Optimal flexible designs in phase II clinical trials.

摘要: In the conduct of a phase II cancer clinical trial, patients usually enter in two stages. If response rate from first stage is low, then study terminates. Within various two-stage designs, Simon proposed optimal and minimax criteria. co-operative group setting, practical considerations make it difficult to arrive at planned sample size exactly. Green Dahlberg compared several flexible designs. this paper, we explicitly define design as collection designs where set consecutive values (n1, ..., nk) second also another (N1, Nk), each k2 possible has same probability occurrence. We apply Simon's criteria for trials order minimize number tested on an ineffective drug.