Abstract #301249

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 #301249
Activity Number: 302
Type: Contributed
Date/Time: Tuesday, August 5, 2003 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract - #301249
Title: Adjusting for Center Effects in Multicenter Survival Data Analysis
Author(s): Shibao Feng*+ and Robert A. Wolfe
Companies: University of Michigan and University of Michigan
Address: 1413 McIntyre St., Ann Arbor, MI, 48105-2410,
Keywords: clinical trial ; center effects ; observational study ; survival analysis ; stratification ; frailty model
Abstract:

In multicenter clinical trials and observational studies, the type of patients and quality of management can vary from center to center. For time to event data, several methods have been applied to adjust for the center effects, which include treating center effects as fixed or random, and stratifying on centers. In this manuscript, the statistical properties of these methods are discussed and compared by using a simulation study. We conclude that the fixed effects approach may be applied under the conditions where the number of events in each center is large and the treatment effect is independent of the center effects. However, in observational studies, treatment effect is often correlated with center effects. Under this situation, stratification methods can be applied to yield cobsistent treatment effect estimate. The asymptotic properties of the stratification approach depend on the total number of events occurring in the sample. If the censoring rate is high, which leads to a small sample problem, the treatment effect could be overestimated. Moreover, a random effects approach can be employed if there are a large number of centers enrolled in the study.

  • 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