Dissertation Proposal

One fundamental question in response adaptive randomization is what allocation proportion we should target to achieve requisite power while resulting in fewer treatment failures. For comparing two treatments, such optimal allocations are well studied in literature. Generalization to K (>2) treatments is necessary in practice. We are interested in finding the optimal allocation proportion, which achieves a requisite power of a multivariate test of homogeneity in binary response experiment while minimizing expected treatment failures at the same time. We propose new optimal allocation without completing the proof. We also present simulation studies which shows response adaptive randomization procedure that targets this new optimal allocation performs better over complete randomization. Future research topics also discussed.