Macro model for prediction of road accidents in selected northern states of India

Abstract

According to reports published by the World Bank and MoRTH, with just 1 per cent of the world s vehicles, India accounts for approx. 11 percent of the global death in road accidents, the highest in the world. With the increase in population and number of registered vehicles, road accidents are also increasing. The scenario of road accidents has become so worst that approx. 3 per cent of India s total GDP is getting waste in road accidents. newlineThe present study has been carried out to check the effect of those significant parameters contributing in road accidents in details. By collecting the data from different authentic sources, an attempt has been made to develop various Accident Predication Models (APMs) for the selected northern states of India including two plain area states namely Haryana and Punjab, two hilly area states namely Himachal Pradesh, Uttarakhand, and one union territory Chandigarh. After collecting the relevant data, three different models in terms of total accidents, persons killed and persons injured in road accidents for each states/UT have been developed using SPSS software and all models have been discussed in detail. newlineIn next stage, models were validated to ensure their predictive powers and were compared to three universal existing models namely Smeed model, Andreessen model, and Valli model to find the best one. Based on the results, it was found that the proposed models were statistically significant and could be used to predict road accidents in the respective states. In next stage, the suitability of a particular model to predict road accidents in another state was checked and based on results it was found that the developed models can be used to predict road accidents for that particular state only. At last, based on prioritization matrix, states were assigned priorities/ranks so that if limited budget is to be given in the states to improve road safety of the road users, state with first priority may be given the desired amount. newline newline