DOCSLIB.ORG

Peter Gavin Hall, 1951–2016 It Is with Great Sadness That We Report the Passing Away of Peter Gavin Hall on January 9, Contents 2016, in Melbourne, Australia

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Peter Gavin Hall, 1951–2016 It Is with Great Sadness That We Report the Passing Away of Peter Gavin Hall on January 9, Contents 2016, in Melbourne, Australia Volume 45 • Issue 2 IMS Bulletin March 2016 Peter Gavin Hall, 1951–2016 It is with great sadness that we report the passing away of Peter Gavin Hall on January 9, CONTENTS 2016, in Melbourne, Australia. He was 64. 1 Peter Hall, 1951–2016 During the past four decades Peter was a monumental figure in the statistics commu- nity, both internationally and within his home country of Australia. 2 Members’ News: Manny Parzen, 1929–2016; Xihong Peter was born in Sydney in 1951 and earned degrees from the University of Sydney, Lin, Peter Diggle the Australian National University and Oxford University. He spent many years at the Australian National University, and moved to the University of Melbourne in 2006. He 3 Letter to the Editor also held a one-quarter appointment at the University of California, Davis, that com- 4 Introducing the New menced in 2005. Researchers Group Peter was one of the most influential and prolific theoretical statisticians in the history 5 Student Puzzle 13; Bulletin of the field. The breadth of problems he tackled, and the depth and creativity with which returns to print he solved them, are unique. He made seminal contributions concerning the bootstrap, 6 Obituary: Subramanian rates of convergence, functional data analysis, martingale theory, measurement error mod- “Kesan” Panchapakesan; Asit els, nonparametric function estimation and smoothing parameter selection and published Basu 4 books and approximately 600 journal articles. His contributions were recognized with fellowships from the Australian Academy of Science, the Academy of Social Sciences 7 Meeting report: Meta- Analysis Workshop in Australia, and the UK’s Royal Society, and election as a foreign associate of the US National Academy of Sciences, as well as honorary doctorates and awards that include 8 Recent papers: Electronic the Committee of Presidents of Statistical Societies Award in 1989 and the Guy Medal in Journal of Statistics; Statistics Surveys Silver from the Royal Statistical Society in 2011. Despite his stature, Peter had a gentle and unassuming nature. He offered especially SAMSI News 9 strong support to young scientists, trained more than sixty young statisticians at the doc- 10 IMS Elections 2016: toral or post-doctoral level, and had hundreds of collaborators. He will be remembered Candidate information for his kindness, generosity and sheer 15 Data Mining Cup brilliance. Few could rip apart a theoretical problem as well as Peter. 16 IMS meetings Peter was also strongly committed 19 Other meetings to his profession more generally, and the 25 Employment Opportunities amount of service and support he provided to mathematics and science throughout his International Calendar 28 life, both in Australia and internationally, 31 Information for Advertisers was also extraordinary. He served as IMS President in 2011, as an editor of Statistica Sinica during 2008–11 and co-editor of The Annals of Statistics during 2013–15. Outside of statistics Peter was a keen photographer, with a particular interest in train photography. He enjoyed travel and was a regular visitor to many institutions around the Read it online at world. He is survived by his wife, Jeannie and his sister, Fiona. http://bulletin.imstat.org IMSBulletin 2 . IMS Bulletin Volume 45 . Issue 2 Volume 45 • Issue 2 March 2016 IMS Members’ News ISSN 1544-1881 Emanuel (Manny) Parzen: 1929–2016 Contact information IMS Fellow Emanuel Parzen, a respected IMS Bulletin Editor: Anirban DasGupta figure in signal detection theory and time Assistant Editor: Tati Howell series analysis who, with Murray Rosenblatt, Contributing Editors: Robert Adler, Peter introduced the use of kernel density Bickel, Stéphane Boucheron, David Hand, Vlada Limic, Xiao-Li Meng, Dimitris estimation (the so-called “Parzen window”), Politis, Terry Speed and Hadley Wickham died February 6, 2016, in Boca Raton, Florida. He was 86. Contact the IMS Bulletin by email: Manny Parzen, who was born on April e [email protected] w http://bulletin.imstat.org 21, 1929, in New York, received the