Although there is a significant reduction in atherosclerotic cardiovascular disease risk with statins, a higher risk of diabetes mellitus has been demonstrated in randomized clinical trials. The risk of incident diabetes with statins may be heterogeneous by presence of coronary artery calcium (CAC). We evaluated participants without prevalent diabetes at baseline from the MESA (Multi-Ethnic Study of Atherosclerosis), a prospective cohort study of subjects free of clinical cardiovascular disease at baseline. We used multivariable-adjusted Cox proportional hazards models to study the association between statin use and incident diabetes, adjusting for sociodemographic and cardiovascular risk factors, including time-varying statin use and stratifying by baseline CAC (0, 1 to 100, ≥100). The study population included 5,943 participants with a mean (SD) age of 62 (10) years, 54% women, 41% White, 26% Black, 12% Chinese-American, and 21% Hispanic. In the unadjusted analyses, statin use was associated with a higher risk of incident diabetes (hazard ratio [HR] 1.62, 95% confidence interval [CI] 1.27 to 2.06). After adjustment, this risk was no longer significant (HR 1.13, 95% CI 0.83 to 1.54). Although imprecise, the HR expressing the association of statins with diabetes was lower for those with CAC = 0 (HR 0.80, 95% CI 0.45 to 1.40) than for those with a higher CAC burden (HR 1.30, 95% CI 0.71 to 2.39 for CAC 1 to 100 and HR 1.39, 95% CI 0.85 to 2.28 for CAC ≥100), but this heterogeneity was not statistically significant. In conclusion, statin therapy was not significantly associated with incident diabetes mellitus in this observational study. The risk of incident diabetes did not significantly differ by baseline CAC.