STAT 601/ SOC 897-002

Advanced Topics in Applied Statistics:
Event History Analysis/Survival Analysis

Goals

  1. To understand how survival and event history models are applied in diverse fields such as Demography, Sociology, Economics, Medical Sciences, Study of Prevention/Intervention, and Education.
  2. To improve communication skills with researchers from other backgrounds.
  3. To learn and benefit from the latest developments in other related fields for your own research interests.
  4. To understand problems encountered by applied researchers and explore solutions to these problems as methodologists.

Course Description

In general the entire class meets on Thursdays from 1:30-3:00 pm in the Conference Room at the Population Studies Center, 1225 South University Avenue. The class will be divided into working teams, each composed of participants with a variety of backgrounds and experiences and a faculty mentor. We will discuss a number of papers representing new methodological developments that are motivated by substantive research interests in various scientific fields. All participants are expected to read all papers. The teams will take turns giving presentations and leading discussions of these papers. Several well-known researchers representing diverse interests in event history analysis will be invited to give presentations. Participants are encouraged to work together on any problems arising out of these presentations/discussions. Team meetings will be held on Tuesdays during the 2:30pm to 4:00pm time interval; however, teams along with their faculty mentor may elect to meet at other times. The talks by researchers will be held from 2pm to 4pm on selected Tuesdays and Thursdays also at the Population Studies Center.

Instructors

Susan Murphy (Statistics/Institute for Social Research); Yu Xie (Sociology/Population Studies Center/Institute for Social Research). For more information, e-mail Susan Murphy (samurphy@umich.edu) or Yu Xie (yuxie@umich.edu).

References

Concepts and Justification

(1) HP Blossfeld, A Hamerle, KU Mayer, Event History Analysis: Statistical Theory and Applications, 1989, Lawrence Erlbaum Assoc., Hillsdale, NJ, pgs. 1-55 on hazard functions, survival functions, life tables and time.

(2) JD Singer, JB Willet, "Modeling the Days of Our Lives: Using Survival Analysis When Designing and Analyzing Longitudinal Studies of Duration and the Timing of Events," Psychological Bulletin, 1991, vol 110, pgs. 268-290.

Life Tables and Log-linear Models

(1) K Namboodiri, CM Suchindran, Life Table Techniques and Their Applications, 1987, Academic Press, Inc., FL, pgs. 1-9.

(2) N Laird, D Olivier, "Covariance Analysis of Censored Survival Data Using Log-Linear Analysis Techniques," JASA, 1981, vol. 76, pgs. 231-240.

Cox's Proportional Hazards Model for Continuous Time Data

(1) PD Allison, Event History Analysis: Regression for Longitudinal Event Data, 1984, Sage Publications, Beverly Hills, CA, (pgs.33-44 on Cox's proportional hazards model.)

(2) L. Wu. "Effects of Family Instability, Income, and Income Instability on the Risk of a Premarital Birth." American Sociological Review 1996 vol 61, pgs. 386-406.

Discrete Time Hazards Models

(1) JD Singer, and JB Willet, "It's About Time: Using Discrete-Time Survival Analysis to Study Duration and the Timing of Events," Journal of Educational Statistics, 1993, vol 18, pgs. 155-195.

Heterogeneity

(1) JW Vaupel, AI Yashin, "Heterogeneity's Ruses: Some Surprising Effects of Selection on Population Dynamics," American Statistician, 1985, vol. 39, pgs. 176-185.

(2) LA Lillard, "Premarital Cohabitation and Subsequent Marital Dissolution: A Matter of Self-Selection?," Demography, 1995, vol. 32, pgs. 437-457.

(3) Trussell, James and Toni Ricards. 1985. "Correcting for Unobserved Heterogeneity in Hazard Models Using the Heckman-Singer Procedure." In N. B. Tuma (Ed.), Sociological Methodology, pp. 242-276. Josey-Bass, San Francisco.

(4) AI Yashin, IA Iachine, "How frailty models can be used for evaluating longevity limits: taking advantage of an interdisciplinary approach," Demography, 1997, vol. 34, 1997, pgs. 31-48.

Causality

(1) JM Robins, "Structural Nested Failure Time Models," to appear in Encyclopedia of Biostatistics, eds. P Armitage, T Colton. (this is a paper about confounding by time dependent covariates in a proportional hazards model)

(2) JC Witteman, RB D'Agostino, T Stijnen, WB Kannel, JC Cobb, MA de Ridder, A Hofman, JM Robins, "G-estimation of causal effects: isolated systolic hypertension and cardiovascular death in the Framingham Study" (this is an applied paper using the above methodology in an observational study).

Schedule

See updated class schedule on-line at:

 

http://www.psc.lsa.umich.edu/~yuxie/soc897/schedule.html