|
Activity Number:
|
416
- Clinical Trial Design- 4
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #329055
|
Presentation
|
|
Title:
|
New Multiple Hypotheses Testing Procedures Based on Covering Principle
|
|
Author(s):
|
Hong Zhou* and Huajiang Li
|
|
Companies:
|
Arkansas State University and Avanir Pharmaceuticals
|
|
Keywords:
|
Familywise error rate;
multiple hypotheses testing;
covering principle;
closure principle;
graphical method;
gate-keeping
|
|
Abstract:
|
The converting principle has proposed recently to deal with the multiplicity issues when multiple hypotheses are tested simultaneously. New multiple testing procedures are constructed based on the covering principle by using the information among the rejection regions of hypotheses in the sample space. The new procedures can strongly control the familywise error rate. Applications of new procedures to real clinical trials are presented to illustrate how to use the new procedures. The simulation studies show that new procedures are more powerful than the widely used graphical approaches in some scenarios. In addition, the covering principle provides new solutions to the gate-keeping problems.
|
Authors who are presenting talks have a * after their name.
