APPLIED LONGITUDINAL ANALYSIS:
CONTRASTING MARGINAL AND MIXED EFFECTS MODELS
Garrett M. Fitzmaurice
(Harvard University)
Abstract
| The goal of this short course is to provide an introduction to modern statistical methods for analyzing longitudinal data. The main emphasis is on the practical rather than the theoretical aspects of longitudinal analysis. The course begins with a general introduction to linear mixed effects models for analyzing longitudinal data when the response of interest is continuous. When the response of interest is categorical (e.g., binary or count data), a number of extensions of generalized linear models to longitudinal data have been proposed. We present a broad overview of two main types of models: "marginal models" and "generalized linear mixed models". While both classes of models account for the within-subject correlation among the repeated measures, they differ in approach. Moreover, these two classes of models have regression coefficients with quite distinct interpretations and address somewhat different questions regarding longitudinal change in the response. In this course we highlight the main distinctions between these two types of models and discuss the types of scientific questions addressed by each. |
Garrett Fitzmaurice is Professor of Psychiatry (Biostatistics) at the Harvard Medical School, Professor in the Department of Biostatistics at the Harvard School of Public Health, and Foreign Adjunct Professor of Biostatistics at the Karolinska Institute, Sweden. He is a Fellow of the American Statistical Association and a member of the International Statistical Institute. He has served as Associate Editor for Biometrics, the Journal of the Royal Statistical Society, Series B, and Biostatistics; currently, he is Statistics Editor for the journal Nutrition.
His research and teaching interests are in methods for analyzing longitudinal and repeated measures data. A major focus of his methodological research has been on the development of statistical methods for analyzing repeated binary data and for handling the problem of attrition in longitudinal studies. Much of his collaborative research has concentrated on applications to mental health research,broadly defined.
He has co-authored the textbook Applied Longitudinal Analysis (Wiley, 2004) and recently co-edited the book Longitudinal Data Analysis (Chapman & Hall/CRC Press, 2008). He received the American Statistical Association's Excellence in Continuing Education Award for a short course on longitudinal analysis at the Joint Statistical Meetings in 2006.