ASA’s https://www.facebook.com/IMSTATI 1994 Samuel S. Wilks Memorial Medal for his time series analysis research, in particular Contact the IMS regarding your dues, Emanuel (Manny) Parzen and his wife, Carol membership, subscriptions, orders or his “innovative introduction” of reproducing change of address: kernel Hilbert spaces, spectral analysis and IMS Dues and Subscriptions Office spectrum smoothing, as well as for “pioneering contributions” in quantile and density quantile 9650 Rockville Pike, Suite L3503A functions and estimation. Manny wrote six highly successful books, including the classic Bethesda, MD 20814-3998 USA Modern Probability Theory and its Applications. Manny was a Fellow of the IMS, ASA and t 877-557-4674 [toll-free in USA] the AAAS. He received the 2005 Gottfried E. Noether Award, “for a lifetime of outstanding t +1 216 295 5661[international] achievements and contributions in the field of nonparametric statistics.” f +1 301 634 7099 In a tribute on the Texas A&M University’s website (http://www.science.tamu.edu/news/ e [email protected] story.php?story_ID=1541#.VrtLZMCyOko), Dr. Valen E. Johnson, professor and head of Texas A&M Statistics department, said, “Manny Parzen was a pioneer in statistics during its nascent Contact the IMS regarding any other matter, including advertising, copyright stages of development in the 1960s. He played a central role in the development of the theory permission, offprint orders, copyright of stochastic processes and was a pioneer in the fields of time series and spectral analyses transfer, societal matters, meetings, fellows in addition to making important contributions in the area of nonparametric statistics. His nominations and content of publications: textbook Modern Probability Theory and its Applications is a classic text that continues to be Executive Director, Elyse Gustafson widely used as reference in the field today. On a personal level, Manny was extremely engaging IMS Business Office and always anxious to discuss new approaches toward statistical inference. The Department of PO Box 22718, Beachwood OH 44122, USA Statistics — and the statistical community in general — has lost one of its giants.” t 877-557-4674 [toll-free in USA] A full obituary will appear in a future issue. t +1 216 295 5661[international] f +1 216 295 5661 e [email protected] Xihong Lin, Peter Diggle speakers at ENAR The 2016 ENAR Spring Meeting will be held in Austin, Texas, from Executive Committee March 6–9. The meeting brings together researchers and practitioners President: Richard Davis from academia, industry and government, connected through a [email protected] common interest in Biometry. President-Elect: Jon Wellner [email protected] Featuring the 2016 ENAR Presidential Invited Speaker, Xihong Xihong Lin Past President: Erwin Bolthausen Lin (Harvard University), whose lecture will be on Biostatistics, Peter Diggle [email protected] Biomedical Informatics, and Health Data Science: Research and Treasurer: Jean Opsomer Training. There will also be an IMS Medallion Lecture,Model-Based [email protected] Geostatistics for Prevalence Mapping in Low-Resource Settings by Peter Program Secretary: Judith Rousseau [email protected] Diggle (Lancaster University, UK). Executive Secretary: Aurore Delaigle See http://www.enar.org/meetings/spring2016/index.cfm [email protected] = access published papers online March . 2016 IMS Bulletin . 3 IMS Journals and Publications Annals of Statistics: Peter Hall and Runze Li http://imstat.org/aos http://projecteuclid.org/aos Annals of Applied Statistics: Stephen Fienberg Letter to the Editor http://imstat.org/aoas http://projecteuclid.org/aoas Annals of Probability: Maria Eulalia Vares http://imstat.org/aop A Commentary on “The Kids Are Alright: Divide by n when estimating variance,” by Jeffrey S. http://projecteuclid.org/aop Rosenthal, IMS Bulletin (December 2015), Vol. 44, No. 8, Page 9 Annals of Applied Probability: Timo Seppäläinen http://imstat.org/aap http://projecteuclid.org/aoap Dear Editor Statistical Science: Peter Green http://imstat.org/sts − http://projecteuclid.org/ss Professor Rosenthal’s piece is persuasive I begin with ∑ n ( − )2. But I note that i=1 Xi X IMS Collections n − and very clearly written. I thank Professor ∑i=1 (Xi − X) is identically zero for any set http://imstat.org/publications/imscollections.htm Rosenthal for taking us back to this old of n numbers. That is, amongn