SummaryTraditionally, noninferiority hypotheses have been tested using a frequentist method with a fixed margin. Given that information for the control group is often available from previous studies, it is interesting to consider a Bayesian approach in which information is "borrowed" for the control group to improve efficiency. However, construction of an appropriate informative prior can be challenging. In this paper, we consider a hybrid Bayesian approach for testing noninferiority hypotheses in studies with a binary endpoint. To account for heterogeneity between the historical information and the current trial for the control group, a dynamic P value-based power prior parameter is proposed to adjust the amount of information borrowed from the historical data. This approach extends the simple test-then-pool method to allow a continuous discounting power parameter. An adjusted α level is also proposed to better control the type I error. Simulations are conducted to investigate the performance of the proposed method and to make comparisons with other methods including test-then-pool and hierarchical modeling. The methods are illustrated with data from vaccine clinical trials.
| INTRODUCTIONWhen designing a clinical trial to evaluate a test treatment, active controls are often considered when placebo treatment becomes unethical, for example, in cases of life-threatening disease and the availability of established therapy. However, the goal may not be to demonstrate superiority of the test treatment over the active control but rather be to show that the test treatment is at least as efficacious as the active control. In this case, a noninferiority (NI) trial is commonly used to show that the effect of the test treatment is within a certain prespecified amount of the effect of the active control. This prespecified quantity, called the NI margin, has to be predetermined and agreed upon by the sponsor and regulatory agencies.For clinical trials with a binary endpoint, response rate is often the primary endpoint for treatment comparison. Assuming that a higher rate represents a better response, an NI hypothesis can be formulated as follows: