The paper i concerned with linear multiregression analysis on accident rates related to road geometric design elements. Supposing that a data set of accident 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 the present paper is the first step. Occurrence of a traffic accident in a road segment is a stochastic event and an observed accident rate in a segment contains a certain magnitude of random error that deteriorates the explanatory power and reliability of the regression analysis. Random errors are required to beappropriately controlled for an effective regression analysis. The first part of the paper discusses how to evaluate a random error contained in an accident rate of a road segment and shows that a randomerror depends on the number of accidents and vehicle kilometerage of the segment. It is then shown that random errors of the segments should be as much as possible equal to each other and small enough compared with the accident rate variance based on the discussion of how the random errors affect the efficiency of regression analysis. several alternative criteria on the random errors for dividing a road into segments are proposed and numerical examples of tokyo-kobe expressway are presented to examine the appropriateness of the alternative criteria. One of them is finally recommended as the most practically useful criterion. (a).
Samenvatting