Application of Random-parameter Negative Binomial Model to Examine the Relationship between the Severity of Traffic Accident

Abstract

Traffic accident injury is the eighth leading cause of death in the world, which seriously affects economic development and life stability. In order to explore the influencing factors of the severity of major road traffic accidents in China, potential influencing factors were selected from the statistical data of 366 major accidents. Fixed-parameter and random-parameter negative binomial model were respectively used to build models for accidents data. The results show that geographical zone, time and date of accident, road administrative grade, season, accident type, road alignment and number of traffic violation behavior are significantly related to the accident severity. Strict management of drivers is an effective way to improve the degree of accident injury.