An Analysis of Vehicle Occupants’ Injury Severity in Crashes Occurred On Rural Freeways and Multilane Highways in Iran

Abstract

Vehicle occupants comprise a considerable proportion of traffic crash victims in Iran. This paper has focused on vehicle<br />occupants' injury severity and employed the Classification and Regression Tree (CART) technique in order to<br />identify the most important variables affecting the injury severity of these road users in crashes occurred on rural freeways<br />and multilane highways in Iran over a three year period (2006-2008). In the procedure adopted in this paper, the<br />problem of three-class prediction was decomposed into four binary prediction models. Results revealed a high overall<br />prediction accuracy of the models. Ten explanatory variables were considered in the current study in order to find the<br />most important variables affecting the injury severity of occupants. In this regard, some “if-then" rules pertaining to<br />the conditions that lead to more severe injuries are provided based on the decision tree analysis. Results confirm the<br />already-known importance of seatbelt usage for preventing serious injuries in one hand, and imply the insufficiency<br />of seatbelt usage for protecting the occupants from receiving serious injuries in some collision types, on the other<br />hand. This underscores the need for more safety instruments (especially airbags for all occupants of the vehicle) to be<br />installed in passenger cars in Iran.