On the nature of over-dispersion in motor vehicle crash prediction models.

Statistical modeling of traffic crashes has been of interest to researchers for decades. Over the most recent decade many crash models have accounted for extra-variation in crash counts--variation over and above that accounted for by the Poisson density. The extra--variation--or dispersion--is theorized to capture unaccounted for variation in crashes across sites. The majority of studies have assumed fixed dispersion parameters in over-dispersed crash models--tantamount to assuming that unaccounted for variation is proportional to the expected crash count. Miaou and Lord [Miaou, S.P., Lord, D., 2003. Modeling traffic crash-flow relationships for intersections: dispersion parameter, functional form, and Bayes versus empirical Bayes methods. Transport. Res. Rec. 1840, 31-40] challenged the fixed dispersion parameter assumption, and examined various dispersion parameter relationships when modeling urban signalized intersection accidents in Toronto. They suggested that further work is needed to determine the appropriateness of the findings for rural as well as other intersection types, to corroborate their findings, and to explore alternative dispersion functions. This study builds upon the work of Miaou and Lord, with exploration of additional dispersion functions, the use of an independent data set, and presents an opportunity to corroborate their findings. Data from Georgia are used in this study. A Bayesian modeling approach with non-informative priors is adopted, using sampling-based estimation via Markov Chain Monte Carlo (MCMC) and the Gibbs sampler. A total of eight model specifications were developed; four of them employed traffic flows as explanatory factors in mean structure while the remainder of them included geometric factors in addition to major and minor road traffic flows. The models were compared and contrasted using the significance of coefficients, standard deviance, chi-square goodness-of-fit, and deviance information criteria (DIC) statistics. The findings indicate that the modeling of the dispersion parameter, which essentially explains the extra-variance structure, depends greatly on how the mean structure is modeled. In the presence of a well-defined mean function, the extra-variance structure generally becomes insignificant, i.e. the variance structure is a simple function of the mean. It appears that extra-variation is a function of covariates when the mean structure (expected crash count) is poorly specified and suffers from omitted variables. In contrast, when sufficient explanatory variables are used to model the mean (expected crash count), extra-Poisson variation is not significantly related to these variables. If these results are generalizable, they suggest that model specification may be improved by testing extra-variation functions for significance. They also suggest that known influences of expected crash counts are likely to be different than factors that might help to explain unaccounted for variation in crashes across sites.

[1]  Dipak K. Dey,et al.  Overdispersed Generalized Linear Models , 1997 .

[2]  G. Casella,et al.  Explaining the Gibbs Sampler , 1992 .

[3]  S. Washington,et al.  Statistical and Econometric Methods for Transportation Data Analysis , 2010 .

[4]  Christian P. Robert,et al.  Monte Carlo Statistical Methods , 2005, Springer Texts in Statistics.

[5]  Patrick T McCoy,et al.  ESTIMATION OF SAFETY AT TWO-WAY STOP-CONTROLLED INTERSECTIONS ON RURAL HIGHWAYS , 1993 .

[6]  B. G. Heydecker,et al.  Identification of sites for road accident remedial work by Bayesian statistical methods: an example of uncertain inference , 2001 .

[7]  Simon Washington,et al.  Modeling crash types: New insights into the effects of covariates on crashes at rural intersections , 2006 .

[8]  Bhagwant Persaud,et al.  Calibration and Transferability of Accident Prediction Models for Urban Intersections , 2002 .

[9]  Sarath C. Joshua,et al.  Estimating truck accident rate and involvements using linear and poisson regression models , 1990 .

[10]  Shaw-Pin Miaou,et al.  STATISTICAL EVALUATION OF THE EFFECTS OF HIGHWAY GEOMETRIC DESIGN ON TRUCK ACCIDENT INVOLVEMENTS , 1993 .

[11]  P. McCullagh,et al.  Generalized Linear Models , 1992 .

[12]  Robert Chapman,et al.  The concept of exposure , 1973 .

[13]  M J Maher,et al.  A comprehensive methodology for the fitting of predictive accident models. , 1996, Accident; analysis and prevention.

[14]  Simon Washington,et al.  Validation of FHWA Crash Models for Rural Intersections: Lessons Learned , 2003 .

[15]  H Lum,et al.  Modeling vehicle accidents and highway geometric design relationships. , 1993, Accident; analysis and prevention.

[16]  Simon Washington,et al.  Empirical Investigation of Interactive Highway Safety Design Model Accident Prediction Algorithm: Rural Intersections , 2003 .

[17]  Bhagwant Persaud,et al.  Accident Prediction Models With and Without Trend: Application of the Generalized Estimating Equations Procedure , 2000 .

[18]  David R. Cox,et al.  Some remarks on overdispersion , 1983 .

[19]  Andrew Gelman,et al.  General methods for monitoring convergence of iterative simulations , 1998 .

[20]  Ezra Hauer,et al.  Estimation of safety at signalized intersections , 1988 .

[21]  Yinhai Wang,et al.  Estimating the risk of collisions between bicycles and motor vehicles at signalized intersections. , 2004, Accident; analysis and prevention.

[22]  Bradley P. Carlin,et al.  Bayesian measures of model complexity and fit , 2002 .

[23]  S. Satterthwaite.  A SURVEY OF RESEARCH INTO RELATIONSHIPS BETWEEN TRAFFIC ACCIDENTS AND TRAFFIC VOLUMES , 1981 .

[24]  K. M. Bauer,et al.  STATISTICAL MODELS OF AT-GRADE INTERSECTION ACCIDENTS - ADDENDUM , 2000 .

[25]  E Hauer,et al.  Empirical Bayes approach to the estimation of "unsafety": the multivariate regression method. , 1992, Accident; analysis and prevention.

[26]  J. Lawless,et al.  Tests for Detecting Overdispersion in Poisson Regression Models , 1989 .

[27]  R. Winkelmann.  Econometric Analysis of Count Data , 1997 .

[28]  Carl Belanger,et al.  ESTIMATION OF SAFETY OF FOUR-LEGGED UNSIGNALIZED INTERSECTIONS , 1994 .

[29]  Shaw-Pin Miaou,et al.  Modeling Traffic Crash-Flow Relationships for Intersections: Dispersion Parameter, Functional Form, and Bayes Versus Empirical Bayes Methods , 2003 .

[30]  Bhagwant Persaud,et al.  Disaggregate Safety Performance Models for Signalized Intersections on Ontario Provincial Roads , 1998 .