numbers http://projecteuclid.org/imsc − − − IMS Monographs and IMS Textbooks: David Cox concern that never truly goes away. Indeed (residuals) X1−X, X2−X, … , Xn−X, we have http://imstat.org/cup/ the basic issue under consideration appears exactly n − 1 free-riding numbers, since all n IMS Co-sponsored Journals and and reappears when one teaches a cohort of residuals add up to zero. That is, the remain- Publications th new students. ing n number is fully determined by the Electronic Journal of Statistics: George Michailidis With nearly 40 years of teaching expe- other n − 1 free-riding numbers. Thus, while http://imstat.org/ejs http://projecteuclid.org/ejs rience now, I have a different, but easy, way one obtains the sample variance, one divides n − 2 Electronic Journal of Probability: Brian Rider to explain why the divisor in the customary ∑i=1 (Xi − X) by (n − 1) instead of n. In this http://ejp.ejpecp.org sample variance is suddenly n − 1 instead sense, n − 1 is customarily called the “degree Electronic Communications
Load more

Recommended publications
  • Royal Statistical Scandal
    Royal Statistical Scandal False and misleading claims by the Royal Statistical Society Including on human poverty and UN global goals Documentary evidence Matt Berkley Draft 27 June 2019 1 "The Code also requires us to be competent. ... We must also know our limits and not go beyond what we know.... John Pullinger RSS President" https://www.statslife.org.uk/news/3338-rss-publishes-revised-code-of- conduct "If the Royal Statistical Society cannot provide reasonable evidence on inflation faced by poor people, changing needs, assets or debts from 2008 to 2018, I propose that it retract the honour and that the President makes a statement while he holds office." Matt Berkley 27 Dec 2018 2 "a recent World Bank study showed that nearly half of low-and middle- income countries had insufficient data to monitor poverty rates (2002- 2011)." Royal Statistical Society news item 2015 1 "Max Roser from Oxford points out that newspapers could have legitimately run the headline ' Number of people in extreme poverty fell by 137,000 since yesterday' every single day for the past 25 years... Careless statistical reporting could cost lives." President of the Royal Statistical Society Lecture to the Independent Press Standards Organisation April 2018 2 1 https://www.statslife.org.uk/news/2495-global-partnership-for- sustainable-development-data-launches-at-un-summit 2 https://www.statslife.org.uk/features/3790-risk-statistics-and-the-media 3 "Mistaken or malicious misinformation can change your world... When the government is wrong about you it will hurt you too but you may never know how.
    [Show full text]
  • BERNOULLI NEWS, Vol 24 No 2 (2017)
    Vol. 24 (2), November 2017 Published twice per year by the Bernoulli Society ISSN 1360–6727 CONTENTS News from the Bernoulli A VIEW FROM THE PRESIDENT Society p. 1 Awards and Prizes p. 2 New Executive Members in the Bernoulli Society p. 3 Articles and Letters On Bayesian Measures for Some Statistical Inverse Problems with Partial Differential Equations p. 5 Obituary Alastair Scott p. 10 Past Conferences, Susan A. Murphy receives the Bernoulli Book from Sara van de Geer during the General Assembly of the Bernoulli Society ISI World Congress in Marrakech, Morocco. Meetings and Workshops p. 11 Dear Members of the Bernoulli Society, Next Conferences, Meetings and Workshops It is an honor to assume the role of Bernoulli Society president, particularly be- cause this is a very exciting time to be a statistician or probabilist! As all of us have and Calendar of Events become, ever-more acutely aware, the role of data in society and in science is dramat- p. 13 ically changing. Many new challenges are due to the complex, and vast amounts of, data resulting from the development of new data collection tools such as wearable Book Reviews sensors in clothing, on eyeglasses, in toothbrushes and most commonly on our phones. Indeed there are now wearable radar sensors that provide data that might be used Editor to improve the safety of bicyclists or help visually impaired individuals gain greater MIGUEL DE CARVALHO independence. There are also wearable respiratory sensors that provide data that School of Mathematics could be used to help us investigate the impact of dietary and exercise regimens, or THE UNIVERSITY of EDINBURGH EDINBURGH, UK identify nutritional imbalances.
