Recent studies do not agree on the possible relationship between medical conditions and traffic safety;​ most of them do not control for exposure factors. In this study, we estimate the effect of binocular vision problems on taxi drivers' distributions of crashes (frequency). Moreover, given a crash, we estimate the effect of monocular vision problems on the distributions of the number of victims per crash (dead or injured). Our data and models permit the simultaneous consideration of many variables:​ age, medical condition, exposure factors measured by distance driven and time behind the wheel, qualitative risk factors, other characteristics of the driver, and crash circumstances in the models for the number of victims. Results show that taxi drivers have a large average number of crashes per year, larger for those with binocular vision problems compared with healthy ones, but not more severe in terms of the number of victims. The past driver's record (number of crashes and demerit points in the previous year) is a significant predictor for the number of crashes. Age is associated significantly with the number and the severity of crashes with older drivers having a better record than the youngest group (30 years old or less).