Abstract #301783

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301783
Activity Number: 420
Type: Contributed
Date/Time: Wednesday, August 6, 2003 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #301783
Title: A Generalized Mixed-Effects Model Approach to the Analysis of Binary Longitudinal Data Subject to Informative Dropout
Author(s): George Manos*+ and Michael P. Jones and Mary K. Cowles
Companies: Bristol-Myers Squibb Company and University of Iowa and University of Iowa
Address: 97 David Dr., Middletown, CT, 06457-5193,
Keywords: informative dropout ; binary longitudinal data ; generalized mixed-effects models ; Gibbs sampler
Abstract:

The time of dropout in longitudinal epidemiological studies is often related to the measure under study thus resulting in informatively censored values. In these situations, estimates of population parameters are biased when they are derived using standard methods of longitudinal data analysis, which assume that the data are missing at random. A growing body of statistical methods addresses ways to correct this bias by modeling the time to dropout jointly with the longitudinal data. A Bayesian approach is proposed for the analysis of binary longitudinal data, where time to dropout is modeled by a discrete-time proportional hazards model jointly with the longitudinal data. Gibbs sampler is used to simultaneously estimate all fixed and random effects parameters, as well as their standard errors. Results from a simulation study, where longitudinal data were generated subject to informative censoring mechanisms, show that the proposed model compares favorably against a likelihood based mixed-effects generalized linear model and against a similar Bayesian longitudinal model that make no adjustments for the dropout mechanism.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003