Dept. of Statistics and Biostatistics
California State University at East Bay
題 目：Curve-free Bayesian Decision-theoretic Designs for Dose-finding Phase I Trials
時 間：民國106年12月11日 (星期一) 下午13：30
Although Bayesian statistical methods gain attention in the medical community, as they provide a framework for incorporating prior information, the complexity of these methods limited their adoptions in real trials. In addition, how to set up prior distributions is often mysterious to clinicians even to biostatisticians. In this talk, we will propose a curve-free Bayesian method for dose-finding trials, which is easy to understand and implement, yet performs comparably to or better than many other more complex Bayesian methods. We will begin with the simplest case, one-agent case, then to two-agent case and finally to the trials with two responses (toxicity and efficacy).