Background and purpose Depressed mood is a common psychiatric problem associated with Parkinson's disease (PD), and studies have suggested a benefit of rasagiline treatment. Methods ACCORDO (see the ) was a 12‐week, double‐blind, placebo‐controlled trial to evaluate the effects of rasagiline 1 mg/day on depressive symptoms and cognition in non‐demented PD patients with depressive symptoms. The primary efficacy variable was the change from baseline to week 12 in depressive symptoms measured by the Beck Depression Inventory (BDI‐IA) total score. Secondary outcomes included change from baseline to week 12 in cognitive function as assessed by a comprehensive neuropsychological battery; Parkinson's disease quality of life questionnaire (PDQ‐39) scores; Apathy Scale scores; and Unified Parkinson's Disease Rating Scale (UPDRS) subscores. Results One hundred and twenty‐three patients were randomized. At week 12 there was no significant difference between groups for the reduction in total BDI‐IA score (primary efficacy variable). However, analysis at week 4 did show a significant difference in favour of rasagiline (marginal means difference ± SE: rasagiline −5.46 ± 0.73 vs. placebo −3.22 ± 0.67; P = 0.026). There were no significant differences between groups on any cognitive test. Rasagiline significantly improved UPDRS Parts I (P = 0.03) and II (P = 0.003) scores versus placebo at week 12. Post hoc analyses showed the statistical superiority of rasagiline versus placebo in the UPDRS Part I depression item (P = 0.04) and PDQ‐39 mobility (P = 0.007) and cognition domains (P = 0.026). Conclusions Treatment with rasagiline did not have significant effects versus placebo on depressive symptoms or cognition in PD patients with moderate depressive symptoms. Although limited by lack of correction for multiple comparisons, post hoc analyses signalled some improvement in patient‐rated cognitive and depression outcomes.