Abstract
This study attempts to investigate spatial autocorrelation and spillover effects in micro traffic safety analysis. To achieve the objective, a Poisson-based count regression with consideration of these spatial effects is proposed for modeling crash frequency on freeway segments. In the proposed hybrid model, the spatial autocorrelation and the spillover effects are formulated as the conditional autoregressive (CAR) prior and the exogenous variables of adjacent segments, respectively. The proposed model is demonstrated and compared to the models with only one kind of spatial effect, using one-year crash data collected from Kaiyang Freeway, China. The results of Bayesian estimation conducted in WinBUGS show that significant spatial autocorrelation and spillover effects simultaneously exist in the freeway crash-frequency data. The lower value of deviance information criterion (DIC) and more significant exogenous variables for the hybrid model compared to the other alternatives, indicate the strength of accounting for both spatial autocorrelation and spillover effects on improving model fit and identifying crash contributing factors. Moreover, the model results highlight the importance of daily vehicle kilometers traveled, and horizontal and vertical alignments of targeted segments and adjacent segments on freeway crash occurrences.
Highlights
Due to the enormous influences of roadway crashes on human societies, reducing crash risk has long been a primary objective of highway agencies [1].The development of effective countermeasures requires a thorough understanding of the factors that contribute to a crash occurrence
The spatial autocorrelation effect was specified by the intrinsic conditional autoregressive (CAR) prior, and the spatial spillover effect was modeled as the safety impacts of the exogenous variables observed at adjacent segments
One-year crash frequency data for Kaiyang Freeway, which has been split into 154 homogeneous segments, were used to demonstrate the proposed hybrid model and to compare it to the models with only one kind of spatial effect, that is, the traditional CAR model and the emerging spatial spillover effects model
Summary
Due to the enormous influences (over 1.2 million fatalities, as many as 50 million injuries, and billions of dollars in medical treatment and productivity loss annually) of roadway crashes on human societies, reducing crash risk has long been a primary objective of highway agencies [1]. The development of effective countermeasures requires a thorough understanding of the factors that contribute to a crash occurrence. Safety performance functions, are usually developed to identify relationships between the frequency of crashes at specific locations (roadway segment or intersection at the micro-level; state, county, or traffic analysis zone at the macro-level) over specific periods (day, month, or year) and the contributing factors. While the steady progression of methodological innovation has enabled us to more precisely assess the impacts of these factors, some critical methodological issues Public Health 2019, 16, 219; doi:10.3390/ijerph16020219 www.mdpi.com/journal/ijerph
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International journal of environmental research and public health
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
