Online Program Home
My Program

Abstract Details

Activity Number: 621
Type: Contributed
Date/Time: Wednesday, August 3, 2016 : 2:00 PM to 3:50 PM
Sponsor: Health Policy Statistics Section
Abstract #319614
Title: Using Adaptive Designs to Avoid Selecting the Wrong Arms in a Comparative Effectiveness Trial
Author(s): Byron Gajewski*
Companies: University of Kansas Medical Center
Keywords: Adaptive sample size ; Bayesian adaptive trials ; Comparative effectiveness research ; Response adaptive randomization
Abstract:

How to involve potential treatments, when there are more than two, is an important step in the planning of a comparative effectiveness clinical trial. A constraint is the small amount of resources for conducting the trial places a limitation on the sample size. It is tempting to increase the efficiency of this sample size by selecting, say a pair, among the pool of promising treatments before the clinical trial starts. The problem with this approach is that the investigator may inadvertently screen the most beneficial treatment. This talk offers a solution to this problem using response adaptive randomization (RAR). Rather than having to guess at the two best treatments to compare based on no data, we suggest putting more arms in the trial and let RAR figure out the better arms. By doing this you avoid "type III Errors" (the arm not studied) with little lost in the cases where you would have in fact selected the best two.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association