Purpose: To propose a generalized framework to derive multi-treatment optimal response-adaptive designs which are popular in phase III clinical trials so as to allocate a larger number of patients to better treatment. Summary: The response-adaptive designs allocate a larger portion of the sample to better treatment. The studies available are mostly on play-the-winner or randomized play-the-winner rules. These designs can be extended to more than two treatments. Optimal response-adaptive designs are now applied due to their capability to meet certain design objectives. This paper proposes an alternative framework for the derivation of multi-treatment optimal proportions with a general response function.
展开▼
