Swiss Summer School 2008

Johanne Boisjoly
Panel Data Analysis/Event History

Johanne Boisjoly

Johanne Boisjoly is a full professor at the Université du Québec à Rimouski, since 1982. She has a Ph.D. in Sociology from the University of Montreal. Her main interests are in Methodology, Statistical Methods applied to the study of socio-economic inequalities. While spending two years at the Institute for Social Research at the University of Michigan (1993-1995), she was involved in numerous research project involving the analysis of the Panel Study of Income Dynamics 25-year data. She is currently working on two new longitudinal data analysis projects using the Add Health data (National Longitudinal Study of Adolescent Health, University of North Carolina at Chapel Hill), with Greg J. Duncan (Northwestern University) and Kathleen M. Harris (University of North Carolina); and the Canadian Panel Survey data: Survey of Labor and Income Dynamics, with Paul Bernard and Stéphane Crespo (Université de Montréal).

Workshop contents and objectives

Introduction to longitudinal data: censoring and time-varying explanatory variables.

Descriptive methods: the survival analysis. Event history methods. Discrete-Time Method using Logistic Regression Models. Introduction to parametric methods. The Proportional-Hazards Model (Cox regression). Introduction to the various Statistical Packages that provide Event History analysis methods: SPSS, SAS, STATA, TDA. Overview of advanced topics.

The objective of this workshop will be to acquire a practical knowledge of event history data analysis. It will involve the use of SPSS to analyse longitudinal data. There will also be a special emphasis put on the data construction issues involved in longitudinal data analysis.

Bibliography

Basic texts/overview

Remedial Reading

  1. Lewis-Beck, Michael S. Applied Regression. An introduction. Quantitative Applications in the Social Sciences, #22, Sage: Beverly Hills, 1980.
  2. Aldrich, J.H., Forrest D. Nelson. Linear Probability, Logit, and Probit Models. Quantitative Applications in the Social Sciences, #45, Sage: Beverly Hills, 1984.
  3.  

    [Workshops]