American Statistical Association
The topic of my talk is Growth Mixture Modeling, a method to discover latent growth trajectories in longitudinal outcomes (e.g., Prostate-Specific Antigen test) and link these latent growth curves with an outcome of interest (e.g., survival without PCa). The advantages of GMM over mixed-effects models in longitudinal data analysis will be discussed. Several applications of GMM will be summarized, with a focus on McCulloch et al's (2002) study on linking longitudinal changes in PSA with survival. I will briefly describe how to carry out a similar analysis with a binary outcome (not survival) using Mplus.
|Date:||Wednesday, April 23, 2008|
|Time:||4:00 P.M. - 5:00 P.M.|
Memorial Sloan-Kettering Cancer Center
Department of Epidemiology and Biostatistics
307 East 63rd Street
(between First and Second Avenues)
3rd Floor Conference Room
New York, New York
Note: To gain access to the building, please follow the directions by the telephone in the foyer.