Online Program Home
My Program

Abstract Details

Activity Number: 673 - Clinical Trial Design- 8
Type: Contributed
Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
Sponsor: Biopharmaceutical Section
Abstract #327184 Presentation
Title: Bayesian Predictive Probability for Interim Analysis
Author(s): Dung-Tsa Chen*
Companies: Moffitt Cancer Center
Keywords: Simon two-stage design; Bayesian predictive probability; interim analysis

Simon two-stage design is a widely used approach in early phase II study to evaluate efficacy for single treatment (i.e., single arm design). The 1st stage is used for futility analysis to stop the trial if the treatment is inferior. The method deterministically defines interim and final analysis points and sample sizes for given type I and II errors by minimizing the expected sample size (optimal design) or the maximum sample size (minimax design). In this application, we use the Bayesian posterior probability and the predictive probability to construct a feasible design to evaluate futility in interim analysis. The proposed approach has flexible options to manage the futility assessment at the interim analysis.

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

Back to the full JSM 2018 program