Objective: To investigate the association between cigarette smoking, alcohol drinking, coffee consumption and Parkinson’s disease (PD). Methods: We selected subjects affected by idiopathic PD, with a Mini-Mental State Examination of ≧24, and controls matched 1 to 1 with cases by age (± 2 years) and sex. Controls were randomly selected from the resident list of the same municipality of residence of the cases. We assessed cigarette smoking, alcohol drinking, and coffee consumption preceding the onset of PD or the corresponding time for controls using a structured questionnaire, which also evaluated the duration and dose of exposure. Using conditional logistic regression analysis, we calculated adjusted OR and 95% CI. Results: We interviewed 150 PD patients and 150 matched controls. Cigarette smoking (ever vs. never smokers OR = 0.66, 95% CI = 0.41–1.05, p = 0.08) did not show a statistically significant association with PD. We observed an inverse association between alcohol drinking (ever vs. never OR = 0.61, 95% CI = 0.39–0.97, p = 0.037) and coffee consumption (ever vs. never OR = 0.16, 95% CI 0.05–0.46, p = 0.0001) and PD. These associations remained significant after adjustment for other covariates: OR for ever vs. never alcohol consumption was 0.62 (95% CI = 0.43–0.89, p = 0.009) and that for coffee drinking 0.19 (95% CI = 0.07–0.52, p = 0.001). Heavy coffee consumption confirmed the inverse association between coffee and PD (more than 81 cup/year vs. none: OR = 0.20, 95% CI = 0.08–0.47, p ≤ 0.0001). Conclusions: Consistent with previous studies, our results suggest an inverse association between coffee drinking, alcohol consumption and PD. The multiple inverse association observed may indicate a complex interaction between genetic and environmental factors.