We conducted a population-based cohort study to estimate the risk of myopathy associated with use of lipid-lowering drugs. Using data from general practices in the United Kingdom in 1991 through 1997, we identified three cohorts of individuals 40 to 74 years of age. One cohort comprised 17,219 persons who had received at least one prescription for lipid-lowering drugs in the period; a second cohort consisted of patients with a hyperlipidemia diagnosis who had not been prescribed lipid-lowering drugs (N = 28,974); and a third cohort comprised 50,000 individuals from the general population with no diagnosis of hyperlipidemia. The incidence rate of myopathy in the cohort of users of lipid-lowering drugs was 2.3 per 10,000 person-years [95% confidence interval (95% CI) = 1.2-4.4], which exceeded the incidence rates observed in the nontreated hyperlipidemia cohort [0 per 10,000 person-years (95% CI = 0.0-0.4)] and the general population [0.2 per 10,000 person-years (95% CI = 0.1-0.4)]. The relative risks of myopathy in current users of fibrates and statins compared with nonusers were 42.4 (95% CI = 11.6-170.5) and 7.6 (95% CI = 1.4-41.3), respectively. Potential risk factors other than drug use could not explain our findings in the nested case-control analysis. We conclude that use of lipid-lowering drugs is associated with a substantially greater risk of myopathy, which is most pronounced for fibrates. The absolute risk of myopathy in users of lipid-lowering drugs is, however, small.