A method of reviewing a series of clinical trials by extracting the basic data in the form of 2 x 2 tables and analysing these by Fisher's two-tailed Exact Test is described, and illustrated by published imipramine-placebo trials. The results suggest that the benefit of this drug in patients with endogenous depression who have not become institutionalized is indisputable, and that further drug-placebo trials in this condition are not justified. Two of the three trials of imipramine in neurotic depression gave results showing significant improvement. Possible explanations of the apparent failure of this drug in groups of patients with undifferentiated depression are discussed.