Abstract:
|
Bayesian adaptive design is a popular concept in recent dose-finding studies. The idea of adaptive design is to use accrued data to make adaptation or modification to an ongoing trial to improve the efficiency of the trial. During the interim analysis, most current methods only use data from patients who have completed the study. However, in certain therapeutic areas subjects are usually studied for months to observe a treatment effect. Thus, a large proportion of them have not completed the study at the interim analysis. Fu and Manner (2010) proposed a Bayesian integrated two-component prediction model to incorporate subjects who have not yet completed the study at the time of interim analysis. In this paper, we extend this method to accommodate delayed binary response and illustrate the Bayesian adaptive design through a simulation example.
|