In order to identify the possible contributory factors on urban road environment to accident severity, the logistic regression model was applied to traffic accident data collected from police-reports. A total of 2117 accidents occurred in Shijiazhuang in 2002 were considered for the purpose of this paper. Accident severity (dependent variable) in this paper is a dichotomous variable with two categories: extra serious or major accident and ordinary or minor accident. Because of the binary nature of this dependent variable, the logistic regression model was found suitable. Of nine independent variables obtained from police-reports, five were found most significant associated with accident severity, namely, road cross-section, accident location, road alignment, road type and lighting condition. A statistical interpretation is given of the model-developed estimates in terms of odds ratio concept. The findings show that the logistic regression model as used in this paper provides a better understanding of risk factors related to urban road environment.
Analysis of the logistic model for accident severity on urban road environment
2009 IEEE Intelligent Vehicles Symposium ; 983-987
2009-06-01
634094 byte
Conference paper
Electronic Resource
English
Analysis of the Logistic Model for Accident Severity on Urban Road Environment
British Library Conference Proceedings | 2009
|An Analysis of Pedestrian Fatal Accident Severity Using a Binary Logistic Regression Model
Online Contents | 2012
|Correlation Analysis of Traffic Accident Severity of the Heavy Trucks Based on Logistic Model
British Library Conference Proceedings | 2023
|Using logistic regression to estimate the influence of accident factors on accident severity
Online Contents | 2002
|Correlation Analysis of Traffic Accident Severity of the Heavy Trucks Based on Logistic Model
Springer Verlag | 2022
|