This study estimates the dose-response relationship between Body Mass Index (BMI) and crash risk in operators of heavy commercial motor vehicles. Intake data were collected during the first two weeks of instruction from 744 new truck drivers training for their commercial driver’s licenses at a school operated by the cooperating trucking firm. Drivers were then followed prospectively on the job using the firm's operational data for two years, or until employment separation, whichever came first. Multivariate Poisson regression and Cox proportional hazards models were used to estimate the relationship between crash risk and BMI, controlling for demographic characteristics and for variations in the exposure to risks on the road. Results from the Poisson regression, which used cumulative miles driven as an exposure control, indicated that compared to normal BMI (18.5 < BMI < 25) the risk ratio (RR) for all crashes was significantly higher for drivers in the combined obesity Classes II and III: RR = 1.55 (95% CI 1.24-1.94). Similarly, the multivariate Cox proportional hazard model (controlling for miles and job type on a week-by-week basis) showed that crash risk was significantly higher compared to normal BMI for the same combined obesity Classes II and III: RR = 1.54 (95% CI 1.13-2.10). The results of this prospective study establish an association between obesity and crash risk and have important implications for driver health and public safety.