Familywise error rate control for block response-adaptive randomization

Abstract

Response-adaptive randomization allows the probabilities of allocating patients to treatments in a clinical trial to change based on the previously observed response data, in order to achieve different experimental goals. One concern over the use of such designs in practice, particularly from a regulatory viewpoint, is controlling the type I error rate. To address this, Robertson and Wason (Biometrics, 2019) proposed methodology that guarantees familywise error rate control for a large class of response-adaptive designs. In this paper, we propose an improvement of their proposal that is conceptually simpler, in the specific context of block-randomised trials with a fixed allocation to the control arm. We show the modified method guarantees that there will never be negative weights for blocks of data, and can also provide a substantial power advantage in practice.