Development of a model for determining the traffic accident black spots based on Geographical Information Systems (GIS) aided spatial statistical methods

Traffic accidents are one of the important problems in our country as it in the world. The World Health Organization case reports published in 2015 is stated that about 1.25 million people died each year and more than 50 million people injured as a result of traffic accidents in the World. Considering this situation, it is seen that the traffic accidents are human origin and one of the major problems that is negatively affecting life. In this context, many investments and many studies performed to reduce traffic accidents. The thesis takes into account a variety of reasons in order to determine traffic accident black spot. It is aimed to get a descriptive model for determining the traffic accident black spots by using model-based spatial statistical methods. These methods are accident rate, accident frequency, accident severity, Getis Ord Gi *, Moran's I, Poisson regression, Negative Binomial regression and empirical Bayesian method. The ultimate aim of this study is to build a model that allows evaluating all the methods together in Geographic Information Systems (GIS) which is now quite widely in use. In this study, 300 thousand traffic accident data of 2408 different state road covering the years 2005-2013 obtained from General Directorate of Highways. State roads are divided into 32107 sub-segments that all is 1km. depending on the methods are used in the study, 126 sub-segment are decided as traffic accident black spots. According to comparison of the methods used in the study, the Empirical Bayesian method is giving better results than other methods.