Statistically modelling relationships between accident types and highway features

Although in recent years considerable progress has been made to establish relationships between accidents and highway characteristics, no specific accident models are widely accepted by the highway engineering agencies. Four commonly used models are developed in this study, that is, two conventional linear regression models and two Poisson models. Accident data monitored by the National Freeway Bureau in Taiwan are used to model statistically relationships between accident types and highway features. Traditional models are demonstrated to possess unsatisfactory statistical properties that cannot adequately describe discrete, non-negative, random and sporadic accident events along a highway. Based upon statistic estimates, the Poisson models are shown to be more appropriate, accurate and reliable than the conventional linear regression models.