Abstract
China's rapid urbanization and high traffic accident frequency have received many researchers’ attention. It is important to reveal how urban infrastructures and other risk factors affects the traffic accident frequency. A growing amount of research has examined the local risk factors impact on traffic accident frequency at certain time. Some studies considered these spatial influences but overlooked the temporal correlation/heterogeneity of traffic accidents and related risk factors. This study explores risk factors’ influence on urban traffic accidents frequency while considering both the spatial and temporal correlation/heterogeneity of traffic accidents. The study area is split into 100 equally sized rectangle traffic analysis zones (TAZs), and the urban traffic accident frequency and attributes in each TAZ are extracted. The linear regression model, spatial lag model (SLM), spatial error model (SEM) and time-fixed effects error model (T-FEEM) are established and compared respectively. The proposed methodologies are illustrated using ten-month traffic accident data from the urban area of Guiyang City, China. The results reveal that the time-fixed effects error model, which considers both spatial and temporal correlation/heterogeneity of traffic accidents, is superior to other models. More traffic accidents will happen in those TAZs that have more hospitals or schools. Moreover, hospitals have a greater influence on traffic accidents than schools. Because of the location in the margin of the city, those TAZs that have passenger stations have more traffic accidents. This study provides policy makers with more detailed characterization about the impact of related risk factors on traffic accident frequencies, and it is suggested that not only the spatial correlation/heterogeneity but also the temporal correlation/heterogeneity should be taken into account in guiding traffic accident control of urban area.
Highlights
In the field of transportation, the road traffic accident is a critical problem that urban road traffic must face
The objective of this paper is to propose a framework of spatial panel time-fixed effects error model that can address spatial correlation/heterogeneity and temporal correlation/heterogeneity of traffic accidents and related risk factors
The parameter estimation of the general model is based on the least squares method, while parameter estimation of spatial lag model (SLM) and spatial error model (SEM) are the maximum likelihood estimation method
Summary
In the field of transportation, the road traffic accident is a critical problem that urban road traffic must face. A total of 203,049 road traffic accidents occurred in 2017 in China, which caused 63,772 fatalities, 209,654 injuries, and direct economic loss valued at 1.21 billion yuan[2]. To reduce the occurrence of traffic accidents and the impact of traffic accidents on road traffic, it is vital to analyze the important factors that affect the occurrence of traffic accidents and to put forward the corresponding accident analyzing model. This can provide a scientific basis for traffic management to optimize the road environment, and useful information for the development of scientific traffic regulations. Some other methods, such as negative binomial regression model[9], mixed logit model[10], artificial intelligence models[11,12,13,14], osculating value method[15], computer vision method[16], have been used to analyze traffic safety and traffic management
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
