SAN DIEGO STATE UNIVERSITY Graduate School of Public Health Division of Epidemiology and Biostatistics

PH 628 Applications of Multivariate Statistics in Public Health (3 units) Fall 2018

Section Day Time Location Schedule No. 1 Monday, Wednesday 2:00 pm – 3:15 pm HH-210 22757

Instructor: John Alcaraz, Ph.D. Phone: 619-594-1342 E-mail: [email protected] Office location: Hardy Tower 231 Office hours: Monday 10:30 am – 1:30 pm, Wednesday 10:30 am – 1:30pm

Course Description: Statistical methods for multivariate problems in public health including regression diagnostics, cluster analysis, discriminant analysis, principal components, multivariate discrete analysis and Poisson regression. Computer applications included.

Prerequisites: • PH 627 or equivalent course work in multiple regression, analysis of variance and logistic regression. • Completion of the SAS computer labs offered concurrently with PH 602 and PH 627, or equivalent knowledge of SAS.

Required texts: • Kleinbaum, Kupper, Nizam, Rosenberg: Applied Regression Analysis and Other Multivariable Methods, Fifth Edition. • Afifi, May, Clark: Practical Multivariate Analysis, Fifth Edition. • Slymen: “PH 628: Applications of Multivariate Statistics in Public Health” (Customized Materials). [Readings] • Slymen: “PH 628: Annotated SAS Output for Public Health 628” (Customized Materials). Note: The annotated output should be brought to every class meeting.

Blackboard: During the semester, course-related materials such as announcements, lecture notes, assignments and solutions will be posted on Blackboard. Please check regularly for new materials. Student support for Blackboard is provided by the Library Computing Hub, located on the second floor of Love Library. They can be reached at 619-594-3189 or [email protected]

Coursework and Grading System: Your course grade will be based on a set of six homework assignments (worth 25% of your grade), a project (35%), and a take-home comprehensive exam (40%). The project requires you to write a paper describing an in-depth analysis you perform using one or more multivariable methods. All coursework will require using SAS on the PC. All submitted coursework must be printed, computer-written documents. Handwritten coursework is not acceptable. Do not submit any SAS output. Scores and their equivalent letter grades are as follows:

Score Letter Grade 93 – 100 A 90 – 93 A– 87 – 90 B+ 83 – 87 B 80 – 83 B– 77 – 80 C+ 73 – 77 C 70 – 73 C– 67 – 70 D+ 63 – 67 D 60 – 63 D– 0 – 60 F

Dates for Coursework (subject to change): Assignment Date Assigned Date Due Exercise 1 September 12 September 26 Exercise 2 September 26 October 10 Exercise 3 October 3 October 17 Exercise 4 October 17 October 31 Exercise 5 October 31 November 14 Exercise 6 November 5 November 19 Project September 17 November 26 Exam (open-book, open-notes) November 19 December 10

Learning Objective Competency Assessment Method Identify and distinguish between Apply epidemiological methods to the Exercises 1-6, various multivariate methods for the breadth of settings and situations in project, exam analysis of health-related data with public health practice. multiple dependent and independent measures, where multivariate assessment and/or variable reduction are the primary goals. Check for violations of the Identify and address errors, outliers, Exercises 1-3, assumptions of multiple linear and other issues in public health data exam regression, identify influential data that may adversely impact statistical points, and check for collinearity. analysis.

Assess goodness-of fit of logistic regression models, identify influential data points, and check for collinearity. Test the association between a set of Identify and distinguish between Exercises, 1, 4, & independent variables and a various statistical methods for the 5, exam categorical dependent variable that analysis of categorical outcome has more than two categories, variables. whether ordered or unordered. Analyze studies in which subjects Apply appropriate statistical methods Exercise 6, exam are followed over time and repeated to the analysis of longitudinal data. measurements of the outcome variables are taken on each subject. Become familiar with and apply a Analyze quantitative and qualitative Exercises 1-6, number of computer procedures in data using biostatistics, informatics, project, exam SAS for the analysis of multivariate computer-based programming and data. software, as appropriate. Interpret the results of multivariate Interpret results of data analysis for Exercises 1-6, data analysis performed in SAS, public health research, policy or project, exam either to answer health-related practice. hypotheses or to guide further analyses. Formulate and pursue an applied Select quantitative and qualitative Project public health research question data collection methods appropriate using multivariate data analysis, and for a given public health context. write a short paper interpreting the results. Work independently or with minimal supervision to write a report analyzing a public health data set with multivariate methods. Describe the statistical theory (such Describe the theory that underlies the Project as underlying assumptions and statistical procedures used to analyze relevant model equations) behind public health data. various multivariate methods for the analysis of health-related data.

Statistical Procedures: A full list of statistical procedures that students will learn in this course follows:

1. Linear regression diagnostics. Students will be able to check for violations of the assumptions of multiple linear regression, to identify influential data points, and to check for collinearity.

2. Logistic regression diagnostics. Students will be able to assess goodness-of-fit of logistic regression models, to identify influential data points, and to check for collinearity.

