Optimization of Error Spending Approach in Clinical Trials

• Activity Number: 130
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Michael Baron*+ and Yi Zhong
• Companies: The University of Texas at Dallas and The University of Texas at Dallas
• Keywords: group sequential clinical trial ; sequential planning ; error spending ; power ; Type I error ; canonical distribution

Abstract

Error spending approach developed by Slug and Wei (1982) and Lan and DeMets (1983) provides convenient flexibility of group sizes in group sequential clinical trials. According to a suitably chosen error spending function, a sequential design can be chosen that partitions the overall significance level and the overall power between the interim points of the trial. This talk focuses on the optimality of error spending functions, aiming to minimize the expected cost of the clinical trial, fixed cost plus variable cost, under the given significance level and power. We show how such optimization can be accomplished using the new binary segmentation approach and estimate the resulting cost saving.