A random parameters regional quantile analysis for the varying effect of road-level risk factors on crash rates

Abstract Many studies have been devoted to investigate the spatial variations (heterogeneities) in the effects of risk factors on crash likelihood. However, investigations mainly target the safety effects on the mean of the crash data (distribution). Less attention was paid to investigate the spatial nonstationary effects on the different quantiles of the crash data distribution. In this study, a conditional quantile-based Bayesian hierarchical random parameter Tobit model is proposed to investigate the regional varying effects of road-related factors on crash rate at different quantiles of the crash rate distribution. A specific roadway facility type, urban two-lane two-way roadway segments in Florida, with crash and road related data for a three-year period is used for a case study. The results show that: 1) the regression coefficients of all of the selected risk factors vary over a wide range among 34 counties on every investigated quantiles of crash rate distribution; 2) in each county, the regression coefficients of all of the factors vary over investigated quantiles of the crash rate distribution, and for the same factor, the coefficients present different ranges of the variation in different counties; 3) the 50th-quantile conditional quantile-based Bayesian hierarchical random parameter Tobit model outperforms the conditional mean-based Bayesian hierarchical random parameter Tobit model, Bayesian quantile Tobit model and Bayesian Tobit model in terms of the prediction accuracy measured by the MAE, and 75th-quantile conditional quantile-based Bayesian hierarchical random parameter Tobit model is outstanding in terms of the goodness-of-fit measured by the DIC. These findings suggest the importance of investigating the regional nonstationary effects of risk factors for different quantiles of the crash rate distribution. The practical implications of the proposed conditional quantile-based Bayesian hierarchical random parameter Tobit model in terms of data prediction, parameters interpretation and safety effects explanation are highlighted at the end of this paper.

[1]  Anuj Sharma,et al.  Exploring spatio-temporal effects in traffic crash trend analysis , 2017 .

[2]  Chandra R. Bhat,et al.  Analytic methods in accident research: Methodological frontier and future directions , 2014 .

[3]  Xiao Qin.  Quantile Effects of Causal Factors on Crash Distributions , 2012 .

[4]  Mohamed Abdel-Aty,et al.  A Bayesian spatial random parameters Tobit model for analyzing crash rates on roadway segments. , 2017, Accident; analysis and prevention.

[5]  Yang Song,et al.  Macro-level traffic safety analysis in Shanghai, China. , 2019, Accident; analysis and prevention.

[6]  M. Quddus.  Modelling area-wide count outcomes with spatial correlation and heterogeneity: an analysis of London crash data. , 2008, Accident; analysis and prevention.

[7]  Fred L Mannering,et al.  A note on modeling vehicle accident frequencies with random-parameters count models. , 2009, Accident; analysis and prevention.

[8]  Helai Huang,et al.  Statistical and machine-learning methods for clearance time prediction of road incidents: A methodology review , 2020, Analytic Methods in Accident Research.

[9]  Pengpeng Xu,et al.  Revisiting crash spatial heterogeneity: A Bayesian spatially varying coefficients approach. , 2017, Accident; analysis and prevention.

[10]  Geert Wets,et al.  Application of Geographically Weighted Regression Technique in Spatial Analysis of Fatal and Injury Crashes , 2014 .

[11]  Flávio Cunto,et al.  Geographically weighted negative binomial regression applied to zonal level safety performance models. , 2017, Accident; analysis and prevention.

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

[13]  Bo Song,et al.  Macro and micro models for zonal crash prediction with application in hot zones identification , 2016 .

[14]  Sudeshna Mitra,et al.  Spatial Autocorrelation and Bayesian Spatial Statistical Method for Analyzing Intersections Prone to Injury Crashes , 2009 .

[15]  Marco Geraci,et al.  Linear quantile mixed models , 2013, Statistics and Computing.

[16]  Yu Zhang,et al.  A new access density definition and its correlation with crash rates by microscopic traffic simulation method. , 2014, Accident; analysis and prevention.

[17]  Chuan Ding,et al.  Spatial heterogeneous impact of built environment on household auto ownership levels: evidence from analysis at traffic analysis zone scales , 2016 .

[18]  Lalita Thakali,et al.  Benchmarking regions using a heteroskedastic grouped random parameters model with heterogeneity in mean and variance: Applications to grade crossing safety analysis , 2018, Analytic Methods in Accident Research.

[19]  Xuedong Yan,et al.  Modeling traffic crash rates of road segments through a lognormal hurdle framework with flexible scale parameter , 2015 .

[20]  M. Saberi,et al.  The effect of variations in spatial units on unobserved heterogeneity in macroscopic crash models , 2017 .

[21]  Mohamed M. Ahmed,et al.  Exploring a Bayesian hierarchical approach for developing safety performance functions for a mountainous freeway. , 2011, Accident; analysis and prevention.

[22]  Ming Ma,et al.  A multivariate spatial model of crash frequency by transportation modes for urban intersections , 2017 .

