Identifying Areas of High Risk for Collisions: a Canda-wide study of grade crossing safety

Ranking sites and identifying high-crash risk locations based on various safety performance measures (e.g. expected crash frequency) are among the key tasks of the safety management program, enabling an effective allocation of funds for safety improvement projects. While several studies have discussed the issues relating to the hotspot identification process at a micro-level (e.g., intersections or highway segments), less attention is given to the macro-level hotspot identification issue: how to identify areas or regions with the highest risk of crashes. In this research, we introduce a Bayesian multilevel (hierarchical) model for estimating the regional differences while controlling for other important site attributes. The proposed method is illustrated using a case study on railway grade crossings in Canada. While accommodating the spatial dependencies of crash risk, our method allows a fair comparison of different regions by adjusting for the effect of covariates such as traffic exposure. In particular, we compute pairwise probabilities of crash risk for each province in Canada compared to all others. We are therefore able to draw inferences about regional safety performances under similar circumstances. Our findings indicate the need for further investigation to identify the possible reasons for inter-region variations in grade crossing safety across Canada. Our approach could be useful to guide safety policy development and resource allocation.