Escitalopram, a selective serotonin reuptake inhibitor (SSRI), was compared to placebo in a study of patients with major depressive disorder (DSM-IV) who had baseline Montgomery–Åsberg Depression Rating Scale (MADRS) total scores ≥22 and ≤40. After a 1-week, single-blind placebo period, patients were randomized to receive escitalopram 10 mg/day (n =191) or placebo (n =189) in an 8-week, double-blind period. The primary efficacy analysis of adjusted mean change in MADRS total score from baseline showed a statistically significantly larger effect for escitalopram than for placebo with a treatment difference at week 8 (last observation carried forward, LOCF) of 2.7 points (SE 0.85;P =0.002). In further by-week efficacy analyses, the effect of escitalopram was consistently larger than that of placebo (P <0.05) beginning at week 1 (Clinical Global Impression–Improvement score), week 2 (MADRS score) or week 3 (Clinical Global Impression–Severity score). Escitalopram was very well tolerated with a low overall withdrawal rate similar to that for placebo. Nausea was the only adverse event reported significantly more in escitalopram-treated patients than in placebo-treated patients, although it was infrequent and transient. Escitalopram 10 mg/day had a statistically significantly better antidepressant effect than placebo as early as week 1, and was safe and very well tolerated.