A review of the state-of-the-art methods in estimating crash modification factor (CMF)

Road authorities and road safety experts are involved in estimating the expected outcomes from road safety treatments. Information derived from proposed treatments enables planners to make comparisons between the expected savings from crash reductions and associated treatment costs. This review aims to provide direction to agencies and practitioners interested in estimating safety effectiveness. Specifically, this study discusses the main methods for developing CMFs, including an overview of each method, data considerations, and their strengths and weaknesses. It also discusses the techniques of estimating combined CMFs resulting from multiple safety treatments. The review showed that observational Before-After (BA) studies with the Empirical Bayes (EB) and Full Bayes (FB) approaches provide enhanced consistency and precision for the estimated safety effectiveness. Alternatively, the cross-sectional method can be adopted in cases where observational BA studies are not practical due to data restrictions. Five additional techniques for estimating combined CMFs were also reviewed. The study notes that while there has been substantial research in the broad area, few studies have reported comparative methods of combined CMF estimation. Future research directions and research gaps are also highlighted in this review.