[23]  F. Mannering,et al.  Safety impacts of signal-warning flashers and speed control at high-speed signalized intersections. , 2013, Accident; analysis and prevention.

[24]  Patrick Morency,et al.  The link between built environment, pedestrian activity and pedestrian-vehicle collision occurrence at signalized intersections. , 2011, Accident; analysis and prevention.

[25]  Pengpeng Xu,et al.  Modeling crash spatial heterogeneity: random parameter versus geographically weighting. , 2015, Accident; analysis and prevention.

[26]  Rahim Alhamzawi,et al.  Bayesian Tobit quantile regression using g-prior distribution with ridge parameter , 2015 .

[27]  J. Powell,et al.  Censored regression quantiles , 1986 .

[28]  Jinjun Tang,et al.  Crash prediction based on random effect negative binomial model considering data heterogeneity , 2020, Physica A: Statistical Mechanics and its Applications.

[29]  Paul P Jovanis,et al.  Analysis of Road Crash Frequency with Spatial Models , 2008 .

[30]  Fred L. Mannering,et al.  The effect of speed limits on drivers' choice of speed: A random parameters seemingly unrelated equations approach , 2016 .

[31]  Tawfiq Sarwar,et al.  The Effect of Long Term Non-invasive Pavement Deterioration on Accident Injury-severity Rates: A Seemingly Unrelated and Multivariate Equations Approach , 2017 .

[32]  Nalini Ravishanker,et al.  Selecting exposure measures in crash rate prediction for two-lane highway segments. , 2004, Accident; analysis and prevention.

[33]  A. Shalaby,et al.  Macrolevel Accident Prediction Models for Evaluating Safety of Urban Transportation Systems , 2003 .

[34]  Dominique Lord,et al.  Multilevel Dirichlet process mixture analysis of railway grade crossing crash data , 2016 .

[35]  Jonathan Aguero-Valverde,et al.  Multivariate spatial models of excess crash frequency at area level: case of Costa Rica. , 2013, Accident; analysis and prevention.

[36]  H. Lian,et al.  Bayesian quantile regression for longitudinal data models , 2012 .

[37]  Xiaoyan Huo,et al.  A correlated random parameters tobit model to analyze the safety effects and temporal instability of factors affecting crash rates. , 2019, Accident; analysis and prevention.

[38]  Duncan Lee,et al.  Bayesian quantile regression for count data with application to environmental epidemiology , 2010 .

[39]  Simon Washington,et al.  On the significance of omitted variables in intersection crash modeling. , 2012, Accident; analysis and prevention.

[40]  Tom Brijs,et al.  Assessing the road safety impacts of a teleworking policy by means of geographically weighted regression method , 2014 .

[41]  Juneyoung Park,et al.  Crash modeling for intersections and segments along corridors: a Bayesian multilevel joint model with random parameters , 2017 .

[42]  Helai Huang,et al.  Modeling unobserved heterogeneity for zonal crash frequencies: A Bayesian multivariate random-parameters model with mixture components for spatially correlated data , 2019 .

[43]  Jinjun Tang,et al.  Crash injury severity analysis using a two-layer Stacking framework. , 2019, Accident; analysis and prevention.

[44]  Mohamed Abdel-Aty,et al.  Sensitivity analysis in the context of regional safety modeling: identifying and assessing the modifiable areal unit problem. , 2014, Accident; analysis and prevention.

[45]  S. Erdogan.  Explorative spatial analysis of traffic accident statistics and road mortality among the provinces of Turkey. , 2009, Journal of safety research.

[46]  Chandra R. Bhat,et al.  Unobserved heterogeneity and the statistical analysis of highway accident data , 2016 .

[47]  Zhiliang Ying,et al.  Simple resampling methods for censored regression quantiles , 2000 .

[48]  Maozai Tian,et al.  Hierarchical linear regression models for conditional quantiles , 2006 .

[49]  Yuanchang Xie,et al.  Crash frequency analysis of different types of urban roadway segments using generalized additive model. , 2012, Journal of safety research.

[50]  Le Minh Kieu,et al.  Spatiotemporal and random parameter panel data models of traffic crash fatalities in Vietnam. , 2016, Accident; analysis and prevention.

[51]  P. Jovanis,et al.  Spatial analysis of fatal and injury crashes in Pennsylvania. , 2006, Accident; analysis and prevention.

[52]  Helai Huang,et al.  Investigating varying effect of road-level factors on crash frequency across regions: A Bayesian hierarchical random parameter modeling approach , 2018, Analytic Methods in Accident Research.

[53]  Helai Huang,et al.  A multivariate random-parameters Tobit model for analyzing highway crash rates by injury severity. , 2017, Accident; analysis and prevention.

[54]  Jie Wang,et al.  The effect of zonal factors in estimating crash risks by transportation modes: Motor vehicle, bicycle and pedestrian. , 2017, Accident; analysis and prevention.

[55]  A. Gelfand,et al.  Spatial Quantile Multiple Regression Using the Asymmetric Laplace Process , 2012 .

