In Reply.—
Dr Klein raised two major issues in his critique of our article on the NIMH Treatment of Depression Collaborative Research Program: (1) the specific comparisons made between treatment conditions and the related probability levels for accepting differences between treatments as statistically significant, and (2) the role that the initial severity of depression plays in our study and in interpretation of the findings. We will focus our response on these two issues.Dr Klein stated that the "meaningful pairwise contrasts are not stipulated" and that "counterproductive and arbitrary significance level 'adjustments' are inflicted on the data." In regard to the pairwise contrasts of interest, we stated in our article that "... the two major questions addressed were the following: (1) Is there evidence of the effectiveness of each of the psychotherapies, as compared both with the standard reference treatment of imipramine-CM and with the placebo plus CM (PLA-CM) control