    [Show full text]
  • 2015 Conference Directory
    RSS International Conference 2015 The conference for all statisticians and users of data sponsored by 7 – 10 September 2015 Exeter University www.rss.org.uk/conference2015 Welcome Outline Timetable Wednesday 9 September 9am – 10am Invited/Contributed sessions (5) It is my great honour to welcome you all to Exeter for the 10.05am – 11.25pm 2015 RSS Conference! After listening to your feedback, you Monday 7 September Invited sessions (6) will see that this year we have adopted a new streaming 9.30am – 5.30pm format to Conference which should allow you to easily 11.25am – 11.50am Pre-conference short courses and workshops identify sessions that are directly relevant to your area of Refreshment break (The Forum) expertise and interests. That being said, I do hope that you 11.50am – 1.10pm will take advantage of this unique opportunity to pop into 7pm – 9pm Invited sessions (7) sessions that you may not have access to elsewhere. Welcome Reception (Royal Albert Memorial Museum) 1.10pm – 2.10pm Lunch We have a great line-up of speakers and sessions organised for you, but I also hope that you will find some time for 2.10pm – 3.10pm exploration. The Conference will be hosted in three Tuesday 8 September Plenary 3 – Significance lecture outstanding venues - The Forum (which all you Broadchurch fans may recognise as the 3.15pm – 4.15pm 9am – 9.30am Courtroom in the second series), the award winning Royal Albert Memorial Museum Invited/Contributed sessions (8) and the University’s Great Hall. The Young Statisticians’ Guide to the Conference 4.15pm – 4.40pm Exeter is an ancient city with many notable landmarks, including the Cathedral which 9.30am – 10.30am Refreshment break boasts an astronomical clock and the longest uninterrupted vaulted ceiling in England.
    [Show full text]
  • BERNOULLI NEWS, Vol 24 No 1 (2017)
    Vol. 24 (1), May 2017 Published twice per year by the Bernoulli Society ISSN 1360–6727 CONTENTS News from the Bernoulli Society p. 1 Awards and Prizes p. 2 New Executive Members A VIEW FROM THE PRESIDENT in the Bernoulli Society Dear Members of the Bernoulli Society, p. 3 As we all seem to agree, the role and image of statistics has changed dramatically. Still, it takes ones breath when realizing the huge challenges ahead. Articles and Letters Statistics has not always been considered as being very necessary. In 1848 the Dutch On Bayesian Measures of Ministry of Home Affairs established an ofŮice of statistics. And then, thirty years later Uncertainty in Large or InŮinite minister Kappeyne van de Coppelo abolishes the “superŮluous” ofŮice. The ofŮice was Dimensional Models p. 4 quite rightly put back in place in 1899, as “Centraal Bureau voor de Statistiek” (CBS). Statistics at the CBS has evolved from “simple” counting to an art requiring a broad range On the Probability of Co-primality of competences. Of course counting remains important. For example the CBS reports in of two Natural Numbers Chosen February 2017 that almost 1 out of 4 people entitled to vote in the Netherlands is over the at Random p. 7 age of 65. But clearly, knowing this generates questions. What is the inŮluence of this on the outcome of the elections? This calls for more data. Demographic data are combined with survey data and nowadays also with data from other sources, in part to release the “survey pressure” that Ůirms and individuals are facing.
