Analysis of driver injury severity in truck-involved accidents using a non-parametric classification tree model

Abstract

To explore the factors contributing to driver injury severity in traffic accidents, parametric regression models, such as multinomial logit models (MNLs) or ordered probabilistic regression models, have been commonly applied for many years. However, these parametric models have their own model assumptions and pre-defined underlying relationships between dependent and independent variables. If these assumptions are violated, the models can lead to erroneous estimation of the injury likelihood. This study collects the 2005–2006 truck-involved accident data from national freeways in Taiwan and develops a non-parametric Classification and Regression Tree (CART) model to establish the empirical relationship between injury severity outcomes and driver/vehicle characteristics, highway geometric variables, environmental characteristics, and accident variables. The results show that drinking-driving, seatbelt use, vehicle type, collision type, contributing circumstance and driver/vehicle action, number of vehicles involved in the accident and accident location were the key determinants of injury severity outcomes for truck accidents.