Citation

Dong C, Nambisan SS, Xie K, Clarke DB, Yan X. Transportmetrica A: Transp. Sci. 2016; 13(2): 91-107.

Copyright

(Copyright © 2016, Informa - Taylor and Francis Group)

DOI

10.1080/23249935.2016.1212290

PMID

unavailable

Abstract

Since highway safety laws vary greatly from state to state in the U.S., there is a need to analyze the effectiveness and performances of the implemented highway safety laws. The random-parameter zero-truncated negative binomial (RZTNB) models are proposed to analyze the effects of highway safety laws on fatal crashes at state levels. The results show that the proposed models are useful in describing the relationships between the fatal crashes and the explanatory variables with better goodness of fit. By accounting for the heterogeneities, the RZTNB model outperforms the negative binomial (NB) model and reveals new insights. The findings indicate that 1) compared to the secondary ban, the primary hand held cellphone ban is more effective; 2) establishing reasonable and acceptable speed limits can enhance the traffic safety; 3) the implemented speed camera system and ignition interlock device have weaknesses and alternative methods should be considered when upgrading laws and regulations.

Language: en