Dear Allstaters I've to decide for the sample size of a multiarm phase II clinical trial. The problem is to evaluate 2 new chemoterapy treatments and to choice the best one for a possible phase III design. The outcome is response. We know that standard therapy response is p0; response at treatment-1 will be p1 and p2 for treatment-2. We'll continue the study on treatment-1 if p1>p2 and p1>p0 (from a statistical point of view). We'll continue with treatment-2 if p2>p1 and p2>p0. No further analysis will be performed if p1<=p0 and p2<=p0. Questions: - Which is the best criterion to establish the sample size? - Does anyone knows other works about multiarm phase II design based on response, apart Simon et al (1985) Randomized Phase II Clinical Trials, Cancer Treatment Reports, 69, n. 12? - Which problems arise using standard optimization criterion for 2 stage phase II clinical trial (Simon, Optimal two-stage design for phase II clinical trials, Controlled Clinical Trials 10:1-10, 1989), considering the two arms as two separated studies? - If you've to choice one, which combination do you prefer between {alpha=0.05 & beta=0.20} and {alpha=0.10 & beta=0.10} in a phase II? many thanks Cristian ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Cristian Pattaro Sezione di Epidemiologia & Statistica Medica Dipartimento di Medicina e Sanità Pubblica Università degli Studi di Verona Istituti Biologici II - Blocco B Strada Le Grazie, 8 I-37134 Verona - Italy Tel +39 045 8027668 fax +39 045 505357 [log in to unmask]