In any antidepressant study, placebo response in patients assigned active drug is a troubling source of variance. There have been few attempts to identify the patients whose conditions improve as a result of true drug effect, in contrast with improvement that is a result of nonspecific effects. In a previous report we demonstrated that true drug effect seemed to be characterized by a two-week delay in onset and persistence. We described a method of pattern analysis to identify such patients. In this report, we describe the use of pattern analysis to replicate our initial findings. Data from a new sample of 150 nonmelancholic patients support the hypothesis that true drug effect is characterized by a two-week delay in onset and persistence of improvement, once achieved. There was little evidence of the onset of antidepressant effect before two weeks. The theoretical and clinical implications of this work are discussed.