Obviously, improving the road safety and the efficient allocation of limited resources to the provinces according to their ranking should be done. This paper presents a hybrid method of multivariate statistical analysis-decision making to evaluate Iran road traffic safety. In order to solve the problems of road traffic safety, a macroscopic evaluation and traffic safety level classification in Iran was carried out. An index system which consists of 14 relative indexes for road traffic safety evaluation was established. The principal component analysis method was used to reduce the dimensions of the multi-index data. Based on this, 2 components were extracted. The Index of Road Traffic Safety (IRTS) was calculated to rank the provinces of the country. A K-means method was applied to classify the provinces. A TOPSIS technique was used to examine the status of each cluster in terms of safety levels. Results showed that there are 4 safety levels entitled good, average, weak and very weak. The levels are approximately similar to result of the rankings.