Empirical Bayesian methods for the identification of sites to be considered for specific safety treatments

grantor: University of TorontoThis study develops and illustrates a methodology for identifying sites which have the potential for safety improvements for a specific treatment type. The methodology is applied to two types of vehicular accidents, those occurring due to the presence of horizontal curves and those that are speed related. The road segments investigated are all on two-lane rural undivided highways; data used were obtained from the Ministry of Transportation, Ontario. The modeling utilizes the Empirical Bayesian methodology to estimate the expected frequency of treatable accidents occurring at each site. This estimate is used as a ranking index for treatment. Models are developed for injury (fatal and non-fatal injury) accidents as well as all severities combined. A validation of the procedure shows that it is more efficient and reliable than commonly used blackspot identification methods based on recent accident counts or rates. A useful side benefit is that the procedure provides the basis for the estimation of the safety effect of treatments applied.M.A.Sc