Accident prediction models for safety evaluation of urban transportation network.

摘要

The objective of this study was to develop a series of macro-level prediction models that would estimate the number of accidents in planning zones in the City of Toronto as a function of zonal characteristics. A generalized linear modeling approach was employed in which Negative Binomial regression models were developed. Separate models were developed for total accidents and for severe (fatal and non fatal injury) accidents as a function of socioeconomic/demographic, traffic demand and network data variables. The variables, which had significant effects on accident occurrence, were the number of households, major road kilometers, vehicle kilometers traveled, intersection density, posted speed and volume-capacity ratio. In addition, the Geographic Weighted Regression approach was employed to test spatial variations in the estimated parameters from zone to zone. Mixed results were obtained from that analysis.