|
Activity Number:
|
562
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 3, 2016 : 11:35 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #321581
|
|
|
Title:
|
A Simulation-Based Method for Detecting the Best Treatment in Clinical Trials
|
|
Author(s):
|
Yan Zhao* and Roy Tamura and Michael Brown
|
|
Companies:
|
University of Oklahoma Health Sciences Center and University of South Florida and Oklahoma Medical Research Foundation
|
|
Keywords:
|
best treatment ;
bootstrap ;
clinical trials ;
power ;
simulation
|
|
Abstract:
|
We consider clinical trials without a control arm comparing a binary endpoint among several treatment groups. The objective of the clinical trial is to determine the best treatment group and compare this treatment group to the best of the other treatment groups. Previously, Kim (1988) has shown that for continuous data, the usual t-test comparing the best observed arm with the best of the rest arms has the proper alpha level but is conservative. A similar argument holds for the score test for binary data. In our research, we propose a simulation-based method that controls the alpha level and is more powerful than the score test. The operating characteristics of the new method will be assessed using simulation studies.
|
Authors who are presenting talks have a * after their name.
