This paper introduces a Bayesian accident risk analysis framework that integrates both accident frequency and its expected consequences in the hotspot identification process. This Bayesian framework allows the introduction of uncertainty not only in the accident frequency/severity model parameters but also in key variables such as vehicle occupancy levels and severity weighing factors. For modeling and estimating the severity levels of each individual involved in an accident, a Bayesian multinomial model is proposed. For modeling accident frequency, we use hierarchical Poisson models.We also show how our framework can be implemented to compute alternative relative and absolute measures of total risk for hotspot identification. To illustrate the applicability of our proposed approach, a group of highway-railway crossings from Canada is used as an application environment.
Samenvatting