Response-Adaptive Randomized Clinical Trial with Missing Data

• Activity Number: 132
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Zhenjun Ma*+ and Feifang Hu
• Companies: University of Virginia and University of Virginia
• Keywords: Asymptotic properties ; Complete case analysis ; Doubly-adaptive biased coin design ; Likelihood-based inference ; Missing at random ; Power

Abstract

Missing data are commonly encountered in clinical studies. In the literature, attention has been mainly focused on clinical trials that are implemented following fixed designs. For the past decades, response-adaptive randomization has been extensively studied in clinical trial designs due to its ethical and efficient advantages. Dealing with missing data in response-adaptive randomized clinical trials is important and urgent. In this paper we propose likelihood-based inference to sequentially analyze missing data to ensure the desired allocation proportion be consistently estimated and approached. We established the asymptotic properties of doubly-adaptive biased coin design under the ignorable missing mechanism. We illustrate the proposed approach by examples where both binary and normal responses are considered. Simulation studies demonstrated the merits of our approach in finite sample cases.