JSM Preliminary Online Program
This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.

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 2006 Program page

Activity Number: 231
Type: Topic Contributed
Date/Time: Tuesday, August 8, 2006 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract - #306269
Title: Is It Better To Use Random Effects Models in Analysis of Repeated Binary Responses with Missing Data?
Author(s): Guanghan Liu*+
Companies: Merck Research Laboratories
Address: 785 Jolly Road, Blue Bell, PA, 19422,
Keywords: repeated binary response ; dropouts ; random effects ; GEE ; LOCF
Abstract:

In analysis of repeated binary responses with missing data, conventional methods such as the last observation carried forward (LOCF) approach can be biased in both parameter estimates and hypothesis tests. Generalized estimating equation (GEE) method is valid when missing data are missing complete at random. However, when data are missing at random, analyses based on GEE can be biased. Several random effect--based likelihood or quasi-likelihood methods have been proposed in the literature to overcome the drawbacks. These methods are available in many statistical software packages, including SAS version 9. In this presentation, we will evaluate the random effects models with full- or quasi-likelihood methods in the analysis of repeated binary response data. Simulations are used to compare the results and performance among these methods under different assumptions.

  • 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 2006 program

JSM 2006 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised April, 2006