A recent case-control study raised the hypothesis that acetaminophen use 1 day or more per week for at least 6 months reduces the risk of epithelial ovarian cancer. We assessed analgesic use in relation to epithelial ovarian cancer risk using data from our case-control surveillance study of medication use and cancer. Patients were interviewed in hospitals in Baltimore, Boston, New York, and Philadelphia during 1976-1998. We compared 780 women with epithelial ovarian cancer to 2053 cancer controls and 2570 noncancer controls. For acetaminophen use 1 day or more per week for at least 6 months, the odds ratio estimate was 0.9 (95% confidence interval, 0.6-1.4) derived with cancer controls and 1.0 (0.6-1.5) with noncancer controls. Estimates for more frequent and longer term use were also compatible with 1.0. The odds ratios among patients with metastatic ovarian cancer were reduced but not statistically significant. The odds ratio for use of nonsteroidal anti-inflammatory drugs 4 or more days per week for at least 5 years, 0.5, was statistically significant. The present results provide only weak support for a reduction in the risk of epithelial ovarian cancer among acetaminophen users. They raise the possibility of an inverse association with long-term nonsteroidal anti-inflammatory drug use.