|
Activity Number:
|
135
- Multiplicity, Missing Data and Other Topics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 9, 2021 : 1:30 PM to 3:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #319135
|
|
|
Title:
|
Treatment Effects Across Subgroups Based on Shrinkage Estimation
|
|
Author(s):
|
Amarjot Kaur and qing li and Jia Hua*
|
|
Companies:
|
Merck & Co., Inc. and Merck & co., Inc. and Merck
|
|
Keywords:
|
Shrinkage estimation;
Shrinkage estimation;
Bayesian hierarchical models
|
|
Abstract:
|
Subgroup analyses, in addition to overall efficacy and safety assessments, play an important role in evaluation of treatment effect and to understand if there were differences in response among sex, race, age or any other patient characteristics. It is not uncommon to encounter discordant results in subgroups warranting further exploration to help interpret results meaningfully while keeping in mind the caveats around interpretation due to lack of power and multiplicity adjustments for subgroups. In this presentation we will examine shrinkage estimation using Bayesian hierarchical models as an alternative approach for subgroup effect estimation. We will explore subgroup estimation in the context of realistic scenarios encountered in clinical trials and examine the performance using simulated data.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
