A multinomial logit model-Bayesian network hybrid approach for driver injury severity analyses in rear-end crashes. (July 2015)

• Record Type: Journal Article
• Authors: Chen, Cong; Zhang, Guohui; Tarefder, Rafiqul; Ma, Jianming; Wei, Heng; Guan, Hongzhi
• Is Part Of: Accident analysis and prevention. Volume 80(2015)
• Page Start: 76
• Page End: 88
• Publication Date: 2015-07
• Subjects: Rear-end crash -- Multinomial logit model -- Bayesian network -- Traffic safety; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2015.03.036
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: This study formulated driver injury severities in rear-end crashes in New Mexico. A multinomial logit model is used to select significant factors on injury severity. A Bayesian network is trained to examine interdependency among selected factors. This study provides insights for understanding and reducing rear-end crashes. Abstract: Rear-end crash is one of the most common types of traffic crashes in the U.S. A good understanding of its characteristics and contributing factors is of practical importance. Previously, both multinomial Logit models and Bayesian network methods have been used in crash modeling and analysis, respectively, although each of them has its own application restrictions and limitations. In this study, a hybrid approach is developed to combine multinomial logit models and Bayesian network methods for comprehensively analyzing driver injury severities in rear-end crashes based on state-wide crash data collected in New Mexico from 2010 to 2011. A multinomial logit model is developed to investigate and identify significant contributing factors for rear-end crash driver injury severities classified into three categories: no injury, injury, and fatality. Then, the identified significant factors are utilized to establish a Bayesian network to explicitly formulate statistical associations between injury severity outcomes and explanatory attributes, including driver behavior, demographic features, vehicle factors, geometric and environmental characteristics, etc. The test results demonstrate that the proposed hybrid approach performs reasonably well. The Bayesian network reference analyses indicate that the factors including truck-involvement, inferior lighting conditions, windy weather conditions, the number of vehicles involved, etc. could significantly increase driver injury severities in rear-end crashes. The developed methodology and estimation results provide insights for developing effective countermeasures to reduce rear-end crash injury severities and improve traffic system safety performance.