To evaluate the relationship between prostate cancer and several potential lifestyle risk factors. We analyzed data obtained from a population-based case-control study conducted in eight Canadian provinces. Risk estimates were generated by applying multivariate logistic regression methods to 1623 histologically confirmed prostate cancer cases and 1623 male controls aged 50-74. Cases were more likely to have a first-degree relative with a history of cancer, particularly prostate cancer (OR = 3.1, 95% CI = 1.8-5.4). Reduced risks of prostate cancer were observed among those of Indian descent (OR = 0.2, 95% CI = 0.1-0.5) or any Asian descent (OR = 0.3, 95% CI = 0.2-0.6) relative to those of western European descent. Total fat consumption, tomato and energy intake, were not associated with prostate cancer. The risk of prostate cancer was inversely related to the number of cigarettes smoked daily (p = 0.06) and cigarette pack-years (p < 0.01), while no association was observed between the total number of smoking years or the number of years since smoking cessation. Anthropometric measures and moderate and strenuous levels of leisure time physical activity were not strongly related to prostate cancer. In contrast, strenuous occupational activities at younger ages appeared protective. Our analyses are limited by the absence of data related to tumor severity and screening history. Further studies are needed to investigate the relationship between behavioral risk factors and prostate cancer screening practices.