Activity Number:
|
370
- A Memorial Session for Arthur Cohen
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Memorial
|
Abstract #320855
|
|
Title:
|
Power Calculations and Critical Values for Two-Stage Nonparametric Testing Regimes
|
Author(s):
|
John Edward Kolassa* and Yodit Seifu and Dewei Zhong
|
Companies:
|
Rutgers, the State University of New Jersey and Bristol Myers Squibb and Anheuser-Busch
|
Keywords:
|
Cornish-Fisher Expansion;
Multi-Stage Testing;
Multiple Comparisons
|
Abstract:
|
Interim analysis techniques for clinical trials provide improved power with smaller average sample sizes. These techniques crucially require multivariate probability calculations for determining critical values. Most existing techniques rely on multivariate normal approximations to the joint null distribution of test statistics evaluated on potential interim and full data sets. More accurate critical values for nonparametric testing with an interim analysis are given, using a new multivariate Cornish--Fisher expansion. While earlier authors demonstrated that such an expansion is possible, it has never been implemented before this manuscript. Superior accuracy of power calculations via an Edgeworth series is demonstrated. Example calculations giving sample sizes from desired power are provided. Calculations are implemented in an R package.
|
Authors who are presenting talks have a * after their name.