본문 바로가기
  • Home

A Study on Traffic Accident Model Using Random Parameters Poisson at 3-legged Non-signalized Intersections

Kim Taeho 1 Park Minho 1

1인천발전연구원

Accredited

ABSTRACT

This study aims to develop a statistical accident model at 3-legged non-signalized intersections with random parameters Poisson method to find the elements affecting traffic accident frequencies. Meanwhile, non-signalized intersections have been treated relatively poorly compared to signalized intersections, which result in fewer studies than signalized intersections. In addition, the previous count models with fixed parameters are not enough to explain the integrated variations in terms of spatial-temporal characteristics road segments or points have. This drawback of the traditional count models results in the underestimation of the standard error of the derived coefficient and finally affects the low reliability of the derived model. To diminish this problem, this study uses the random parameters which take into account the heterogeneity of all the observations. As a result of the analysis, 13 variables were found to have statistically significant variables, 10 variables of which were found to have fixed parameters, and 3 variables (# of entrance/exit on major road, Existence of pedestrian crossing on minor road, and Existence of median barrier on major road) were found to have random parameters indicating the effects on accident frequencies could be varied at each intersection.

Citation status

* References for papers published after 2022 are currently being built.