BACKGROUND: Platinum-based chemotherapy is the standard of care for women with advanced ovarian cancer based on the results of randomized trials. We previously showed that only about half of women over the age of 65 years with this disease received platinum-based chemotherapy, and that the likelihood of receiving it decreases with age. METHODS: We used the Surveillance, Epidemiology, and End Results (SEER)-Medicare database to identify women diagnosed from 1/1/92 to 12/31/96 with stage III or IV ovarian cancer who survived > or =120 days beyond diagnosis, and were > or =65 years of age. Cox proportional hazards models and propensity scores were used to control for known predictors of receiving treatment and to estimate the relative effectiveness of different platinum-based regimens. RESULTS: Of the 1759 patients in the sample who met our eligibility criteria, 53% received platinum-based therapy. For this sample, the Cox proportional hazard ratio was 0.72 (95% CI, 0.62-0.91) for mortality associated with the use of any platinum-based therapy, and 0.59 (95% CI, 0.45-0.76) for combination platinum/paclitaxel therapy. Similar results were obtained using propensity score modeling. CONCLUSIONS: In this population-based study, we found that only about half of women with advanced ovarian cancer over age 65 were treated with platinum-based chemotherapy; however, survival improved by 38% in treated women, similar to the benefits described in randomized controlled trials among younger patients, and were greatest when platinum was combined with paclitaxel. An effort to increase the utilization of platinum combination therapy among older patients with advanced ovarian cancer is justified.