Fig. 2From: Type I error rates of multi-arm multi-stage clinical trials: strong control and impact of intermediate outcomesEffect of θ I on the FWER. The FWER of two 3-arm two-stage I≠D designs when both experimental arms are ineffective on D but the underlying treatment effects on I vary in one or both experimental arms. θ Ik is the underlying log HR of arm k on I. a α 1=0.5. b α 1=0.2. HR hazard ratio, FWER familywise error rateBack to article page