Methodological development for selection of significant predictors explaining fatal road accidents

• The article proposes a variable selection methodology combining neural network design and statistical approaches.
• Estimation is carried out through Markov Chain Monte Carlo simulation tools.
• The variable selection methodology is applied to a parsimonious model and the estimation results are compared with those of a sophisticated dynamic regression model.
• For the empirical analysis the fatal accident data in Spain, covering the period 2000–2011, were used.
• Driver behavior surveillance, legislative measures, investment on road maintenance, vehicle characteristics, and high capacity roads are found to be the main factors that could best explain the fatal accident data.
• The proposed methodology also provides very relevant tools for future decision making in road safety policy.

Identification of the most relevant factors for explaining road accident occurrence is an important issue in road safety research, particularly for future decision-making processes in transport policy. However model selection for this particular purpose is still an ongoing research. In this paper we propose a methodological development for model selection which addresses both explanatory variable and adequate model selection issues. A variable selection procedure, TIM (two-input model) method is carried out by combining neural network design and statistical approaches. The error structure of the fitted model is assumed to follow an autoregressive process. All models are estimated using Markov Chain Monte Carlo method where the model parameters are assigned non-informative prior distributions. The final model is built using the results of the variable selection. For the application of the proposed methodology the number of fatal accidents in Spain during 2000–2011 was used. This indicator has experienced the maximum reduction internationally during the indicated years thus making it an interesting time series from a road safety policy perspective. Hence the identification of the variables that have affected this reduction is of particular interest for future decision making. The results of the variable selection process show that the selected variables are main subjects of road safety policy measures.