Increasing evidence suggests that the Mediterranean diet can reduce the risk of CVD. Olive oil is the hallmark of this dietary pattern. We conducted a meta-analysis of case–control, prospective cohort studies and a randomised controlled trial investigating the specific association between olive oil consumption and the risk of CHD (101 460 participants) or stroke (38 673 participants). The results of all observational studies were adjusted for total energy intake. The random-effects model assessing CHD as an outcome showed a relative risk (RR) of 0·73 (95 % CI 0·44, 1·21) in case–control studies and 0·96 (95 % CI 0·78, 1·18) in cohort studies for a 25 g increase in olive oil consumption. In cohort studies, the random-effects model assessing stroke showed a RR of 0·74 (95 % CI 0·60, 0·92). The random-effects model combining all cardiovascular events (CHD and stroke) showed a RR of 0·82 (95 % CI 0·70, 0·96). Evidence of heterogeneity was apparent for CHD, but not for stroke. Both the Egger test (P= 0·06) and the funnel plot suggested small-study effects. Available studies support an inverse association of olive oil consumption with stroke (and with stroke and CHD combined), but no significant association with CHD. This finding is in agreement with the recent successful results of the PREDIMED randomised controlled trial.