BACKGROUND AND AIMS: Most studies reporting alcohol use among fatally injured victims are subject to bias, particularly those related to sample selection and to absence of injury context data. We developed a research method to estimate the prevalence of alcohol consumption and test correlates of alcohol use prior to fatal injuries. DESIGN, SETTING AND PARTICIPANTS: Cross-sectional study based on a probability sample of fatally injured adult victims (n = 365) autopsied in São Paulo, Brazil. Victims were sampled within systematically selected 8-hour sampling blocks, generating a representative sample of fatal injuries occurring during all hours of the day for each day of the week between June 2014 and December 2015. MEASUREMENTS: The presence of alcohol and blood alcohol concentration (BAC) were the primary outcomes evaluated according to victims' socio-demographic, injury context data (type, day, time and injury place) and criminal history characteristics. FINDINGS: Alcohol was detected in 30.1% [95% confidence interval (CI) = 25.6-35.1)] of the victims, with a mean blood alcohol level (BAC) level of 0.11% w/v (95% CI = 0.09-0.13) among alcohol-positive cases. Black and mixed race victims presented a higher mean BAC than white victims (P = 0.03). Fewer than one in every six suicides tested positive for alcohol, while almost half of traffic-related casualties were alcohol-positive. Having suffered traffic-related injuries, particularly those involving vehicle crashes, and injuries occurring during weekends and at night were associated significantly with alcohol use before injury (P < 0.05). CONCLUSIONS: Nearly one-third of fatal injuries in São Paulo between June 2014 and December 2015 were alcohol-related, with traffic accidents showing a greater association with alcohol use than other injuries. The sampling methodology tested here, including the possibility of adding injury context data to improve population-based estimates of alcohol use before fatal injury, appears to be a reliable and lower-cost strategy for avoiding biases common in death investigations.