Citation

Rengarasu TM, Hagiwara T, Hirasawa M. J. East Asia Soc. Transp. Stud. 2010; 8: 2187-2200.

Copyright

(Copyright © 2010, Eastern Asia Society for Transportation Studies)

DOI

unavailable

PMID

unavailable

Abstract

This study aimed to find the effects of road geometry and cross section variables on accident frequency. The study also developed a methodology to combine variables using decision trees. Combination variables for road geometry and cross-section were developed using the Chi-squared Automatic Interaction Detection algorithm. Three Negative Binomial models were developed: two with homogeneous and one with 1-km road segments. Accuracy of Negative Binomial models developed with different road segments was compared. The Negative Binomial model using homogeneous road segments based on horizontal alignment was found to be the most accurate of the 3 models. Combination variables showed a significant effect on accident frequency. It was found that number of accidents in a road segment is influenced by the average accident rate in adjacent road segments.