Sample size calculations when outcomes will be compared with an historicalcontrol

The usual formulae for calculating sample size are not valid when a treated cohort will be compared with an historical control population. Methods app ropriate for a single group study may greatly underestimate the required sa mple size because they, in effect, assume a control population of infinite size. Methods appropriate for a two-group study require specification of th e proportions of patients in the two groups - a requirement that can not be met when the size of the historical control group is fixed. An easily prog rammed iterative solution is presented and simulations indicating the valid ity of the method are performed. (C) 1999 Elsevier Science Ltd. All rights reserved.