Adaptations That Should Not Raise Objections, but Probably Will

• Activity Number: 221
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Michael Proschan*+
• Companies: National Institute of Allergy and Infectious Diseases
• Keywords: Adaptive methods ; Blinding ; Permutation Tests ; Primary Endpoint ; Type 1 Error Rate

Abstract

Adaptive methods are controversial, especially when something as important as the primary endpoint is changed. But what if the trial data show that the originally planned primary endpoint is simply not available? Alternatively, what if there were two equally reasonable primary endpoint candidates? Is it legitimate to change primary endpoints after looking at data? In some cases the answer is yes. What is perceived as one of the most objectionable midstream adaptions--changing the primary endpoint--should actually be the least objectionable if it is done correctly.