A SEGMENTATION METHOD FOR REGRESSION ANALYSIS OF ACCIDENT RATES WITH RANDOM ERRORS

Bibliographic Information

Other Title
  • 偶然誤差を考慮した事故率分析の区間設定方法
  • グウゼン ゴサ オ コウリョシタ ジコリツ ブンセキ ノ クカン セッテイ ホ

Search this article

Description

A traffic accident is a stochastic event and observed accident rates contains random errors that deteriorate the explanatory power and rthe eliability of the regression analysis. Random errors have to be appropriately controlled. When a data set of accident records, traffic records and geometric design elements of a certain stretch of a road is given, there are two steps for regression analysis: first, division of the road into a number of segments; and second, application of regression analysis to the set of segments. The main interest of this paper is the first step. The paper discusses how to evaluate random errors contained in accident rates of segments and what influence the random errors have on the regression. A segmentation method is proposed and examined by numerical examples of Tokyo-Kobe Expressway.

Journal

References(2)*help

See more

Details 詳細情報について

Report a problem

Back to top