Improving functional form in cross-sectional regression studies to capture the non-linear safety effects of roadway attributes—Freeway median width case study

Crash modification factors (CMFs) for several roadway attributes are based on cross-sectional regression models, in the main because of lack data preferred observational before-after study. In developing these little attention has been paid to those functional forms that reflect reality CMFs should not be single-valued, as most available ones are, but vary with application circumstance. Using a full Bayesian Markov Chain Monte Carlo (MCMC) approach, this study aimed improve used derive focus capturing variability inherent crash functions (CMFunctions). The estimated CMFunction target crashes freeway median width, case study, indicates approach is capable function can capture logical CMF given change feature’s value depends only amount also original value. results highlight importance using non-linear effects road estimation models. provides credible assessing safety implications decisions width could improving current design practice.