基于最优尺度Logit模型的交通事故形态致因分析

Cause analysis of traffic accident forms based on optimal scale Logit model

为剖析典型交通事故形态致因,在利用最优尺度分析法诊断交通事故形态致因共线性的基础上,筛选关键影响因素,构建无序多分类Logit交通事故致因模型并对模型进行参数标定,并选择100个交通事故样本对模型进行精度验证,该模型相对误差仅为4.0%,能够较为准确地分析典型交通事故形态致因。研究结果表明:路侧及中央隔离设施、照明是事故的保护性因子,可有效降低事故率;路侧行道树设置不合理或未及时修剪,使车辆不能有效识别道路信息,是正面碰撞的重要影响因素;机非混合道是事故的危险因子,增大了侧面碰撞事故发生概率。研究结果可为交通隐患精准识别、交通事故主动预防以及交通设施科学设计提供理论依据和技术支撑。

In order to analyze the causes of typical traffic accident forms,based on the collinearity of traffic accident forms diagnosed by the optimal scale analysis method,the key influencing factors were screened.A disordered multiple classification Logit traffic accident cause model was constructed,then the parameters of the model were calibrated,and 100 traffic accident samples were selected to verify the accuracy of the model.The relative error of the model was only 4.0%,which could accurately analyze the causes of typical traffic accident forms.The results showed that the roadside and central isolation facilities and the lighting were the protective factors of accidents,which could effectively reduce the accident rate.The roadside trees were set unreasonably or not trimmed in time,so that the vehicles could not effectively identify the road information,which was an important influencing factor of frontal collision.The mixed lane of motor vehicle and non-motor vehicle was the risk factor of accidents,which increased the probability of side collision accidents.This study provides theoretical basis and technical support for the accurate identification of traffic hazards,active prevention of traffic accidents and scientific design of traffic facilities.