Generalized Hypothesis Testing in Interim Treatment Selection with a Flexible Selection Margin

• Activity Number: 408
• Type: Contributed
• Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Yujun Wu*+ and Peng-Liang Zhao
• Companies: Sanofi-Aventis and sanofi-aventis
• Keywords: adaptive design ; interim treatment selection ; hypothesis testing ; clinical trial

Abstract

Wu and Zhao (2009) introduced a two-stage adaptive design with selection of the treatment at the interim stage. A pre-specified selection margin is used on the interim mean responses to define the acceptable difference in treatment effects for further consideration. The design allows the selection of more than one arm at the interim stage and brings the flexibility to choose the experimental treatment with the best overall merit. However, the proposed hypothesis testing is limited to the situation of two treatment arms and one control/placebo arm. To make the design more practical, we developed a generalized hypothesis testing which can handle the cases when more than two treatment arms are studied. An unconditional testing procedure is proposed to test the individual treatment effects if more than one treatment arms continue to the second stage.