A study of factors affecting intersection crash frequencies using random-parameter multivariate zero-inflated models

Abstract

Recent research demonstrates the appropriateness of multivariate regression models in crash count modelling when one specific type of crash counts needs to be analysed, since they can better handle the correlated issues in multiple crash counts. In this paper, a random-parameter multivariate zero-inflated Poisson (RMZIP) regression model is proposed as an alternative multivariate methodology for jointly modelling crash counts simultaneously. Using this RMZIP model, we are able to account for the heterogeneity due to the unobserved roadway geometric design features and traffic characteristics. Our formulation also has the merit of handling excess zeros in correlated crash counts, a phenomenon that is commonly found in practice. The Bayesian method is employed to estimate the model parameters. We use the proposed modelling framework to predict crash frequencies at urban signalized intersections in Tennessee. To investigate the model performances, three models – a fixed-parameter MZIP model, a random-parameter multivariate negative binomial (RMNB) model, and a random-parameter multivariate zero-inflated negative binomial (RMZINB) model – have been employed as the comparison methods. The comparison results show that the proposed RMZIP models provide a satisfied statistical fit with more variables producing statistically significant parameters. In other word, the RMZIP models have the potential to provide a fuller understanding of how the factors affect crash frequencies on specific roadway intersections. A variety of variables are found to significantly influence the crash frequencies by varying magnitudes. These variables result in random parameters and thereby their effects on crash frequencies are found to vary significantly across the sampled intersections.

Keywords:

• Crash frequency
• geometric design features, traffic characteristics
• RMZIP model, Bayesian method

Acknowledgements

Special thanks to TDOT for providing the TRIMS data. This research is supported by funding provided by the Southeastern Transportation Center – a Regional UTC funded by the USDOT Research and Innovative Technology Administration. Additional funding was provided by the Natural Science Foundation of China (No. 51208052).

Disclosure statement

No potential conflict of interest was reported by the authors.