Mid-Course Sample Size Modification in Group-Sequential Designs for Three-Arm Noninferiority Clinical Trials

• Activity Number: 500
• Type: Contributed
• Date/Time: Wednesday, August 6, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Toshimitsu Ochiai*+ and Yuko Ohno and Toshimitsu Hamasaki
• Companies: Shionogi & Co. and Osaka University Graduate School of Medicine and Osaka University Graduate School of Medicine
• Keywords: Three-arm non-inferiority trial ; Group sequential designs ; Sample size recalculation

Abstract

In this presentation, we discuss sample size modification in group-sequential designs for three-arm non-inferiority clinical trials, based on effects observed at the interim, where the trial is designed to demonstrate the non-inferiority (NI) of an experimental intervention to active control and to assess the assay sensitivity (AS) to placebo control. We first outline the power and sample size methods under two decision-making frameworks: (i) designing the trial to demonstrate the NI and AS simultaneously (i.e., at the same interim timepoint of the trial), and (ii) designing the trial to demonstrate the NI and AS at any interim timepoint (i.e., not necessarily simultaneously), with the restriction of demonstrating the AS prior to the NI. We then discuss the sample size recalculation using Cui-Hung-Wang statistics to preserve the overall Type I error rate at a pre-specified alpha level. We evaluate the impact of the sample size recalculation on the power and type I error rate via a simulation study, with the three options, i.e., (a) only allowing an increase in the sample size, (b) only allowing a decrease in the sample size, and (c) allowing an increase or decrease in sample size.