Abstract #301914

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 #301914
Activity Number: 178
Type: Contributed
Date/Time: Monday, August 4, 2003 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract - #301914
Title: Joint Modeling of Longitudinal Data and Outcome-Related Observation Times
Author(s): Daohai Yu*+ and Donglin Zeng
Companies: Duke University and University of North Carolina
Address: Dept. of Biostatistics and Bioinformatics, Durham, NC, 27710-0001,
Keywords: informative visit times ; semiparametric modeling ; EM algorithm ; profile likelihood ; kernel estimate ; bias
Abstract:

In many longitudinal studies, subjects' visit times are often informative of their longitudinal outcome. When the visit time could depend on the current outcome, simply fitting a joint model may not completely account for the informativeness of the observation times and hence result in biased estimates and invalid inference results. We propose two new joint modeling approaches, one semiparametric and one nonparametric, for the longitudinal outcome observed at outcome-related times. The observation times are modeled using a counting process with subject-specific random effects. We assume that such random effects are shared by the longitudinal outcome and account for the dependence between the visit time and the longitudinal outcome. In the semiparametric approach, the parameter estimates are derived from an EM algorithm and their asymptotic SEs from the profile likelihood function. In the nonparametric approach, the mean function of the longitudinal outcome is assumed to be smooth but completely unknown. We first derive the bias of the usual kernel estimate; then we propose some intuitive methods to eliminate such bias. Both methods are illustrated with examples.

  • 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