Apply at http://jobs.gmu.edu, posi- Both positions will have considerable involvement in developing statistical components of investigator- initiated grant applications. e ability to work independently on several diff erent projects with a range tion number F9318Z. GMU is an equal of investigators across a variety of clinical disciplines is essential. opportunity/affirmative action employ- er. Women and minority candidates are Responsibilities include: 1) Providing expert biostatistical consultation and collaboration on study de- particularly encouraged to apply. sign, implementation, analysis and the preparation of protocols, grants and manuscripts for multiple projects; 2) Planning and overseeing comprehensive analyses for many types of data and types of studies; 3) Training clinical faculty in the principles of biostatistics and study design and 4) Supervising master’s level biostatisticians. Canada e successful candidate will have a doctoral degree in Statistics, Biostatistics, Epidemiology or a related fi eld with four years experience in grant writing and experimental design. Excellent oral and written British Columbia communication skills along with profi ciency with statistical computer languages such as SAS, R, S-plus n University of British Columbia etc. are a must. Knowledge and experience in , data collection and management, and data analysis for a wide range of experimental and observational studies such as clinical trials, method Statistics Department invites applica- comparison and longitudinal studies are required. Experience in the design and analysis of cancer related tions for a tenure-track assistant profes- research studies (eg. Early Phase Clinical Trials) is required for the Cancer Center position. sor position starting July 2010. Submit application to [email protected]. Visit Interested candidates should send a cover letter, CV and three names of references to james.dziura@ yale.edu. www.stat.ubc.ca for more informa-

Yale University is an affi rmative action/equal opportunity employer. Yale values diversity in its faculty, students, and staff and espe- tion. UBC hires on merit basis and is cially welcomes applications from women and underrepresented minorities.

90 Amstat News December 2009 U NITIE S PROFESSIONAL OPPORT committed to employment equity. We Ontario research record in actuarial science comple- encourage all qualified persons to apply, menting the department. Good teach- particularly women, visible minori- n Actuarial Science-Lecturer. Statistics/ ing and communication skills; see www. ties, and individuals with disabilities. actuarial science-limited-term lecturer posi- stats.uwaterloo.ca. Submit CV and three Canadians and permanent residents of tion in actuarial science with eligibility for reference letters to Paul Marriott, Chair, Canada are given priority. reappointment as continuing lecturer. PhD Statistics and Actuarial Science, University preferred; master’s seriously considered. of Waterloo, Waterloo, Ontario N2L 3G1, Committed to excellence in teaching with Canada. Closing: January 31, 2010. EOE. n University of British Columbia good communication skills. Professional Statistics Department is hiring a tenure- actuarial qualifications and experience pre- track instructor, start date July 2010. ferred; see www.stats.uwaterloo.ca. Submit n Biostatistics-assistant or associate. Apply online at http://hr.ubc.ca/careers/ CV and three reference letters to Paul Statistics/actuarial science-tenure-track faculty_postings.html or by email search@ Marriott, Chair, Statistics and Actuarial positions in biostatistics, assistant or asso- stat.ubc.ca by January 24, 2010. Visit Science, University of Waterloo, Waterloo, ciate; contingent upon funding. PhD in www.stat.ubc.ca for more information. Ontario N2L 3G1, Canada. Closing: statistics or biostatistics. Proven research UBC hires on merit basis, commits 01/31/2010. EOE. record w/statistical methods in collab- to employment equity. We encourage all orative health research. Opportunities for qualified persons to apply, particularly extensive collaboration. Good teaching and women, visible minorities, and individuals n Actuarial Science-Tenure Track. communication skills; see www.stats. with disabilities. Canadians and permanent Statistics/actuarial science-tenure-track uwaterloo.ca. Submit CV and three ref- residents of Canada are given priority. position in actuarial science, assistant or erence letters to Paul Marriott, Chair, associate professor rank. PhD in mathe- Statistics and Actuarial Science, University matical, statistical, or actuarial sciences and of Waterloo, Waterloo, Ontario N2L 3G1, Canada. Closing: 01/31/2010. EOE. n

December 2009 Amstat News 91 OPPORTPROFESSIONAL UNITIES

92 Amstat News December 2009 S DIRECTORY ASA RE S O U RCE

Contacts General Information Information about any of the Main following may be found by linking American Statistical to the web sites listed below or by Association contacting Member Services. 732 North Washington Street Alexandria, VA 22314-1943 Amstat Online Phone: (703) 684-1221 Access up-to-date information Toll-free: (888) 231-3473 at www.amstat.org. Updated Fax: (703) 684-2037 often, the ASA’s web site gives Email: [email protected] you access to recent news; the ASA’s products and services; and section, chapter, and committee ASA Departments home pages.

