Online Program Home
My Program

Abstract Details

Activity Number: 262
Type: Contributed
Date/Time: Monday, August 1, 2016 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #318678
Title: Stratified Exact Test and Confidence Interval for Causal Effects on a Binary Outcome Based on Principal Stratification
Author(s): Yasutaka Chiba*
Keywords: Causal Inference ; Potential Outcome ; Principal Stratification

In the context of randomized trials, Chiba (Journal of Biometrics and Biostatistics 2015; 6: 244) developed an exact test for the weak causal null hypothesis on a binary outcome, by applying the concept of principal stratification. Fisher's exact test, which is a hypothesis test for the sharp causal null hypothesis, is a special case of his exact test. His exact test can straightforwardly be extended to non-inferiority trials and to construct confidence interval. Chiba (Statistics in Medicine, in press) demonstrated that his confidence interval had a width no greater than that from Rigdon and Hudgens (Statistics in Medicine 2015; 34: 924-935), using an example. His approach is nonparametric and requires no assumption about random sampling from a larger population. Consequently, his approach can be applied for statistical inference of causal effects as a unified approach. In this presentation, I extend his approach to stratified exact test and confidence interval, and show some characteristics of the stratified approach. Note that the stratified Fisher's exact test (Jung, Biometrical Journal 2014; 56: 129-140) is also a special case of the stratified exact test given here.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association