American Statistical Association
In this talk, I will describe a model where two or more longitudinal markers are predictors of a univariate outcome. Each longitudinal marker is summarized by a few latent trajectory variables in stage one of the model. In stage two of the model, these latent trajectory variables are used as predictors of the outcome. A fully Bayesian approach is used to obtain estimates for model parameters. The proposed approach is applied to an example germ cell cancer dataset. Preliminary results from a simulation study and methodological challenges in fitting these models will be discussed.
|Date:||Wednesday, May 2, 2007|
|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.