高速公路追尾事故严重程度影响因素异质性分析  

Analysis on the heterogeneity of factors influencing the rear-end crash severity on highways

作　　者：苑仁腾 王晨竹 项乔君[1,2] Yuan Renteng;Wang Chenzhu;Xiang Qiaojun(School of Transportation,Southeast University,Nanjing 211189,China;Jiangsu Key Laboratory of Urban ITS,Southeast University,Nanjing 211189,China)

机构地区：[1]东南大学交通学院,南京211189 [2]东南大学江苏省城市智能交通重点实验室,南京211189

出　　处：《东南大学学报（自然科学版）》2024年第5期1231-1238,共8页Journal of Southeast University：Natural Science Edition

基　　金：国家自然科学基金资助项目(52372323);江苏省研究生科研与实践创新计划资助项目(KYCX22_0270).

摘　　要：为了探索白天和夜晚高速公路追尾事故严重程度致因机理的差异性,构建了具有均值异质性的相关随机参数有序Probit(CROPHM)模型,用以捕捉未被观测的异质性和解释随机因素之间的关联性.从2012—2018年山西省高速事故数据集中提取出8664起追尾事故,以时间变量、环境变量和事故属性为输入指标,并以追尾事故的最大受伤等级为输出指标,分别探索了影响白天和夜晚追尾事故严重程度的影响因素.首先,利用似然比(LR)检验证明了分别针对白天和夜晚追尾事故严重程度单独建模的必要性;然后,构建了2个CROPHM模型,用以比较追尾事故严重程度致因因素在不同时段的差异性;最后,通过边际效用分析提出了相应的改善建议.研究结果表明:相较于18:00—24:00,凌晨00:00—06:00发生追尾事故会导致致死事故的概率增加0.0637;相比于单车事故,夜间发生多车追尾事故时,致死事故的概率增加0.0156;当追尾事故中涉及大型车辆时,无论是白天还是夜晚,发生致死事故的概率均显著增加.To explore the differences in the mechanisms leading to highway rear-end crash severity during daytime and nighttime,the correlated random parameter order Probit model with heterogeneity-in-means(CROPHM)was constructed to capture unobserved heterogeneity and explain the correlation between random parameters.A sample of 8664 highway rear-end crashes was extracted from 2012—2018 Shanxi highway accidents dataset.With time variables,environmental variables and accident attributes as input indicators and the maximum injury severity as the output variable,the factors influencing the severity of rear-end crashes during the daytime and nighttime were explored separately.Firstly,likelihood ratio(LR)tests were conducted to validate whether rear-end crashes classified by daytime and nighttime should be modeled separately.Subsequently,two CROPHM models were established to examine the temporal differences in factors influencing the rear-end crash severity.Finally,through marginal effect analysis,corresponding recommendations were presented.The study findings indicate that rear-end crashes between 00:00 and 06:00 significantly increase the probability of fatal accidents by 0.0637 compared with 18:00—24:00.Moreover,the probability of fatal crashes increases by 0.0156 during nighttime multi-vehicle rear-end collisions compared with single-vehicle crashes.When large vehicles are involved in rear-end collisions,the probability of fatal accidents significantly increases,both during the daytime and nighttime.

关 键 词：交通工程 交通安全 追尾事故严重程度 异质性 有序PROBIT模型 

分 类 号：U491[交通运输工程—交通运输规划与管理]