Road Accident Models with Two Threshold Levels of Fuzzy Linear Regression

It has been hypothesized that number of road accidents and road casualties are increased in line with the raise in the variables of registered vehicles, population and road length. However, the effects of these variables toward road accidents are still inconclusive. Therefore, this paper develops models based on the variables which can be used to determine road accidents in Malaysia. In order to explain the effects of these variables to number of road accidents, fuzzy linear regression models with threshold level 0.5 and 0.9 are tested. Historical data of the variables from the year 1974 to 2007 were collected to test the model. The results show that by applying a multi-variable approach of fuzzy linear regression, the models provide not only crisp output but also output range for number of road accidents in Malaysia. The model with threshold level 0.5 outperformed the latter model. The variables of registered vehicles and population were notable predictors to number of road accidents in Malaysia.