Keywords: Bayesian design, clinical trial, frequentist, operating characteristics
Bayesian statistics is an approach to reveal clinical evidence as it accumulates. If correctly employed, It may be less burdensome than a frequentist approach because the Bayesian approach uses Bayes’ Theorem to formally combine prior information with current information on a parameter of interest while the frequentist approach uses previous information only at the design stage. Although Bayesian analyses are often computationally intense, recent breakthroughs in computational algorithms and computing speed have made it possible to carry out calculations for very complex and realistic Bayesian models. Regardless of whether a Bayesian or frequentist approach is used, scientifically sound clinical trial planning and rigorous trial conduct are important from a regulatory perspective. FDA usually recommends that the sponsor remain vigilant regarding randomization, concurrent controls, prospective planning, blinding, bias, precision, and all other factors that go into a successful clinical trial. Because of the inherent flexibility in the design of a Bayesian clinical trial, a thorough evaluation of the operating characteristics is recommended in the “Guidance for the Use of Bayesian Statistics in Medical Device Clinical Trials.” Specifically, a regulatory reviewer expects to see the following parameters as the part of the trial planning. During the luncheon, we will discuss these parameters and exchange views regarding these parameters between the industry statisticians and FDA statistical reviewers. • probability of erroneously approving an ineffective or unsafe device (type I error rate, • probability of erroneously disapproving a safe and effective device (type II error rate), • power (the converse of type II error rate: the probability of appropriately approving a safe and effective device), • sample size distribution (and expected sample size), • prior probability of claims for the device, and • if applicable, probability of stopping at each interim look