APPLICATION OF MULTIPLE LOGISTIC REGRESSION, BAYESIAN LOGISTIC AND CLASSIFICATION TREE TO IDENTIFY THE SIGNIFICANT FACTORS INFLUENCING CRASH SEVERITY

Abstract

Identifying cases in which road crashes result in fatality or injury of drivers may help improve their safety. In this study, datasets of crashes happened in TehranQom freeway, Iran, were examined by three models (multiple logistic regression, Bayesian logistic and classification tree) to analyse the contribution of several variables to fatal accidents. For multiple logistic regression and Bayesian logistic models, the odds ratio was calculated for each variable. The model which best suited the identification of accident severity was determined based on AIC and DIC criteria. Based on the results of these two models, rollover crashes (OR = 14.58, %95 CI: 6.8-28.6), not using of seat belt (OR = 5.79, %95 CI: 3.1-9.9), exceeding speed limits (OR = 4.02, %95 CI: 1.8-7.9) and being female (OR = 2.91, %95 CI: 1.1-6.1) were the most important factors in fatalities of drivers. In addition, the results of the classification tree model have verified the findings of the other models.

Keywords

• Bayesian logistic
• Classification tree
• Injury severity
• Multiple logistic regression
• Traffic crash