We conducted a multicenter case-control study of clinically and histologically diagnosed idiopathic pulmonary fibrosis (IPF), a chronic diffuse interstitial lung disease of unknown cause. The study included 248 cases, and 491 control subjects identified through random-digit dialing, matched to cases in sex, age, and geographic region. Telephone interviews were conducted with both cases and controls to collect information on potential risk factors for IPF, including smoking and household, occupational, and environmental exposures. Pulmonary function tests, X-rays, computed tomographic (CT) scans of the chest, and lung biopsy reports were submitted by referring centers to support the diagnoses. An a priori hypothesis that smoking is associated with IPF was examined with conditional logistic regression analyses. More cases (72%) than control subjects (63%) had a history of ever smoking. The odds ratio (OR) for ever smoking was 1.6 (95% CI: 1.1 to 2.4). Risk was significantly elevated for former smokers (OR = 1.9; 95% CI: 1.3 to 2.9) and for smokers with 21 to 40 pack-yr (OR = 2.3; 95% CI: 1.3 to 3.8). A history of smoking is associated with an increased risk for the development of IPF. Although there was no clear exposure-response pattern with cumulative consumption of cigarettes, there was a trend for time since cessation of smoking, with the highest risk for those who had most recently quit.