Does Prior Specification Matter in Hotspot Identification and Before–After Road Safety Studies?

Abstract

This study investigated the effects of prior assumptions in applications of full Bayes methods in road safety analysis. The effect of prior choice was evaluated in the accuracy of model parameters, hotspot identification, goodness of fit, and a treatment effectiveness index in before–after studies. Particular attention was devoted to conditions with a lack of data, which were referenced as the low-mean and small-sample problem. In this research, informative, semi-informative, and noninformative priors were determined on the basis of past published studies. A simulation framework was used to evaluate various scenarios of sample size and crash occurrence mean. Quasi-simulated data were generated on the basis of two empirical databases of divided and undivided rural highway segments in New York and Texas. Various sample mean values were obtained on the basis of time period (number of years) and classifying accidents in fatal–injury and total accidents. The outcomes under low-mean and small-sample conditions were found to be significantly biased. However, the introduction of informative priors can make observational before–after studies feasible when a few observations from treatment or comparison sites are used. Informative priors can help provide more accurate estimates of the effectiveness of the treatment. Finally, in accordance with previous works, the inverse dispersion parameter was significantly affected by prior specifications; nevertheless, regression parameters, goodness of fit, and hotspot identification were less sensitive to prior choices.