Event History Analysis for the Social Sciences, CS&SS 544

Winter 2024

Instructor: Darryl J. Holman

Email: djholman@u.washington.edu
Voice: 206-543-7586
Office: Denny M237

Scope

Scope: Event history analysis is an important analytical tool in many fields within the social sciences. This course covers the standard tools used for event history analysis-things like parametric survival models, life tables, Kaplan Meier estimates, and the Cox proportional hazards model. Additionally, the course focuses on building a tool kit for developing custom models like those that incorporate subgroup heterogeneity, model a non-susceptible subpopulation, model mixtures of risk groups, model clustered observations, incorporate multiple states and model social diffusion processes. This course is not specific to any field within the social sciences, but many of the examples are taken from population studies.

Objectives: After completing this course you will (1) have a working familiarity with the concepts and tools for solving quantitative problems in the statistical analysis of time to events; (2) develop the skills and background to evaluate the use (and misuse) of event history analysis in contemporary social science research; (3) build a tool kit for developing custom event history models; (4) have practical experience analyzing time-to-event data; (5) have undertaken a research project using your own data.

Times

Tuesday and Thursday at 10:30 am-12:20 pm in Savery Hall (SAV) 130.

Office hours: I will typically be available after class for office hours on Thursdays. I will hold Zoom office hours from 6:00 to 6:50 pm on Tuesdays at this meeting ID: 95874140951. Other times can be arranged. Contact me with questions or to set up an appointment.

Readings

The textbooks are

Singer JD, Willett JB (2003) Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford: Oxford University Press.
Box-Steffensmeier JM, Jones BS (2004) Event History Modeling: A Guide for Social Scientists. Cambridge: Cambridge University Press.

Additional readings (here) and handouts (here) will supplement the text. These readings will illustrate principles discussed in lecture and the text, and will also be used as the basis for some class discussions.

A selection of readings (largely collected by past students of this course) are available here

Grading

Grades: There will be 5 problem sets (12% each) that will make up 60% of your final grade, and a final research project (40%). There are no exams.

Problem sets

Problem sets: The five problem sets will consist of analytical exercises, short problems, and data analysis. Data sets used in the problem sets will be available on the course web site. You can use books, readings, notes, and web pages to help you work on the problems. In fact, you can work in groups on most exercises. Grades for late problem sets are reduced by 10% per day, including any fraction of a day late.

Software

You can use any software that works for you and gets the job done. For example, when we work with the Cox proportional hazards regression model, almost any standard statistical software will work. For other assignments only a few "packages" will be able to easily perform the analysis. I strongly encourage you to do most of your work in a statistical programming language like R, Python, Matlab, or Gauss. Most of the coding examples in this class will be in R, so it will be easiest for you to work in R unless you have excellent skills in another language. If there is sufficient interest, I will offer optional weekly computer lab sessions to help you work on course material using the R programming language. Short courses introducing R are usually given by CSSCR during the first two weeks of the quarter. See the CSSCR web site.

Project

40% of your course grade will be based on a project in the form of a completed poster with original research, analysis, and presentation using the methods covered in this course. You will present your poster at a poster session during finals week. The poster session will be a joint event with two+ other CSSS courses, and will be widely advertised to faculty and graduate students. A one paragraph description of your project will be due during week 5. If you don't already have a data set in mind, start early locating one. CSSCR has a data consultant who can help identify and procure relevant data sets.

Course Policies

Academic misconduct

The university's policy on plagiarism and academic misconduct is a part of the Student Conduct Code, which cites the definition of academic misconduct in the WAC 478-121. According to this section of the WAC, academic misconduct includes: "Cheating"-such as "unauthorized assistance in taking quizzes", "Falsification" "which is the intentional use or submission of falsified data, records, or other information including, but not limited to, records of internship or practicum experiences or attendance at any required event(s), or scholarly research"; and "Plagiarism" which includes "[t]he use, by paraphrase or direct quotation, of the published or unpublished work of another person without full and clear acknowledgment."

The UW Libraries have a useful guide for students here.

