Complementary parametric probit regression and nonparametric classification tree modeling approaches to analyze factors affecting severity of work zone weather-related crashes

Abstract

Identifying risk factors for road traffic injuries can be considered one of the main priorities of transportation agencies. More than 12,000 fatal work zone crashes were reported between 2000 and 2013. Despite recent efforts to improve work zone safety, the frequency and severity of work zone crashes are still a big concern for transportation agencies. Although many studies have been conducted on different work zone safety-related issues, there is a lack of studies that investigate the effect of adverse weather conditions on work zone crash severity. This paper utilizes probit-classification tree, a relatively recent and promising combination of machine learning technique and conventional parametric model, to identify factors affecting work zone crash severity in adverse weather conditions using 8 years of work zone weatherrelated crashes (2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013) in Washington State. The key strength of this technique lies in its capability to alleviate the shortcomings of both parametric and nonparametric models. The results showed that both presence of traffic control device and lighting conditions are significant interacting variables in the developed complementary crash severity model for work zone weather-related crashes. Therefore, transportation agencies and contractors need to invest more in lighting equipment and better traffic control strategies at work zones, specifically during adverse weather conditions.

Impact of risk factors on work zone crashes using logistic models and Random Forest

“…Meng et al [8] also developed a novel probabilistic Quantitative Risk Assessment (QRA) model to evaluate the casualty risk combining frequency and consequences of all crash scenarios triggered by long-term work zone crashes. Furthermore, Ghasemzadeh and Ahmed [9] used a probit-classification tree to identify factors affecting work zone crash severity in adverse weather conditions using eight years of work zone weather-related crashes (i.e., 2006-2013) in the State of Washington. Likewise, Koilada [10] examined and identified factors that influence crash injury severity in work zone areas using five years (2010-2014) of crash data from North Carolina.…”