3. Principal components analysis. Students will be able to construct a set of components which summarize the interrelationships among a set of variables. Students will be able to assess whether these components may be used in place of the original variables in other analyses.

4. Factor analysis. By constructing a set of factors, students will be able to verify whether hypothesized or expected interrelationships appear among a set of variables.

5. Cluster analysis. Students will be able to group together subjects (e.g., patients) according to similar values on measured variables, where such groupings are not specified in advance. This is primarily an exploratory technique.

6. Discriminant analysis. Students will be able to construct a rule based on a set of variables which optimizes the classification of subjects among two or more specified groups (e.g., with disease, without disease). Students will be able to assess the utility of the rule for classification.

7. Polychotomous logistic regression. Students will be able to test the association between a set of independent variables and a categorical dependent variable that has more than two categories.

8. Ordinal regression. Students will be able to test the association between a set of independent variables and a categorical dependent variable that has more than two ordered categories.

9. Longitudinal data analysis. Students will be able to analyze studies in which subjects are followed over time and repeated measurements of the outcome variables are taken on each subject.

10. Poisson regression. Students will be able to test the relationship between a set of independent variables and a dependent variable which counts the number of times a particular event occurs.

Attendance: Although attending every class meeting is not required, it is strongly encouraged if you wish to get the most value out of this course. Material may be presented during lecture that is not covered in the lecture notes. If you miss a lecture, it is your responsibility to get the notes from a classmate.

If because of severe circumstances (such as illness, injury, death in the family) you are absent on a day when an assignment is due, you must submit it to me via email no later than one week after the due date, along with documentation explaining your absence. Students for whom a due date falls on a date of planned absence must submit their assignment to me via email by noon on the due date or earlier. Email submissions must be in Word or PDF format.

According to the University Policy File, students should notify the instructors of affected courses of planned absences for religious observances by the end of the second week of classes.

Interacting with me: I will try to respond within 48 hours to e-mails sent to me at [email protected] (do not use Blackboard to send messages). In general, I do not check e-mail after 5pm or over the weekend. For questions that require in-depth clarification, please visit my office hours.

Classroom Conduct: Students will be expected to be active participants in the learning process. When students contribute thoughtful comments and questions to class discussions or presentations, the learning experience is enriched for all. Students should also listen attentively to the speakers and to each other. This course will cover a variety of topics, some of which may elicit strong feelings or opinions. Students are expected to articulate their comments and questions in a respectful manner and understand that others may have different perspectives.

Classroon Disruptions: Please turn off and put away all phones. Tablets and laptops are allowed only for PH 628-related business (no web browsing, e-mailing, or working on other classes).

Classroom Recordings: Students must obtain permission before recording a class lecture or discussion. Students who record without prior permission may be reported for misconduct.

Academic Honesty: Students are expected to maintain the highest standards of academic honesty and respect. According to SDSU's Center for Student Rights and Responsibilities, students may be expelled, suspended, or put on probation for academic dishonesty. In addition to a University review of the incident(s), the Graduate School of Public Health may also take disciplinary action which, depending on the severity of the incident, could result in one or all of the following sanctions: a grade of "F" on the assignment in question, dropping of one letter grade from your final grade in the class, or, for multiple or severe incidents, a grade of "F" in the class. You may receive an Incomplete in a class, which will be removed once the investigation of the incident has been completed.

Cheating shall be defined as the act of obtaining or attempting to obtain credit for academic work by the use of dishonest, deceptive, or fraudulent means. Examples of cheating include, but are not limited to (a) copying, in part or in whole, from another’s test or other examination; (b) discussing answers or ideas relating to the answers on a test or other examination without the permission of the instructor; (c) obtaining copies of a test, an examination, or other course material without the permission of the instructor; (d) using notes, cheat sheets, or other devices considered inappropriate under the prescribed testing condition; (e) collaborating with another or others in work to be presented without the permission of the instructor; (f) falsifying records, laboratory work, or other course data; (g) submitting work previously presented in another course, if contrary to the rules of the course; (h) altering or interfering with the grading procedures; (i) plagiarizing, as defined; and (j) knowingly and intentionally assisting another student in any of the above.

Plagiarism shall be defined as the act of incorporating ideas, words, or specific substance of another, whether purchased, borrowed, or otherwise obtained, and submitting same to the University as one’s own work to fulfill academic requirements without giving credit to the appropriate source. Plagiarism shall include but not be limited to (a) submitting work, either in part or in whole, completed by another; (b) omitting footnotes for ideas, statements, facts, or conclusions that belong to another; (c) omitting quotation marks when quoting directly from another, whether it be a paragraph, sentence, or part thereof; (d) close and lengthy paraphrasing of the writings of another; (e) submitting another person’s artistic works, such as musical compositions, photographs, paintings, drawings, or sculptures; and (f) submitting as one’s own work papers purchased from research companies.

Examples of Plagiarism include but are not limited to: • Using sources verbatim or paraphrasing without giving proper attribution (this can include phrases, sentences, paragraphs and/or pages of work) • Copying and pasting work from an online or offline source directly and calling it your own • Using information you find from an online or offline source without giving the author credit • Replacing words or phrases from another source and inserting your own words or phrases • Submitting a piece of work you did for one class to another class If you have questions on what is plagiarism, please consult the policy.

