论文信息 - Estimation of the effects of countermeasures on different types of accidents in the presence of regression effects.

Estimation of the effects of countermeasures on different types of accidents in the presence of regression effects.

In an earlier paper [Danielsson, 1986], we studied the problem of estimating the safety effect of a countermeasure on the expected number of accidents at road junctions when high-accident sites are selected for the study. Often, however, the countermeasure leads to varying effectiveness on different types of accidents. This paper is a generalization in that we estimate effects of countermeasures for each type of accident. A major result, for which empirical support is provided, is that the expected regression effect is the same for all types of accidents.

S Danielsson | S. Danielsson

[1] Bhagwant Persaud,et al. COMMON BIAS IN BEFORE-AND-AFTER ACCIDENT COMPARISONS AND ITS ELIMINATION , 1983 .

[2] U Brüde,et al. Regression-to-mean effect : Some empirical examples concerning accidents at road junctions , 1982 .

[3] Ezra Hauer,et al. Bias-by-selection: Overestimation of the effectiveness of safety countermeasures caused by the process of selection for treatment , 1980 .

[4] E Hauer,et al. On the estimation of the expected number of accidents. , 1986, Accident; analysis and prevention.

[5] E. Haver. SELECTION FOR TREATMENT AS A SOURCE OF BIAS IN BEFORE-AND-AFTER STUDIES , 1980 .

[6] S Danielsson. A comparison of two methods for estimating the effect of a countermeasure in the presence of regression effects. , 1986, Accident; analysis and prevention.