Online Program Home
My Program

Abstract Details

Activity Number: 609 - New Approaches to Improving Accuracy, Precision, and Robustness of Survival Analysis
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #304536
Title: Joint Testing of Overall and Simple Effects for the 2-By-2 Factorial Trial Design
Author(s): Eric Leifer* and James Troendle and Alexis Kolecki and Dean Follmann
Companies: National Heart,Lung and Blood Institute and National Institutes of Health and National Heart, Lung, and Blood Institute and National Institute of Allergy and Infectious Diseases
Keywords: factorial design; overall and simple effects; subadditivity; stratified logrank test; clinical trial

The 2-by-2 factorial design randomizes subjects to receive treatment A alone, treatment B alone, both treatment A and B (AB), or neither treatment (C). When the combined effect of A and B is less than the sum of the separate A and B effects, called subadditivity, there can be low power to detect the A effect using an overall test which compares the A and AB groups to the C and B groups. Such subadditivity occurred in the Action to Control Cardiovascular Risk in Diabetes blood pressure trial (ACCORD BP) which simultaneously randomized subjects to receive standard or intensive blood pressure, respectively, glycemic, control. For the primary outcome of major cardiovascular event, the overall test for efficacy of intensive blood pressure control was nonsignificant. Simple effect tests such as A vs. C and AB vs. C may be useful since they are not affected by subadditivity, but they can have lower power since they use half the subjects of the overall test. We discuss joint testing procedures which exploit the sample size advantage of the overall test and robustness to subadditivity of the simple tests. These procedures are applied to the ACCORD-BP trial data.

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

Back to the full JSM 2019 program