We evaluated the relation between postmenopausal estrogen use and the risk of first-time myocardial infarction using both cohort and nested case-control analyses for data derived from a large health maintenance organization. The study population comprised all women aged 50 to 64 years who were members of the Group Health Cooperative of Puget Sound during the years 1978-1984. In the cohort analysis of 120 cases of first-time myocardial infarction that occurred during 17,513 woman-years at risk among current users and 110,971 woman-years at risk among nonusers of replacement estrogens, the relative incidence of myocardial infarction among current users compared with nonusers, adjusted for age and calendar year, was 0.7 (95% confidence interval 0.4-1.3). This small inverse relation between myocardial infarction and current use of replacement estrogens remained unchanged after adjustment in the case-control study for previous prescription of diuretics and antiarhythmic, antihypertensive, and antidiabetic drugs. These data are consistent with previous observations that estrogen replacement therapy causes a small reduction in the risk of hospitalization for myocardial infarction, and incompatible with any large increase in the risk of myocardial infarction in users of replacement estrogen.