Suppose the primary outcome for the study is changed to a binary outcome of whether or not the ulcer had healed at three month post‐randomisation. Published data on ulcer healing rates in this population suggest an ulcer healing rate of 20%. Suppose the effect of the new dressing will be considered important if it increases the ulcer healing rate from 20% to 30%, at three month postrandomisation.

Use the appropriate sample size formula to work out how many patients in each group need to be recruited to such a trial with a 5% (two‐sided) significance level and a power of 80%?

A. 291 B. 389 C. 582 D. 778 E. 1251