Advertising: advertise@ amstat.org ASA Membership Amstat News: amstat@ ASA members receive Amstat Host a Membership Social Sponsor an ASA Membership amstat.org News, enjoy a variety of discounts, Now you can sponsor the mem- Awards: [email protected] build an invaluable network of Host a membership social and more than 18,000 members, and the ASA will reimburse up to bership of a colleague, student, or Education: educinfo@ expand their career horizons. To $100 to cover the cost of pizza, K–12 school. You also can give ASA amstat.org join, go to www.amstat.org/join. sandwiches, snacks, and soft membership as a gift! Visit www. drinks. Visit www.amstat.org/ amstat.org/membership/SAM. Fellowships and Research membership/pdfs/ Member Services Programs: ChapterSchoolSocials.pdf Student Membership Drive [email protected] Do you have an address change, to participate. membership question, claim, or Students join the ASA at the Journals: journals@ special rate of $10. Visit general inquiry? Please call the Member Demographics amstat.org ASA Member Service’s toll-free www.amstat.org/join. direct line, (888) 231-3473, for The ASA collects demograph- Meetings: meetings@ all your ASA needs. If you prefer, ics data to create summary Chapter-Get-A-Member amstat.org email Member Services at reports of the ASA membership Chapters are the grass roots of [email protected] or fax to and develop services. All indi- Membership/Member the ASA, which is why we are (703) 684-2037. vidual demographic information Services: remains confidential. Visitwww. challenging our chapters to help [email protected] amstat.org/membersonly and click increase membership with the “My Demographic Profile” under Chapter-Get-A-Member cam- Web site: webmaster@ Campaigns for the ASA “My Account” to participate. paign. Visit www.amstat.org/ amstat.org membership/cgm. Giving to the ASA Members and friends of the ASA Member-Get-A-Member may contribute to the statistics Recruit your colleagues for ASA profession by financially support- membership! You depend on the ing our mission and goals. The ASA, and we count on you, too. We ASA is a 501(c) (3) not-for-profit know our current members are corporation. Contributions to the the best possible sources for new ASA are tax deductible. Please members who could benefit from visit www.amstat.org/giving for all the ASA has to offer. Visitwww. more information. amstat.org/membership/mgm.

DECEMBER 2009 Amstat News 93 n JSM Proceedings. Each year, the ASA publishes papers pre- sented at JSM. For more informa-

ASA RE S O U RCE S DIRECTORY tion, visit www.amstat.org/ publications/booksandcds.cfm.

Ethical Guidelines ASA JobWeb/Career Center Encourage ethical statistical work in morally conducive work envi- The ASA JobWeb, a targeted job ronments. Visit www.amstat.org/ database and résumé-posting about/ethicalguidelines.cfm or con- service, helps you take advantage tact Member Services to request of valuable career opportunities. Publications & a copy. Check out the services available Products n Guidelines for Assessment at www.amstat.org/jobweb or and Instruction in Statistics Journals & Magazines email [email protected]. Back Issues Education (GAISE) Report: A The ASA offers a variety of pub- Back issues of ASA publications Pre-K–12 Curriculum Frame- Chapters & Sections lications in print and online. Visit may be ordered by sending an work provides a conceptual www.amstat.org/publications for Network with thousands of col- email to [email protected]. framework for K–12 statistics more information. leagues through the ASA’s region- education and a coherent pic- al chapters and special-interest ture of the overall curriculum. Books sections. For more information, For more information, visit www. Video Series visit www.amstat.org/chapters or n Making Sense of Statistical amstat.org/education/gaise. The Distinguished Statistician www.amstat.org/sections. Studies provides hands-on inves- Video Series offers the chance to tigations to help students design Brochures bring a lecture or discussion by a and analyze statistical studies. Visit Current Index to Statistics (CIS) renowned statistician to any ASA www.amstat.org/education/msss. The ASA publishes brochures on chapter meeting, university class- ASA members enjoy free online topics of interest to professional room, company archive, or home access to the Current Index statisticians and those who want n The ASA-SIAM Series on collection. For more information, to Statistics (CIS). To activate to explore the field of statistics. Statistics and Applied Probability email [email protected]. your CIS access, log in to ASA Many brochures are available at provides works of general inter- Members Only at www.amstat. no charge or for a nominal fee. For est to statisticians, applied org/membersonly and select the more information and to order, mathematicians, engineers, and CIS Web Access tab. visit www.amstat.org/ASAStore/ Member Benefits scientists. The series is jointly Brochures_C104.cfm. and Honors published by the ASA and the Committees Society for Industrial and Applied Awards Mathematics. Visit www.amstat. CDs Since its founding in 1839, Each year, a number of awards the ASA has depended on the org/publications/booksandcds.cfm. n 41 Years of Technometrics. are presented in recognition of invaluable service of dedicated Now you can have all articles pub- outstanding contributions or volunteers, working through n lished during the first41 years of Teaching Statistics: Resources dedication to the field of statistics. committees, to achieve its goals. Technometrics at your fingertips. for Undergraduate Instructors For more information, visit www. Visit www.amstat.org/comm for For more information, visit www. is a publication of the ASA and amstat.org/careers/awards.cfm or information. the Mathematical Association of amstat.org/publications/ email [email protected]. America. For more information, booksandcds.cfm. visit www.amstat.org/publications/ Education booksandcds.cfm. With the help of knowledgeable and well-respected leaders in the profession, the ASA’s Center for Statistics Education is able to pro- vide quality educational oppor- tunities to statisticians of all levels of achievement. Visit www.amstat. org/education or email educinfo@ amstat.org.

