Development of Statistical Prediction Models to Reduce Fatal and Injury Traffic Accidents

Mohammad Abojaradeh, Basim Jrew

Abstract


Recent studies have shown that Jordan suffers massive human and economical losses as well as social and emotional effects from traffic accidents every year. Despite the efforts of the public and private sectors, traffic accidents are still increasing and exhaust Jordan’s resources at the price of other areas of development and construction.

The main objectives of this study are: to analyze traffic accidents in Jordan and their main causes; to reduce the number of traffic accidents and their severity. Also, to study the effect of driver behavior mistakes on traffic accidents and their severity. In addition, to determine and build prediction statistical regression models, which relates the number of accidents (dependent variable), with drivers behavior mistakes (independent variable) by using the Statistical Package for Social Sciences (SPSS) computer software.

The study was conducted based on accident data provided by the Jordan Traffic Institute from the year 2000 to year 2010. The study investigates 394188 total accidents during the period of the study with five independent variables (close following, lane violation, speeding or violation of speed limit, wrong passing and red light violation).

Regression techniques were used to analyze the collected data and to create four models .The models were developed by SPSS statistical package computer program. The first developed predicted model was for the total accident, the result indicated that the close following and lane violation are the most causes of accidents .The second developed model was for the fatal accidents, and the results indicated that the violation of speed limit and the lane violation are the most causes of the fatalities. The third and fourth models were developed for the slight and sever injuries; the result showed that the same independent variables causes of fatalities are applicable for injuries.

The accident prediction model can be used to develop warrants and standards for law enforcement, geometric design, and traffic operation and to improve the required countermeasures in order to reduce the traffic accidents especially fatal and injury accidents.

Keywords: World Health Organization, Healthcare, Fatality, Injury, Severity, Human losses, Social and Emotional Effects, Traffic Accidents, Traffic Safety, Speed Limit, Speeding, Driver Behavior, Countermeasures, Regression Models.


Full Text: PDF
Download the IISTE publication guideline!

To list your conference here. Please contact the administrator of this platform.

Paper submission email: JEES@iiste.org

ISSN (Paper)2224-3216 ISSN (Online)2225-0948

Please add our address "contact@iiste.org" into your email contact list.

This journal follows ISO 9001 management standard and licensed under a Creative Commons Attribution 3.0 License.

Copyright © www.iiste.org