Spatial Analysis and Geographic Variation of Fatal and Injury Crashes in Mazandaran

Background: Road safety and traffi c accidents change in time and space. Although, time variations have always been considered the subject be-ing focused by researchers, the eff ect of spatial correlation and spatial components on the risk of accident have been less investigated. Due to its specifi c geographical position, Mazandaran Province is one of the highest traffi c provinces. Th is study aims to investigate the factors infl uencing suburban crashes of Mazandaran province by considering the spatial correlation. Methods: Th is study is aggregated (descriptive-analytical) and the study period was 2006 to 2010. Social and environmental factors eff ects on the risk of accidents have been studied considering the correlation structure of the regions and regardless of this structure with Poisson regression, negative binomial and Full Bayes hierarchical models. Geographical pattern of risk distribution for the observed values of SMRs and the estimated values aft er smoothing have been plotted and analyzed. Results: Comparing the measures of models goodness of fi t indicates that hierarchical Bayes model fi ts the data better. Plotting the geographical pattern, the north central parts of the province have been identifi ed as the high-risk areas. Human factors were identifi ed as the important factors for the risk of accident. Conclusions: Th e purpose of this procedure is to separate the random eff ect of residuals correlation. Using this method, the mea