94 Amstat News December 2009 S DIRECTORY ASA RE S O U RCE

E-newsletter JSTOR ASA members receive a monthly ASA members can purchase e-newsletter, ASA Member access to the JSTOR database of News, full of updates and special JASA, TAS, Technometrics, JABES, ASA Calendar of Events announcements. View the lat- JBES, and JCGS. JSTOR is a web The ASA Calendar of Events is est issue at www.amstat.org/ archive of every issue of these a searchable online database newsletters. publications, with the exception Reciprocal Societies of statistical events throughout of the most recent five years. If you reside in a developing the world. Visit www.amstat.org/ Fellows To purchase access, visit www. country and are a member dateline. amstat.org/publications/pdfs/ of one of the ASA’s reciprocal Annually, full members of estab- JSTORSpecialOffer.pdf. societies, you are eligible to Editorial Calendar lished reputation who have made receive an additional $5 off your outstanding contributions to sta- Member Directory developing country member- The Amstat News editorial calen- tistics are recognized by selection ship dues. Visit www.amstat.org/ dar is available at www.amstat. for Fellow. Visit www.amstat.org/ A full member directory is avail- membership/devcountries/app/ org/publications. fellows for more information. able at www.amstat.org/ index.cfm?fuseaction=ShowApp membership/directory/index.cfm for more information. Mailing Lists Grant Program or via ASA Members Only. Only members who choose to partici- The ASA membership list is avail- Six major research programs pate are listed. Salary Report able to rent from our list broker, and one grant program are An annual report of salaries of InFocus. Contact Jessecua Nairn administered by the ASA. Visit Members Only academic statisticians is available of InFocus at JNairn@infocuslists. www.amstat.org/careers/ at www.amstat.org/careers/ com for more information or to fellowshipsgrants.cfm or email As a member of the ASA, you salaryinformation.cfm. order the ASA mailing list. Only [email protected] for more have access to many additional members who choose to partici- information. features and options, including pate are listed. an enhanced searchable mem- Other Resources Joint Statistical Meetings ber directory, the e-newsletter archive, CIS, and discounts. You Advertising JSM is the largest annual gath- also have the ability to manage Advertise in the ASA’s publica- ering of statisticians in North your account online. Visit tions or online. ASA corporate America. Sponsored by the ASA, www.amstat.org/membersonly. International Biometric Society and institutional members receive (ENAR and WNAR), Institute of significant discounts on display Mathematical Statistics, Statistical advertising. Visit www.amstat.org/ Society of Canada, International publications/advertising.cfm or Chinese Statistical Association, and email [email protected]. International Indian Association, JSM is attended by more than 5,000 people each year. Visit www. amstat.org/meetings or email [email protected].

December 2009 Amstat News 95 DECEMBER 2009 • Issue #390

AMSTATNEWS ADVERTISING DIRECTORY

Listed below are our display advertisements only. If you are looking for job-placement ads, please see the professional opportunities section. For more job listings or more information on advertising, please visit our web site at www.amstat.org.

MISC. PRODUCTS AND SERVICES Texas A&M University...... p. 78 CRC Press...... p. 30 U.S. Census Bureau...... p. 75, 86

PROFESSIONAL OPPORTUNITIES University of Connecticut Health Center. . . . .p. 78 University of Michigan...... p. 91 Bureau of Justice Statistics...... p. 76, 87 University of Missouri-Kansas City...... p. 84 Capital One...... p. 82 University of Pittsburgh...... p. 76 Drexel University...... p. 74 University of South Carolina...... p. 81, 89 Duke University...... p. 89 University of Washington...... p. 77 Florida Hospital...... p. 79 Westat ...... p. 81 Fox School of Business, Temple University. . . . p. 77 Worcester Polytechnic Institute...... p. 82 Group Health Research Institute...... p. 76 Yale School of Public Health...... p. 90 Harvard University...... p. 83 Harvard School of Public Health...... p. 86 SOFTWARE Indiana University-Purdue University Indianapolis ...... p. 79 Cytel ...... p. 36 Institute of Statistical Science...... p. 90 JMP, a business unit of SAS...... p. 52 Johns Hopkins Blooomberg Minitab, Inc...... p. 34 School of Public Health...... p. 88 NCSS...... p. 22 Los Alamos National Laboratory...... p. 92 Salford Systems ...... p. 54 Moffitt Cancer Center...... p. 80 SAS ...... p. 51, cover 3 National Heart, Lung, and Blood Institute . . . .p. 83 SPSS ...... cover 4 NORC...... p. 90 StatPoint/statgraphics...... p. 60 North Carolina State University...... p. 85 Statistical Solutions ...... p. 69, 70 The Ohio State University...... p. 77 StatSoft ...... cover 2 Rutgers The State University of New Jersey. . . .p. 79 SYSTAT...... p. 65 Smith Hanley...... p. 84

96 Amstat News December 2009