Temporal analysis of crash severities involving male and female drivers: A random parameters approach with heterogeneity in means and variances

Abstract

There is a great necessity to understand the endogenous and exogenous mechanism of how male and female driver characteristics determine the crash severity. Consequently, this paper estimated a group of random paramters logit models with heterogeneity in means and variances to investigate the heterogeneity and temporal stability of how male and female drivers affect crash severity. Using the crash data from California between January 1, 2013 and December 31, 2017, an extensive body of factors that could potentially affect crash injury severity were examined. Additionally, the temporal stability and gender transferability of the models were investigated through a series of likelihood ratio tests. Marginal effects were also adopted to analyze the temporal stability of the explanatory variables. Three crash injury severity categories were investigated including fatal injury, severe injury, and minor injury, in terms of roadway characteristics, environmental characteristics, crash characteristics, temporal characteristics and driver characteristics significantly influencing crash injury outcomes. Remarkable differences were observed between crashes involving male and female drivers, and both male and female related crashes exhibited statistically significant temporal instability over the five-year period considered. This paper could potentially be utilized to ameliorate highway safety aimed at male and female drivers respectively and facilitate the development of crash injury mitigation policies. Spatial stability may be also a valuable issue that should be further investigated in future research.