Online Program Home
  My Program

Abstract Details

Activity Number: 6 - New Methods and Software for Adaptive Designs
Type: Invited
Date/Time: Sunday, July 30, 2017 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract #322014 View Presentation
Title: An Optimized Adaptive Enrichment Design for Multi-Arm Trials
Author(s): Michael Rosenblum* and Aaron Fisher and Jon Steingrimsson and Joshua A Betz
Companies: Johns Hopkins University and Johns Hopkins University and Johns Hopkins University and Johns Hopkins University
Keywords: Optimization ; Clinical Trials ; Adaptive Designs
Abstract:

We discuss a new adaptive enrichment design comparing two treatments to a common control in two different sub-populations. The proposed design leverages the correlation between the test statistics arising from that both treatments are compared to a common control. Furthermore, the design improves efficiency through step-down procedures and relies only on minimally sufficient statistics. Implementation of the design requires specifying several design parameters. We use simulated annealing to select the design parameters that minimize expected sample size subject to type one error and power constraints. The performance of the design is compared to more traditional designs using a recent clinical trial on cardiac resynchronization therapy.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association