The Multivariate Poisson Log Normal (MVPLN) fully Bayesian (FB) method has recently been introduced in road safety analysis mainly for network screening and using different crash severity levels. However, there is little or no research applying MVPLN to different crash types. Besides, only one model structure for the expected crashes of a given severity was investigated in previous MVPLN studies. Another knowledge gap is that this method has not yet been evaluated for before-after treatment effect analysis. The objective of this study was to evaluate the application of MVPLN FB methods for before-after road safety evaluation studies. Two groups of unsignalized California intersections, for which a naive before-after comparison shows a significant change in the crash frequency after a hypothetical treatment was assigned, were used to conduct the study. Four function forms forthe expected crashes of a given crash type were developed and investigated. The results were then compared with those from the univariate FB method. It was found that the crash reduction rates are sensitive to the function form of expected crashes. For each model structure, MVPLN, univariate Poisson Log Normal (PLN) and Poisson-Gamma models provided comparable results while PLN was proved to be superior. Models considering temporal effects of unobserved latent variables are superior to those without time variation. Both FB methods can simultaneously provide estimation results for all types of crashes while the univariate FB takes much less simulation time. Thus, the traditional univariate FB is preferred for conducting before-after treatment effect analysis for different crash types. KEY WORDS: Multivariate Poisson Log Normal; before-after studies; empirical Bayes; full Bayes; treatment effect analysis; Deviance Information Criterion
Samenvatting