    [Show full text]
  • Coauthorship and Citation Networks for Statisticians
    Submitted to the Annals of Applied Statistics arXiv: arXiv:0000.0000 COAUTHORSHIP AND CITATION NETWORKS FOR STATISTICIANS By Pengsheng Jiy and Jiashun Jinz University of Georgiay and Carnegie Mellon Universityz We have collected and cleaned two network data sets: Coauthor- ship and Citation networks for statisticians. The data sets are based on all research papers published in four of the top journals in statis- tics from 2003 to the first half of 2012. We analyze the data sets from many different perspectives, focusing on (a) centrality, (b) commu- nity structures, and (c) productivity, patterns and trends. For (a), we have identified the most prolific/collaborative/highly cited authors. We have also identified a handful of \hot" papers, suggesting \Variable Selection" as one of the \hot" areas. For (b), we have identified about 15 meaningful communities or research groups, including large-size ones such as \Spatial Statis- tics", \Large-Scale Multiple Testing", \Variable Selection" as well as small-size ones such as \Dimensional Reduction", \Objective Bayes", \Quantile Regression", and \Theoretical Machine Learning". For (c), we find that over the 10-year period, both the average number of papers per author and the fraction of self citations have been decreasing, but the proportion of distant citations has been increasing. These suggest that the statistics community has become increasingly more collaborative, competitive, and globalized. Our findings shed light on research habits, trends, and topological patterns of statisticians. The data sets provide a fertile ground for future researches on or related to social networks of statisticians. 1. Introduction. It is frequently of interest to identify \hot" areas and key authors in a scientific community, and to understand the research habits, trends, and topological patterns of the researchers.
    [Show full text]
  • Supplementary Material HR19008 AC
    Historical Records of Australian Science © Australian Academy of Science 2020 https://doi.org/10.1071/HR19008_AC Supplementary Material: Historical Records of Australian Science, 2020, 31(1), 17–25 Supplementary material. A bibliography of Australian mathematics to 1960 with observations relating to the history of Australian mathematics Graeme L. Cohen Formerly, School of Mathematical Sciences, University of Technology Sydney, NSW 2007, Australia. Email: [email protected] File S1. Lists List 1—Chronological List of Publications to 1900 2 List 2—Alphabetical by Author List of Publications from 1901 16 to 1960 (Excluding Theses and Most School Books) List 3—Alphabetical by Author List of Theses Leading to the 37 Award of a Higher Degree, to 1960 Index 45 References (further to those in the main text) 56 1 Historical Records of Australian Science © Australian Academy of Science 2020 https://doi.org/10.1071/HR19008_AC Supplementary Material: Historical Records of Australian Science, 2020, 31(1), 17–25 LISTS The main item, article HR19008, should be read first for a full understanding of what is included here. The superscript CAI before an author’s name indicates that biographical information on that author is to be found in Counting Australia In.1 List 1— Chronological List of Publications to 1900 1. RUSSELL, JOHN WM. (18-?) Exercises and examples in expert arithmetic, Kealy & Philip, Sydney. 2. BOWDEN, THOMAS (1812) Bowden’s tables, Ferguson I, 532. [‘Their object is to ascertain at a momentary glance, the difference between sterling and currency … They are calculated with a degree of precision that must have occupied considerable time and attention …’, according to Ferguson.
    [Show full text]
  • IMS Bulletin 39(4)
    Volume 39 • Issue 4 IMS1935–2010 Bulletin May 2010 Meet the 2010 candidates Contents 1 IMS Elections 2–3 Members’ News: new ISI members; Adrian Raftery; It’s time for the 2010 IMS elections, and Richard Smith; we introduce this year’s nominees who are IMS Collections vol 5 standing for IMS President-Elect and for IMS Council. You can read all the candi- 4 IMS Election candidates dates’ statements, starting on page 4. 9 Amendments to This year there are also amendments Constitution and Bylaws to the Constitution and Bylaws to vote Letter to the Editor 11 on: they are listed The candidate for IMS President-Elect is Medallion Preview: Laurens on page 9. 13 Ruth Williams de Haan Voting is open until June 26, so 14 COPSS Fisher lecture: Bruce https://secure.imstat.org/secure/vote2010/vote2010.asp Lindsay please visit to cast your vote! 15 Rick’s Ramblings: March Madness 16 Terence’s Stuff: And ANOVA thing 17 IMS meetings 27 Other meetings 30 Employment Opportunities 31 International Calendar of Statistical Events The ten Council candidates, clockwise from top left, are: 35 Information for Advertisers Krzysztof Burdzy, Francisco Cribari-Neto, Arnoldo Frigessi, Peter Kim, Steve Lalley, Neal Madras, Gennady Samorodnitsky, Ingrid Van Keilegom, Yazhen Wang and Wing H Wong Abstract submission deadline extended to April 30 IMS Bulletin 2 . IMs Bulletin Volume 39 . Issue 4 Volume 39 • Issue 4 May 2010 IMS members’ news ISSN 1544-1881 International Statistical Institute elects new members Contact information Among the 54 new elected ISI members are several IMS members. We congratulate IMS IMS Bulletin Editor: Xuming He Fellow Jon Wellner, and IMS members: Subhabrata Chakraborti, USA; Liliana Forzani, Assistant Editor: Tati Howell Argentina; Ronald D.
