|
Activity Number:
|
338
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #302025 |
|
Title:
|
Statistical Power and Sample Size Determination for Clinical Trials with Multiple Primary Endpoints
|
|
Author(s):
|
Chengjie Xiong*+ and J. Philip Miller
|
|
Companies:
|
Washington University, St. Louis and Washington University, St. Louis
|
|
Address:
|
Division of Biostatistics, Campus Box 8067, St. Louis, MO, 63110,
|
|
Keywords:
|
Alzheimer's disease ; Central Limit Theorem ; intersection-union test
|
|
Abstract:
|
This article concerns the statistical power and sample size determination for testing the treatment efficacy from clinical trials involving multiple primary endpoints. We consider a two-arm clinical trial in which the definition of treatment efficacy requires the simultaneous statistical evidence favoring the active treatment from all primary endpoints. We study the significance level and the statistical power for the test of treatment efficacy using the intersection-union test for several different situations based on the type of primary efficacy variables. We also present the appropriate method of sample size determination for such clinical trials and compare it to the intuitive approach of selecting the maximum sample size over those obtained from individual tests of multiple primary variables. We point out that the maximum sample size from multiple individual tests is often inadequate for the test of treatment efficacy. A real Alzheimer's clinical trial is used to demonstrate the sample size method.
|