Accommodation

Your experience in this class is important to me. If you have already established accommodations with Disability Resources for Students (DRS), please communicate your approved accommodations to me at your earliest convenience so we can discuss your needs in this course. The website for the DRO provides other resources for students and faculty for making accommodations.

Washington state law requires that UW develop a policy for accommodation of student absences or significant hardship due to reasons of faith or conscience, or for organized religious activities. The UW's policy, including more information about how to request an accommodation, is available at Religious Accommodations Policy. Accommodations must be requested within the first two weeks of this course using the Religious Accommodations Request form.

Inclusion

Among the core values of the university are inclusivity and diversity, regardless of race, gender, income, ability, beliefs, and other ways that people distinguish themselves and others. If any assignments and activities are not accessible to you, please contact me so we can make arrangements to include you by making an alternative assignment available.

Learning often involves the exchange of ideas. To include everyone in the learning process, we expect you will demonstrate respect, politeness, reasonableness, and willingness to listen to others at all times-even when passions run high. Behaviors must support learning, understanding, and scholarship.

Preventing violence is a shared responsibility in which everyone at the UW plays apart. If you experience harassment during your studies, please report it to the SafeCampus website (anonymous reports are possible). SafeCampus provides information on counseling and safety resources, University policies, and violence reporting requirements help us maintain a safe personal, work and learning environment.

Safety

If you are ill, please do not come to class (or the campus, for that matter). More information about COVID-19 safety and policy can be found here.

Topics and Schedule

Week 1: Introduction to Event History Analysis (Jan 4)

Box-Steffensmeier and Jones Ch 1, 2
Singer and Willett Ch 9
Lecture 1 Notes

Overheads (Jan 4)

Week 2: Probability models (Jan 9, 11)

Box-Steffensmeier and Jones Ch 3
Review probability theory, distributions and random variables, and likelihood as needed: here
Distributions Handout
Likelihood Handout

Week 3: Likelihood and Parametric Survival Models (Jan 16, 18)

Box-Steffensmeier and Jones Ch 3
Messy Data Handout
Covariates Handout

Overheads (Jan 16)
Overheads (Jan 18)
Problem set 1 due (Thursday)
Problem set 2 distributed (Thursday)

Week 4: More Parametric Survival Models (Jan 23, 25)

Gehan (1969)
Blossfeld and Rohwer Ch 3
Singer and Willett Ch 10, 13

Overheads (Jan 23)
Overheads (Jan 25)
Problem set 2 due (Thursday)
Problem set 3 distributed (Thursday)

Week 5: Empirical and seemingly empirical models (Jan 30, Feb 1)

Box-Steffensmeier and Jones Ch 4
Singer and Willett Ch 14
Notes on Writing an Event History Analysis Paper (Tuma)

Week 6: Cox Proportional Hazards Models (Feb 6, 8)

Box-Steffensmeier and Jones Ch 4
Singer and Willett Ch 15

Overheads (Feb 6)
Overheads (Feb 8)
Problem set 3 due (Tuesday).
One paragraph project description due (Thursday)
Problem set 4 distributed (Thursday)

Week 7: More Cox Model and Piecewise Models (Feb 13, 15)

Box-Steffensmeier and Jones Ch 6, 8
Singer and Willett Ch 11, 12

Overheads (Feb 13)
Overheads (Feb 15)
Problem set 4 due (Thursday)

Week 8: Models of Mixed Populations (Unobserved Heterogeneity I) (Feb 20, 22)

Holman (2004)

Week 9: Continuous Unobserved Heterogeneity (Feb 27, 29)

Box-Steffensmeier and Jones Ch 9
Vaupel and Yashin (1985).

