|
Activity Number:
|
202
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #309660 |
|
Title:
|
Assessment of Bayesian Estimates of Biomarker's Surrogacy for a Time-to-Event Clinical Endpoint in a Single Trial
|
|
Author(s):
|
Qian Shi*+ and Mary K. Cowles
|
|
Companies:
|
The University of Iowa and The University of Iowa
|
|
Address:
|
Biostatistics, 525 Hawkeye Court, Iowa City, IA, 52246,
|
|
Keywords:
|
adjusted association ; Bayesian statistics ; relative effect ; surrogate endpoint ; time-to-event data
|
|
Abstract:
|
The Relative effect (RE) and adjusted association (AA) proposed by Buyse are widely accepted measures of surrogacy. Cowles developed Bayesian joint models (BJM) to estimate these measures when the clinical endpoint of interest is time-to-event in a single trial. RE is intended to predict the treatment effect on the clinical endpoint based on its effect on the surrogate. AA measures the association between the clinical and surrogate endpoints, adjusted for treatment. Simulation studies under the BJM show that AA can be precisely and accurately estimated. Inclusion of an endpoint with high AA improves the prediction of censored failure times significantly. In contrast, estimation of RE has tremendous variability, and is influenced by the significance of the treatment effects. Alternatives to RE, multiple surrogate endpoints, and appropriate uses of a marker with high AA are considered.
|
