Abstract #301836

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 #301836
Activity Number: 203
Type: Contributed
Date/Time: Tuesday, August 5, 2003 : 8:30 AM to 10:20 AM
Sponsor: ENAR
Abstract - #301836
Title: Comparison of Analyses for Repeated Binary Data from an Ophthalmic Study
Author(s): Kuolung Hu*+ and Vipin Arora and David Manner
Companies: Eli Lilly & Company and Eli Lilly & Company and Eli Lilly & Company
Address: 9030 Bryce Way, Fishers, IN, 46038-9066,
Keywords: generalized estimating equations ; mixed -effects model ; repeated measures
Abstract:

This work considers population-based model approaches to analyze repeated binary data from randomized longitudinal clinical trials. The ophthalmic data are simulated for a two-arm (treated and nontreated group) study with evenly enrolled patient population with diabetes. The primary endpoint is progression to center-involved Diabetic Macular Edema (DME) (Yes/No) and is observed over time (maximum exposure 36 months with 12 posttime points including baseline). Two statistical approaches, (i) likelihood-based (mixed-effects logistic model with REPL) and (ii) non-ikelihood (GEE) regression models, are compared to analyze the binary response outcome which can reverse during the study. The probability of dropouts and reversal of events are considered for several simulation scenarios. By focusing on (population) marginal modeling, we will demonstrate that GEE performs asymptotically as well as the mixed-effects model for parameter estimation. Furthermore, we demonstrate that GEE is superior to the mixed-effects model in detecting the outcome event rate for some scenarios.

  • 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