1. Introduction
The World Health Organization (WHO) considers that traffic accidents are major public health problem worldwide that every year claiming 1.27 million annual deaths and between 20 and 50 million injuries [1]. For this reason, many safety researchers have attempted to identify affecting the severity as consequence of road accidents.
Different techniques, such as: Regression-type generalized linear models, Logit/Probit models, ordered Logit/Probit models have been used to achieve these objectives [2, 3, 4].
However most of these models have their own model assumptions and pre-defined underlying relationships between dependent and independent variables [5]; if these assumptions are violated, the model could lead to erroneous estimations, for example of the likelihood of severity accident.
An error occurred while printing.