Noncompliance with statins is common in typical patient care settings, yet population-level benefits and cost-effectiveness have been estimated based on clinical trials, where medication compliance is high. OBJECTIVES: To evaluate 1) the excess morbidity and mortality attributable to noncompliance, and 2) the cost-effectiveness of statins under conditions of typical compliance. METHODS: A Markov model was used to compare three scenarios of compliance with statin therapy (ideal, typical, and no treatment) in a hypothetical cohort of patients 65 to 84 years of age with a history of myocardial infarction (MI). Outcomes were compared incrementally among the scenarios and included lifetime risk of reinfarction and stroke, quality-adjusted life-years (QALYs) gained, lifetime costs in U.S. dollars, and cost-effectiveness (cost per QALY gained). Data for the no treatment and ideal compliance scenarios were based on the placebo and treatment arms of the Cholesterol And Recurrent Events (CARE) trial, respectively. Data for the typical compliance scenario were based on a sub-study of actual filled prescriptions in 1035 patients similar to CARE participants, with effectiveness for this group interpolated from the no treatment and ideal compliance groups. RESULTS: Compared with no treatment, typical compliance with statins yielded an average of 0.15 additional QALY; ideal compliance would have gained 0.38 QALY. For 1000 patients with typical compliance, 52 myocardial infarctions and 26 strokes were attributable to noncompliance. Compared to no treatment, the incremental cost-effectiveness of secondary prevention with statins in patients 65-84 years of age with typical compliance was $14,800 per QALY gained. CONCLUSIONS: A typical elderly population using statins for secondary prevention can be expected to receive less than 40% of the potential benefits of therapy. Despite the lost clinical benefits, statin therapy remains relatively cost-effective, even when compliance is modest.