    [Show full text]
  • Statistical Modelling of Citation Exchange Between Statistics Journals
    J. R. Statist. Soc. A (2016) 179, Part 1, pp. 1–63 Statistical modelling of citation exchange between statistics journals Cristiano Varin, Universit`a Ca’ Foscari, Venezia, Italy Manuela Cattelan Universit`a degli Studi di Padova, Italy and David Firth University of Warwick, Coventry, UK [Read before The Royal Statistical Society at a meeting organized by the General Applica- tions Section on Wednesday, May 13th, 2015, Professor P. Clarke in the Chair ] Summary. Rankings of scholarly journals based on citation data are often met with scepticism by the scientific community. Part of the scepticism is due to disparity between the common per- ception of journals’ prestige and their ranking based on citation counts. A more serious concern is the inappropriate use of journal rankings to evaluate the scientific influence of researchers. The paper focuses on analysis of the table of cross-citations among a selection of statistics jour- nals. Data are collected from the Web of Science database published by Thomson Reuters. Our results suggest that modelling the exchange of citations between journals is useful to highlight the most prestigious journals, but also that journal citation data are characterized by consid- erable heterogeneity, which needs to be properly summarized. Inferential conclusions require care to avoid potential overinterpretation of insignificant differences between journal ratings. Comparison with published ratings of institutions from the UK’s research assessment exercise shows strong correlation at aggregate level between assessed research quality and journal citation ‘export scores’ within the discipline of statistics. Keywords: Bradley–Terry model; Citation data; Export score; Impact factor; Journal ranking; Research evaluation; Stigler model 1.
    [Show full text]
  • Spatio-Temporal Point Processes: Methods and Applications Peter J
    Johns Hopkins University, Dept. of Biostatistics Working Papers 6-27-2005 Spatio-temporal Point Processes: Methods and Applications Peter J. Diggle Medical Statistics Unit, Lancaster University, UK & Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, [email protected] Suggested Citation Diggle, Peter J., "Spatio-temporal Point Processes: Methods and Applications" (June 2005). Johns Hopkins University, Dept. of Biostatistics Working Papers. Working Paper 78. http://biostats.bepress.com/jhubiostat/paper78 This working paper is hosted by The Berkeley Electronic Press (bepress) and may not be commercially reproduced without the permission of the copyright holder. Copyright © 2011 by the authors Spatio-temporal Point Processes: Methods and Applications Peter J Diggle (Department of Mathematics and Statistics, Lancaster University and Department of Biostatistics, Johns Hopkins University School of Public Health) June 27, 2005 1 Introduction This chapter is concerned with the analysis of data whose basic format is (xi; ti) : i = 1; :::; n where each xi denotes the location and ti the corresponding time of occurrence of an event of interest. We shall assume that the data form a complete record of all events which occur within a pre-specified spatial region A and a pre-specified time- interval, (0; T ). We call a data-set of this kind a spatio-temporal point pattern, and the underlying stochastic model for the data a spatio-temporal point process. 1.1 Motivating examples 1.1.1 Amacrine cells in the retina of a rabbit One general approach to analysing spatio-temporal point process data is to extend existing methods for purely spatial data by considering the time of occurrence as a distinguishing feature, or mark, attached to each event.
