Activity Number:
|
63
- Power and Sample Size: Methods and Applications
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 3, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Biopharmaceutical Section
|
Abstract #312489
|
|
Title:
|
Calculating Power for the Finkelstein and Schoenfeld Test Statistic for a Composite Endpoint with Two Components
|
Author(s):
|
Thomas Zhou* and Michael P LaValley and Kerrie P Nelson and Howard Cabral and Joseph M Massaro
|
Companies:
|
Boston University and Boston University and Boston University and Boston University and Boston University
|
Keywords:
|
Prioritized outcomes;
generalized pairwise comparisons;
U-statistic;
sample size estimation
|
Abstract:
|
The Finkelstein-Schoenfeld (FS) test is a popular generalized per-patient pairwise comparison approach to analyze prioritized composite endpoints. Power and sample size estimation for the FS test is generally done via simulation. However, this simulation approach can be extremely computationally burdensome, compounded by the increasing complexity of the composite endpoint and sample size. We propose an analytical solution to calculate power and sample size for commonly encountered two component FS-type composite endpoints. The power formulas are derived assuming underlying distributions in each of the component outcomes on the population level, which provide an efficient and practical alternative to the standard simulation approach. Monte-Carlo simulations demonstrate that performance of the proposed formulas for power calculation are consistent with those of the simulation approach, and have generally desirable objective properties including robustness to a wide range of mis-specified distributional assumptions. We demonstrate the application of our proposed power formulas by re-powering the Transthyretin Amyloidosis Cardiomyopathy Clinical Trial (ATTR-ACT).
|
Authors who are presenting talks have a * after their name.