Title

Application of Poisson random effect models for highway network screening

Authors

Authors

X. M. Jiang; M. Abdel-Aty;S. Alamili

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Accid. Anal. Prev.

Keywords

Hotspot identification; Network screening; Empirical Bayesian; Full; Bayesian; Random effect; Poisson Log-Normal; NEGATIVE BINOMIAL MODEL; CRASH-FREQUENCY; ACCIDENT; PREDICTION; SEVERITY; COUNTS; Ergonomics; Public, Environmental & Occupational Health; Social; Sciences, Interdisciplinary; Transportation

Abstract

In recent years, Bayesian random effect models that account for the temporal and spatial correlations of crash data became popular in traffic safety research. This study employs random effect Poisson Log-Normal models for crash risk hotspot identification. Both the temporal and spatial correlations of crash data were considered. Potential for Safety Improvement (PSI) were adopted as a measure of the crash risk. Using the fatal and injury crashes that occurred on urban 4-lane divided arterials from 2006 to 2009 in the Central Florida area, the random effect approaches were compared to the traditional Empirical Bayesian (EB) method and the conventional Bayesian Poisson Log-Normal model. A series of method examination tests were conducted to evaluate the performance of different approaches. These tests include the previously developed site consistence test, method consistence test, total rank difference test, and the modified total score test, as well as the newly proposed total safety performance measure difference test. Results show that the Bayesian Poisson model accounting for both temporal and spatial random effects (PTSRE) outperforms the model that with only temporal random effect, and both are superior to the conventional Poisson Log-Normal model (PLN) and the EB model in the fitting of crash data. Additionally, the method evaluation tests indicate that the PTSRE model is significantly superior to the PLN model and the EB model in consistently identifying hotspots during successive time periods. The results suggest that the PTSRE model is a superior alternative for road site crash risk hotspot identification. (C) 2013 Elsevier Ltd. All rights reserved.

Journal Title

Accident Analysis and Prevention

Volume

63

Publication Date

1-1-2014

Document Type

Article

Language

English

First Page

74

Last Page

82

WOS Identifier

WOS:000330752900009

ISSN

0001-4575

Share

COinS