Hierarchical Bayesian Estimation of Safety Performance Functions for Two-Lane Highways Using Markov Chain Monte Carlo Modeling
Publication: Journal of Transportation Engineering
Volume 131, Issue 5
Abstract
A critical part of any risk assessment is identifying how to represent exposure to the risk involved. Recent research shows that the relationship between crash count and traffic volume is nonlinear; consequently, a simple crash rate computed as the ratio of crash count to volume is not suitable for comparing the safety of sites with different traffic volumes. To solve this problem, we describe a new approach for relating traffic volume and crash incidence. Specifically, we disaggregate crashes into four types: (1) single-vehicle, (2) multivehicle same direction, (3) multivehicle opposite direction, and (4) multivehicle intersecting, and then define candidate exposure measures for each (as a function of site traffic volumes) that we hypothesize will be linear with respect to each crash type. This article describes investigation using crash and physical characteristics data for highway segments from Michigan, California, Washington, and Illinois obtained from the Highway Safety Information System. We have used a hierarchical Bayesian framework to fit zero-inflated-Poisson regression models for predicting counts for each of the above crash types as a function of the daily volume, segment length, speed limit and lane/shoulder width using Markov Chain Monte Carlo methods. We found that the relationship between crashes and the daily volume is nonlinear and varies by crash type, and is significantly different from the relationship between crashes and segment length for all crash types. Significant differences in exposure functions by crash type are proven using analysis of variance and Tukey tests.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This research was sponsored by a Transportation Statistics Research Grant from the Bureau of Transportation Statistics, United States Department of Transportation and was performed at the Connecticut Transportation Institute in the University of Connecticut. The writers thank Yusuf Mohamedshah of Federal Highway Administration for providing them with the HSIS dataset and assisting us in interpreting it. They also gratefully acknowledge contribution to this project made by Dr. Don Tepas and Jianhe Du. Thanks also go to Dr. Diane Lambert of Bell Labs for providing ZIP model computer codes.
References
Bayesian Output Analysis (BOA) (2002). ⟨http://www.public-health.uiowa.edu/boa/⟩, accessed June 1, 2002.
Gelman, A., Carlin, J. B., Stern, H. S., and Rubin, D. B. (1995). Bayesian data analysis, Chapman & Hall/CRC, London.
Hauer, E. (1995). “On exposure and accident rate.” Traffic Eng. Control, 36, 134–138.
Hauer, E. (1997). Observational before–after studies in road safety, Pergamon, New York.
Lambert, D. (1992). “Zero-inflated Poisson regression, with an application to defects in manufacturing.” Technometrics, 34(1), 1–14.
Mathsoft (1995). S-plus, 1995 User’s Manual, Version 3.3 for Windows, Statistical Sciences Division, Seattle.
Miaou, S.-P., and Lord, D. (2003). “Modeling traffic crash-flow relationships for intersections: Dispersion parameter, functional form, and Bayes versus empirical Bayes.” Presented at Transportation Research Board Proc., Washington, D.C.
Miaou, S.-P., and Lum, H. (1993). “Modeling vehicle accidents and highway geometric design relationships.” Accid. Anal Prev., 25(5), 689–709.
SAS Institute, Inc. (1990). SAS/STAT user’s guide, Volume 2, Version 6, 4th Ed. Cary, N.C.
Tanner, M. (1993). Tools for statistical inference, Springer, New York.
Tunaru, R. (1999). “Hierarchical Bayesian models for road accident data.” Traffic Eng. Control, 40, 318–324.
Information & Authors
Information
Published In
Copyright
© 2005 ASCE.
History
Received: Sep 29, 2003
Accepted: Oct 20, 2004
Published online: May 1, 2005
Published in print: May 2005
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.