Activity Number:
|
213
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 13, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biometrics Section*
|
Abstract - #300516 |
Title:
|
Using Counterfactuals to Account for Treatment Failures in Clinical Trials
|
Author(s):
|
Michele Shaffer*+ and Vernon Chinchilli
|
Affiliation(s):
|
Pennsylvania State University and Pennsylvania State University
|
Address:
|
600 Centerview Drive, Suite 2200, Hershey, Pennsylvania, 17033, USA
|
Keywords:
|
Intent-to-treat ; treatment failure ; counterfactual ; data augmentation algorithm
|
Abstract:
|
Consider a two-armed, placebo-controlled trial in which treatment failures may occur. For ethical reasons, it is required to administer emergency medications for subjects experiencing treatment failure, which may bias the set of response measurements. Secondary statistical analyses that supplement the standard intent-to-treat (ITT) analysis can be performed to account for the impact of treatment failures and emergency medications. A Bayesian, counterfactual approach to supplemental analyses uses the data augmentation algorithm for posterior estimation. Bayesian posterior intervals are used to compare the placebo and experimental treatment means for subjects who would not fail under either treatment assignment. A simulation is performed to study the operating characteristics of this approach.
|