基于统计及假设检验的高速公路事故多发点分析  

Analysis of black spot for freeway based on both statistics and hypothesis testing

作　　者：孟祥海[1] 覃薇[1] MENG Xianghai QIN Wei(School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin Heilongjiang 150090, China)

机构地区：[1]哈尔滨工业大学交通科学与工程学院

出　　处：《中国安全科学学报》2017年第5期158-163,共6页China Safety Science Journal

基　　金：国家自然科学基金资助(51329801);广东省交通运输厅科技项目(2012-2013);辽宁省交通科技项目(201306)

摘　　要：为鉴别高速公路基本路段上的事故多发点,识别其突出事故影响因素,首先应用统计分布拟合及假设检验等方法,分析事故起数的统计分布特征;然后提出确定临界事故起数及路段划分长度的方法,分析滑动窗口法与定长法的异同;最后基于二项分布检验法,给出事故影响因素的概率计算公式及突出事故影响因素识别方法。研究结果表明:高速公路基本路段上的事故起数服从负二项分布;应用负二项分布理论来确定路段划分长度具有一定的可行性;滑动窗口法虽有夸大事故多发点数量的倾向,但确实能反映事故的集疏程度。案例分析也表明,可应用二项分布检验法来识别事故多发点的突出事故影响因素。In order to identify the black spots of freeway＇s basic segment and recognize the crash contributing factors,statistical distribution fitting and hypothesis testing were used to analyze the statistical distribution of crashes.Methods of critical crashes number determination and segment division were provided.Similarities and differences between the sliding window method and the equal-length division method were analyzed,and then probability formulas and an identification method of crash contributing factors which based on binomial test methods were given.The results showed that the crashes on freeway basic segments fit the negative binomial distribution,that the segment division method which based on negative binomial distribution is reliable,and taht although the sliding window method has a tendency to exaggerate the number of black spots,it does reflect the intensity of crashes.Case study also showed that crash contributing factors of black spots can be identified by the binomial test method.

关 键 词：交通安全 高速公路 事故多发点分析 负二项分布 二项分布检验 突出事故影响因素 

分 类 号：X928.03[环境科学与工程—安全科学]