Generalized nonlinear models for rear-end crash risk analysis》.pdfVIP

Accident Analysis and Prevention 62 (2014) 9–16 Contents lists available at ScienceDirect Accident Analysis and Prevention j o u rn al h o m e p ag e: w w w. elsev /locate/aap Generalized nonlinear models for rear-end crash risk analysis Yunteng Lao a , Guohui Zhang b , Yinhai Wang a,∗ , John Milton c a Department of Civil and Environmental Engineering, University of Washington, Seattle, WA 98195, USA b Department of Civil Engineering, University of New Mexico, MSC01 1070, 1,Albuquerque, NM 87131, USA c Washington State Department of Transportation, 414 Olive Way, Suite 400, Seattle, WA 98101-1209, USA a r t i c l e i n f o a b s t r a c t Article history: A generalized nonlinear model (GNM)-based approach for modeling highway rear-end crash risk is for- Received 22 November 2012 mulated using Washington State traffic safety data. Previous studies majorly focused on causal factor Received in revised form 24 August 2013 identification and crash risk modeling using Generalized linear Models (GLMs), such as Poisson regression, Accepted 1 September 2013 Logistic regression, etc. However, their basic assumption of a generalized linear relationship between the dependent variable (for example, crash rate) and independent variables (for example, contribute factors Keywords: to crashes) established via a link function can be often violated in reality. Consequently, the GLM-based Generalized linear model (GLM) mo