|
Activity Number:
|
552
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #303539 |
|
Title:
|
Achieving Covariate Balance in Clinical Trials with Outcome-Adaptive Randomization
|
|
Author(s):
|
Jing Ning and Xuelin Huang*+
|
|
Companies:
|
The University of Texas M.D. Anderson Cancer Center and The University of Texas M.D. Anderson Cancer Center
|
|
Address:
|
1400 Pressler Street, Houston, TX, 77230,
|
|
Keywords:
|
Bayesian ; clinical trial design ; covaraite balance ; heterogeneity ; outcome-adaptive design
|
|
Abstract:
|
In randomized clinical trials with a small to moderate sample size, it is important to have roughly balanced distributions for patient characteristics that have great effects on response to treatment. With severe such imbalance, the final conclusion may be invalid. When outcome-adaptive randomization is used to assign more patients to the better-performing treatment arms, the need to achieve covariate imbalance becomes more critical. Block randomization will not work well when the number of covariates to be balanced is not small. In this scenario, we propose a randomization method that is both outcome-adaptive and covariate-adaptive. It is a compromise between these two features. We use simulation to demonstrate the operating characteristics of the proposed design.
|
