|
Activity Number:
|
341
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #307354 |
|
Title:
|
Designing and Analyzing Covariate-Adjusted Response Adaptive Randomized Clinical Trials
|
|
Author(s):
|
Ayanbola Ayanlowo*+ and David Redden
|
|
Companies:
|
The University of Alabama at Birmingham and The University of Alabama at Birmingham
|
|
Address:
|
RPHB 327M, Birmingham, AL, 35294-0022,
|
|
Keywords:
|
response adaptive ; covariate-adjusted ; covariate by treatment interaction ; randomized clinical trials
|
|
Abstract:
|
Response adaptive randomized clinical trial designs adjust the probability of treatment assignment based upon accrued treatment effect information. Recently in literature, the concept of covariate-adjusted response adaptive randomized designs has been proposed. This method adjusts for both the subjects' response and covariate values to determine the treatment assignment probabilities. We examine the statistical properties of covariate-adjusted response adaptive randomized designs in the presence of covariate by treatment interaction. Specifically, we present methods for analyzing covariate-adjusted response adaptive randomized trials and examine the statistical power of these designs in the presence of covariate by treatment interaction. Simulations will be presented illustrating the properties of these methods under different types of covariate by treatment interactions.
|
