A0820
Title: Robust external information borrowing in clinical trial hypothesis testing
Authors: Silvia Calderazzo - German Cancer Research Center (DKFZ) (Germany) [presenting]
Abstract: Bayesian clinical trials offer a natural framework for the incorporation of external information via the specification of informative prior distributions. Borrowing of such external information is often desired in order to improve the trial's efficiency and can be of crucial importance in situations where the sample size that can realistically be recruited is limited, such as paediatric or rare disease trials. An issue associated with the incorporation of external information is that external and current information may systematically differ, but such inconsistency may not be predictable or quantifiable a priori. Robust prior choices are typically proposed to avoid extreme worsening of operating characteristics in such situations. However, trade-offs in terms of frequentist characteristics are still present, and in general, no power gains are possible if strict control of type I error rate is desired. In this context, easily interpretable rationales for controlled type I error rate inflation can be of interest. An approach which allows a principled and controlled type I error rate inflation is presented. Both one and two-arm designs are considered.
