Exploring a Bayesian hierarchical approach for developing safety performance functions for a mountainous freeway

    Authors

    M. Ahmed; H. Huang; M. Abdel-Aty;B. Guevara

    Comments

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

    Abbreviated Journal Title

    Accid. Anal. Prev.

    Keywords

    Safety; Freeway; Adverse weather; Slope; Curve; Bayesian model; ACCIDENT FREQUENCIES; STATISTICAL-ANALYSIS; EMPIRICAL-ANALYSIS; CRASH-FREQUENCY; POISSON-GAMMA; MODELS; SEVERITIES; PREDICTION; DISPERSION; RANKING; Ergonomics; Public, Environmental & Occupational Health; Social; Sciences, Interdisciplinary; Transportation

    Abstract

    While rural freeways generally have lower crash rates, interactions between driver behavior, traffic and geometric characteristics, and adverse weather conditions may increase the crash risk along some freeway sections. This paper examines the safety effects of roadway geometrics on crash occurrence along a freeway section that features mountainous terrain and adverse weather. Starting from preliminary exploration using Poisson models, Bayesian hierarchical models with spatial and random effects were developed to efficiently model the crash frequencies on road segments on the 20-mile freeway section of study. Crash data for 6 years (2000-2005), roadway geometry, traffic characteristics and weather information in addition to the effect of steep slopes and adverse weather of snow and dry seasons, were used in the investigation. Estimation of the model coefficients indicates that roadway geometry is significantly associated with crash risk; segments with steep downgrades were found to drastically increase the crash risk. Moreover, this crash risk could be significantly increased during snow season compared to dry season as a confounding effect between grades and pavement condition. Moreover, sites with higher degree of curvature, wider medians and an increase of the number of lanes appear to be associated with lower crash rate. Finally, a Bayesian ranking technique was implemented to rank the hazard levels of the roadway segments; the results confirmed that segments with steep downgrades are more crash prone along the study section. (C) 2011 Elsevier Ltd. All rights reserved.

    Journal Title

    Accident Analysis and Prevention

    Volume

    43

    Issue/Number

    4

    Publication Date

    1-1-2011

    Document Type

    Article

    Language

    English

    First Page

    1581

    Last Page

    1589

    WOS Identifier

    WOS:000291296200038

    ISSN

    0001-4575

    Share

    COinS