Week 10: Some Advanced Models (Mar 5, 7)

Box-Steffensmeier and Jones Ch 10
Wood et al. (1994);
Strang and Tuma (1993)

Overheads (Mar 5)
Overheads (Mar 7)
Problem set 5 due (Tuesday)

Links

References

Aalen OO, Borgan Ø, Gjessing HK (2008) Survival and Event History Analysis: A Process Point of View. New York: Springer.
^**Allison PD (1984) Event history analysis: Regression for longitudinal event data. Newbury Park, CA: Sage Publications.
>Allison PD (1995) Survival Analysis Using the SAS System: A Practical Guide. Cary, NC: SAS Institute Inc.
Blossfeld H-P, Golsch K, Rohwer G (2007) Event History Analysis with Stata. Mahwah, NJ: Lawrence Erlbaum.
Blossfeld H-P, Hamerle A, Mayer KU (1989). Event history analysis. Hillsdale, New Jersey: Lawrence Erlbaum.
Blossfeld H-P, Rohwer G (1995). Techniques of Event History Modeling. Mahwah, NJ: Lawrence Erlbaum.
^***Box-Steffensmeier JM, Jones BS (2004) Event History Modeling: A Guide for Social Scientists. Cambridge: Cambridge University Press.
Broström, G (2012) Event History Analysis with R. Boca Raton, FL, CRC Press.
Cox DR, Oakes D (1984) Analysis of Survival Data. London: Chapman and Hall.
^§Edwards AWF (1972) Likelihood. Cambridge: Cambridge University Press.
^**Elandt-Johnson RC, Johnson NL (1980) Survival Models and Data Analysis. New York: John Wiley and Sons.
^§Evans M, Hastings N, Peacock B (2000) Statistical Distributions. Third edition. New York: John Wiley and Sons.
Gehan EA (1969) Estimating survival functions from the life table. Journal of Chronic Diseases 13:629-644.
Holman DJ (2003) mle: A programming language for building likelihood models. Version 2.1. Volume 1. User's Manual. and Volume 2, Reference Manual. http://faculty.washington.edu/~djholman/mle.
Holman DJ (2003) Unobserved heterogeneity. In: Lewis-Beck MS, Bryman A, Liao TF, (eds.) Encyclopedia of Social Science Research Methods. Thousand Oaks, CA: Sage Publications
Hosmer DW, Lemeshow S (1999) Applied Survival Analysis: Regression Modeling of Time to Event Data. New York: John Wiley and Sons.
Kalbfleisch JD, Prentice RL (1980) The Statistical Analysis of Failure Time Data. New York: John Wiley & Sons.
^*Klein JP, Moeschberger ML (1997) Survival Analysis: Techniques for Censored and Truncated Data. New York: Springer-Verlag.
London D (1997) Survival Models. Winsted, CT:ACTEX Publicatons.
Mayer KU, Tuma NB (eds.) (1990) Event History Analysis in Life Course Research. Madison:Univ. Wisconsin Press.
Mills M (2011) Introducing Survival and Event History Analysis. Thousand Oaks, CA: Sage Publications.
§Namboodiri K, Suchindran CM (1987) Life Table Techniques and their Applications. Orlando: Academic Press.
Nelson W (1982) Applied Life Data Analysis. New York: John Wiley and Sons.
Schoen R (1988). Modeling Multigroup Populations. New York: Plenum Press.
***Singer JD, Willett JB (2003) Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford: Oxford University Press.
Strang D, Tuma NB (1993) Spatial and Temporal Heterogeneity in Diffusion, American Journal of Sociology 99(3):614-639.
Trussell J, Hankinson R, Tilton J (eds.) (1992) Demographic Applications of Event Histroy Analysis. Oxford:Clarendon Press
Tuma NB, Hannan MT (1984) Social Dynamics: Models and Methods. New York: Academic Press.
Vaupel JW, Yashin AI (1985) Heterogeneity's ruses: Some surprising effects of selection on population dynamics. American Statistician 39:176-85.
Vermunt JK (1997) Log-linear models for event histories. London: Sage Publications.
*Lee ET (1992) Statistical Methods for Survival Data Analysis (2nd edition). New York: John Wiley & Sons.
Wood JW, Holman DJ, Yashin A, Peterson RJ, Weinstein M, Chang M-c (1994) A multistate model of fecundability and sterility. Demography 31(3):403-426.
*Yamaguchi K (1991) Event History Analysis. Newbury Park, CA: Sage Publications, Inc.

^* Recommended book for you collection
^** Recommended book for this course (optional)
^*** Required book for this course
^§ Good technical reference.