    [Show full text]
  • IMS Bulletin 35(4)
    Volume 35 Issue 4 IMS Bulletin May 2006 Executive Director reports ach year as I sit down to write this report, I reflect CONTENTS a bit on the past year. One recurring theme always 1 Executive Director’s report comes to me: the commitment of the IMS leader- Eship. All the IMS leaders are volunteers. They give of their 2 IMS Members’ News: Peter Green, Guy Nason, time and energy to grow your organization and your profes- Geoffrey Grimmett, Steve sion. Countless hours are spent by the Executive Committee, Brooks, Simon Tavaré Editors and Committee Chairs. I have encountered numer- ous people who truly give of themselves to create a strong 3 CIS seeks Contributing and vibrant organization. Editors Elyse Gustafson, the IMS The IMS keeps its administrative expenses incredibly low Executive Director IMS news 5 (only 7% of all income goes to administrative expenses). This 6 Rio guide: tours and trips happens because of the hard work of volunteers. Next time you see one of the IMS leaders, whether the President or a 8 IMS FAQs committee member, thank them for their time. 11 Report: Stochastik-Tage Our best ideas for new programming or improvements come directly from the meeting membership. The number of changes the IMS has made because a member brought 12 Le Cam Lecture preview: the idea to us is immeasurable. As an organization, the IMS leadership is very open to Stephen Stigler growth and change. Bring us your ideas: they will be heard! 13 Medallion Lecture pre- Please feel free to contact me with your thoughts.
    [Show full text]
  • Letter from the RSS Covid-19 Task Force To
    Letter from the Royal Statistical Society Covid-19 Task Force to the Guardian regarding data transparency 7 August 2020 The Covid-19 public health crisis has placed a sharp emphasis on the role of data in government decision-making. During the current phase – where the emphasis is on Test and Trace and local lockdowns – data is playing an increasingly central role in informing policy. We recognise that the stakes are high and that decisions need to be made quickly. However, this makes it even more important that data is used in a responsible and effective manner. Transparency around the data that are being used to inform decisions is central to this. Over the past week, there have been two major data-led government announcements where the supporting data were not made available at the time. First, the announcement that home and garden visits would be made illegal in parts of northern England. The Prime Minister cited unpublished data which suggested that these visits were the main setting for transmission. Second, the purchase of two new tests for the virus that claim to deliver results within 90 minutes, without data regarding the tests’ effectiveness being published. We are concerned about the lack of transparency in these two cases – these are important decisions and the data upon which they are based should be publicly available for scrutiny, as Paul Nurse pointed out in this paper at the weekend. Government rhetoric often treats data as a managerial tool for informing decisions. But beyond this, transparency and well sign-posted data builds public trust and encourages compliance: the daily provision of statistical information was an integral part of full lockdown and was both expected and valued by the public.
    [Show full text]
  • Bibliometrics in the Context of the UK Research Assessment Exercise Bernard W
    Statistical Science 2009, Vol. 24, No. 1, 15–16 DOI: 10.1214/09-STS285A Main article DOI: 10.1214/09-STS285 © Institute of Mathematical Statistics, 2009 Comment: Bibliometrics in the Context of the UK Research Assessment Exercise Bernard W. Silverman Abstract. Research funding and reputation in the UK have, for over two decades, been increasingly dependent on a regular peer-review of all UK de- partments. This is to move to a system more based on bibliometrics. Assess- ment exercises of this kind influence the behavior of institutions, departments and individuals, and therefore bibliometrics will have effects beyond simple measurement. Key words and phrases: Bibliometrics, research funding, perverse incen- tives. In the United Kingdom’s Research Assessment Ex- matical aspects of Operational Research. The com- ercise (RAE), every university may submit its research mittee’s experience of conducting the assessment as in every discipline for assessment. On this assessment a whole strengthened our view that peer review must rests a considerable amount of funding; indeed a num- be at the core of any future assessment of research in ber of universities, leading “research universities” in our area. Reliance on bibliometric and purely quanti- American nomenclature, gain more from this source tative methods of assessment would, in our unanimous of research funding than from government funding for view, introduce serious biases, both into the assessment teaching. Within broad subject bands, the Higher Ed- process and, perhaps more seriously, into the behav- ucation Funding Council for England funds teaching ior of institutions and of individual researchers, to the on a flat rate per student.
    [Show full text]