Activity Number:
|
153
- Contributed Poster Presentations: Biopharmaceutical Section
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 8, 2022 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biopharmaceutical Section
|
Abstract #322066
|
|
Title:
|
An Exact Confidence Interval of Observed Proportion with Stratified Factors
|
Author(s):
|
ruji yao* and Amarjot Kaur and qing li
|
Companies:
|
Merck & Co., Inc. and Merck & Co and Merck & co., Inc.
|
Keywords:
|
exact method;
stratified factor;
independent
|
Abstract:
|
In clinical trials, a stratified randomization is often used to control for treatment confounding. With this additional stratification, the weighted estimation will generally have smaller variance and an increased power in treatment comparisons. It is common to use an exact confidence interval (CI) for observed proportions, which can often be done without requiring a normality assumption. In this presentation, we propose a simple method to expand this idea in the context of Exact (Clopper-Pearson) Confidence Limits; this enables us to construct CIs on observed proportions with the addition of stratified factors. We will demonstrate that our new method exhibits a narrower CI width.
|
Authors who are presenting talks have a * after their name.