[56]  Eren Erman Ozguven,et al.  Multivariate random parameter Tobit modeling of crashes involving aging drivers, passengers, bicyclists, and pedestrians: Spatiotemporal variations. , 2018, Accident; analysis and prevention.

[57]  Helai Huang,et al.  Support vector machine in crash prediction at the level of traffic analysis zones: Assessing the spatial proximity effects. , 2015, Accident; analysis and prevention.

[58]  Shlomo Bekhor,et al.  Risk evaluation by modeling of passing behavior on two-lane rural highways. , 2009, Accident; analysis and prevention.

[59]  J. Tobin.  Estimation of Relationships for Limited Dependent Variables , 1958 .

[60]  Weixu Wang,et al.  Using Geographically Weighted Poisson Regression for county-level crash modeling in California , 2013 .

[61]  Yanyong Guo,et al.  Modeling correlation and heterogeneity in crash rates by collision types using full bayesian random parameters multivariate Tobit model. , 2019, Accident; analysis and prevention.

[62]  Keechoo Choi,et al.  A two-stage bivariate logistic-Tobit model for the safety analysis of signalized intersections , 2014 .

[63]  Rune Elvik,et al.  A synthesis of studies of access point density as a risk factor for road accidents. , 2017, Accident; analysis and prevention.

[64]  Jinjun Tang,et al.  Analyzing Traffic Crash Severity With Combination of Information Entropy and Bayesian Network , 2019, IEEE Access.

[65]  Helai Huang,et al.  Road network safety evaluation using Bayesian hierarchical joint model. , 2016, Accident; analysis and prevention.

[66]  Andrew P Tarko,et al.  Tobit analysis of vehicle accident rates on interstate highways. , 2008, Accident; analysis and prevention.

[67]  R. Koenker,et al.  Regression Quantiles , 2007 .

[68]  Xiao Qin,et al.  Identifying crash-prone locations with quantile regression. , 2010, Accident; analysis and prevention.

[69]  Ling Zhang,et al.  Evaluating the Spatial Deprivation of Public Transportation Resources in Areas of Rapid Urbanization: Accessibility and Social Equity , 2019, Discrete Dynamics in Nature and Society.

[70]  Helai Huang,et al.  County-Level Crash Risk Analysis in Florida: Bayesian Spatial Modeling , 2010 .

[71]  Shahram Heydari,et al.  A flexible discrete density random parameters model for count data: Embracing unobserved heterogeneity in highway safety analysis , 2018, Analytic Methods in Accident Research.

[72]  F. Mannering,et al.  Time-of-day variations and temporal instability of factors affecting injury severities in large-truck crashes , 2019, Analytic Methods in Accident Research.

[73]  Fred L Mannering,et al.  A study of factors affecting highway accident rates using the random-parameters tobit model. , 2012, Accident; analysis and prevention.

[74]  Qiang Zeng,et al.  Bayesian spatial joint modeling of traffic crashes on an urban road network. , 2014, Accident; analysis and prevention.

[75]  Mohamed Abdel-Aty,et al.  Multi-level hot zone identification for pedestrian safety. , 2015, Accident; analysis and prevention.

[76]  Kun Xie,et al.  Multivariate dynamic Tobit models with lagged observed dependent variables: An effectiveness analysis of highway safety laws. , 2018, Accident; analysis and prevention.

[77]  Keming Yu,et al.  A Three-Parameter Asymmetric Laplace Distribution and Its Extension , 2005 .

[78]  Mohamed Abdel-Aty,et al.  Multilevel data and bayesian analysis in traffic safety. , 2010, Accident; analysis and prevention.

[79]  Helai Huang,et al.  Evaluating Spatial-Proximity Structures in Crash Prediction Models at the Level of Traffic Analysis Zones , 2014 .

[80]  Samuel Labi,et al.  Impact of road-surface condition on rural highway safety: A multivariate random parameters negative binomial approach , 2017 .

[81]  Ashim Kumar Debnath,et al.  A Tobit model for analyzing speed limit compliance in work zones , 2014 .

[82]  Rahim Alhamzawi,et al.  Bayesian Lasso-mixed quantile regression , 2014 .

[83]  Mohamed Abdel-Aty,et al.  Intersection crash prediction modeling with macro-level data from various geographic units. , 2017, Accident; analysis and prevention.

[84]  F. Mannering.  Temporal instability and the analysis of highway accident data , 2018 .

[85]  Sze Chun Wong,et al.  Incorporating safety reliability into route choice model: Heterogeneous crash risk aversions , 2020 .

[86]  Keming Yu,et al.  Bayesian quantile regression , 2001 .

[87]  Zhenggang He,et al.  Safety assessment of signalized intersections with through-movement waiting area in China , 2017 .

[88]  Fred L Mannering,et al.  A multivariate tobit analysis of highway accident-injury-severity rates. , 2012, Accident; analysis and prevention.

[89]  Julian Stander,et al.  Bayesian analysis of a Tobit quantile regression model , 2007 .