Abstract

Most statistical methodology for phase III clinical trials focuses on the comparison of a single experimental treatment with a control treatment, with selection of the treatment made in a phase II trial. Recently, however, there has been increasing interest in methods for phase II/III trials that combine the treatment selection element of a phase II clinical trial with the definitive analysis associated with phase III clinical trials.

This talk will describe a method for combining phases II and III in a single phase II/III clinical trial that proceeds in a number of stages. The first stage is rather like the usual phase II trial, with patients randomised between a control treatment and a number of experimental treatments. At the end of this stage, the best experimental treatment is selected. If this is clearly superior or clearly inferior to the control treatment, the trial might be stopped at this point either for efficacy or for futility respectively. If the trial is not stopped, it continues to the second stage, which is more like the usual phase III trial, with recruitment to the control arm and the selected experimental treatment arm alone. The second stage may itself include interim analyses comparing the two treatments. An extension of the group-sequential approach will be used to ensure that the overall type I error rate is controlled at the specified level.

The talk will conclude with a discussion of the problem of estimation of treatment effects after a trial in which treatment selection has taken place.