Turnitin: Students agree that by taking this course all required papers may be subject to submission for textual similarity review to Turnitin.com for the detection of plagiarism. All submitted papers will be included as source documents in the Turnitin.com reference database solely for the purpose of detecting plagiarism of such papers. You may submit your papers in such a way that no identifying information about you is included. Another option is that you may request, in writing, that your papers not be submitted to www.turnitin.com. However, if you choose this option you will be required to provide documentation to substantiate that the papers are your original work and do not include any plagiarized material.

Copyright Policy: SDSU respects the intellectual property of others and we ask our faculty and students to do the same. It is best to assume that any material (e.g., graphic, html coding, text, video, or sound) on the Web is copyrighted unless specific permission is given to copy it under a Creative Commons License. More information about the use of copy written material in education (Fair Use, TEACH ACT) is available here. Whenever possible, you should attribute the original author of any work used under these provisions.

Student Services: A complete list of all academic support services is available on the Academic Success section of the SDSU Student Affairs website. For help with improving your writing ability, the staff at the SDSU Writing Center is available in person and online. Counseling and Psychological Services offers confidential counseling services by licensed psychologists, counselors, and social workers. More info can be found at their website or by contacting (619) 594-5220. You can also Live Chat with a counselor between 4:00pm and 10:00pm, or call San Diego Access and Crisis 24-hour Hotline at (888) 724-7240.

Students with Disabilities: If you are a student with a disability and believe you will need accommodations for this class, it is your responsibility to contact Student Disability Services at (619) 594-6473. You can also learn more about the services provided by visiting the Student Disability Services website. To avoid any delay in the receipt of your accommodations, you should contact Student Disability Services as soon as possible. Please note that accommodations are not retroactive, and that accommodations based upon disability cannot be provided until you have presented your instructor with an accommodation letter from Student Disability Services. Your cooperation is appreciated.

Deferred Action for childhood Arrivals (DACA): All students with questions or concerns regarding DACA are encouraged to see the College of Health and Human Services Assistant Dean for Student Affairs, Jessica Robinson ([email protected]).

Nondiscrimination Policy: • SDSU complies with the requirements of Title VI and Title VII of the Civil Rights Act of 1964, as well as other applicable federal and state laws prohibiting discrimination. No person shall, on the basis of race, color, or national origin be excluded from participation in, be denied the benefits of, or be otherwise subjected to discrimination in any program of the California State University • SDSU does not discriminate on the basis of disability in admission or access to, or treatment or employment in, its programs and activities. Students should direct inquiries concerning San Diego State University’s compliance with all relevant disability laws to the Director of Student Disability Services (SDS), Calpulli Center, Room 3101, SDSU, San Diego, CA 92128 or call 619-594-6473 (TDD: 619-594-2929). • SDSU does not discriminate on the basis of sex, gender, or sexual orientation in the educational programs or activities it conducts. More detail on SDSU’s Nondiscrimination Policy can be found in the SDSU General Catalog, University Policies. Students should direct FERPA, Title IX, Discrimination, Harassment or any other protected categories inquiries and concerns to the office of Employee Relations and Compliance; their phone number is 619-594-6464.

Concerns regarding classroom activity, grades, or other student affair matters: Though students have the option of contacting the San Diego State University Ombudsman or the Assistant Dean for Student Affairs at any time regarding classroom activity, grades, or other student affairs matters students are encouraged to meet with their professor first to discuss the situation. If the issue is not resolved at this level, the student should contact their Graduate Advisor. If the problem is not resolved at this level, contact should be made to their Department Director and finally their Assistant Dean for Student Affairs.

DISCLAIMER: Every effort will be made to follow the syllabus content and schedule; however, if circumstances dictate there may be modifications necessary during the semester. If such is the case the professor will make every effort to notify students in a timely manner.

Course Outline for PH 628

Related Book Topic Chapters (see lecture notes for specifics) 1. Review of multiple linear & logistic regressions 2. Regression diagnostics and goodness-of-fit in multiple linear and Kleinbaum 14, logistic regression Readings a. Residual analysis b. Detecting outliers c. Detecting collinearity d. Goodness-of-fit statistics 3. Principal components analysis (PCA) Afifi 14, Readings a. Basic properties & geometric interpretation b. Using PCA to detect outliers and collinearity 4. Factor analysis (briefly) Afifi 15 5. Cluster analysis Afifi 16 6. Discriminant analysis (DA) Afifi 11, Readings a. Basic properties b. Two-group DA c. DA for more than 2 groups d. Estimation of error rates & posterior probabilities e. Relationship to multivariate ANOVA 7. Polychotomous logistic regression Readings a. Basic properties b. Estimation and hypothesis testing c. Modeling and examples 8. Ordinal regression Readings a. Basic properties b. Modeling and examples 9. Analysis of longitudinal data Readings a. Introduction and examples b. Mixed effects models c. Modeling the covariance structure d. Special issues: missing data, attrition 10. Poisson regression (briefly) Readings