Abstract #301725

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 #301725
Activity Number: 111
Type: Topic Contributed
Date/Time: Monday, August 4, 2003 : 10:30 AM to 12:20 PM
Sponsor: ENAR
Abstract - #301725
Title: Regression Analysis of Correlated Binary Data Using Some Extensions of GEE
Author(s): Justine Shults*+ and Xin Tu
Companies: University of Pennsylvania and University of Pennsylvania
Address: 423 Guardian Dr., Philadelphia, PA, 19104-4209,
Keywords: quasi-least squares ; correlated data ; generalized estimating equations ; GEE1 ; binomial data
Abstract:

We first describe a model for correlated binomial data and several methods for estimating the model parameters. In particular, we study maximum likelihood (ML), the generalized estimating equation (GEE) approach, and the extended GEE approaches of quasi-least squares (QLS) and GEE1 (Prentice 1988). We first discuss the ML approach and conditions under which a first-order approximation to Bahadur's representation for correlated binomial data is a probability density function, for several correlation structures. We then describe implementation of the different approaches for paired correlated binary data. Via simulations, we compare QLS and GEE1 with regard to small sample efficiency and bias of the regression and correlation parameters. We also develop confidence intervals for the correlation parameters for QLS, and compare their properties with those of confidence intervals obtained using GEE1. Finally, we demonstrate the approaches on a subset of paired binary outcomes from a study on physical activity in African American women.

  • 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