基于统计与假设检验的高速公路交通事故数据分布特性

孟祥海; 覃薇; 霍晓艳

doi:10.19818/j.cnki.1671-1637.2018.01.013

基于统计与假设检验的高速公路交通事故数据分布特性

doi: 10.19818/j.cnki.1671-1637.2018.01.013

1.
哈尔滨工业大学交通科学与工程学院, 黑龙江哈尔滨 150090
2.
广西交通规划勘察设计研究院有限公司, 广西南宁 530000

基金项目:

国家自然科学基金项目 51329801

广东省交通运输厅科技项目 2012-01-001-02

辽宁省交通厅科技项目 201306

详细信息

作者简介:
孟祥海(1969-), 男, 黑龙江海伦人, 哈尔滨工业大学教授, 工学博士, 从事道路交通安全、交通规划、交通组织与管理研究

中图分类号: U491.31
计量
- 文章访问数: 1198
- HTML全文浏览量: 193
- PDF下载量: 1130
- 被引次数: 0
出版历程
- 收稿日期: 2017-08-13
- 刊出日期: 2018-02-25

Distribution characteristics of traffic crash data of freeway based on statistics and hypothesis test

1.
School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, Heilongjiang, China
2.
Guangxi Communications Planning Surveying and Designing Institute Co., Ltd., Nanning 530000, Guangxi, China

More Information

Author Bio:
MENGXiang-hai(1969-), male, professor, PhD, mengxianghai100@126.com

Article Text (Baidu Translation)

摘要

摘要: 为了研究高速公路基本路段上交通事故数据的分布特征, 将事故数、伤亡事故数、事故死亡人数与事故受伤人数归类为离散型事故数据, 将事故间隔时间与平均每年每公里事故数归类为连续型事故数据; 对于离散型事故数据, 采用均匀划分法、动态聚类法与滑动窗法划分高速公路统计区段, 运用泊松分布、负二项分布、零堆积泊松分布与零堆积负二项分布对事故数据进行拟合; 对于连续型事故数据, 以收费区间为路段划分标准, 用正态分布、负指数分布进行事故数据拟合; 运用皮尔逊卡方值对各种拟合结果进行拟合优度检验。研究结果表明: 在各种区段上, 事故数均服从负二项分布, 有些情况下会同时服从负二项分布与泊松分布, 伤亡事故数与事故死亡人数主要服从零堆积泊松分布或零堆积负二项分布, 拟合优度检验中的概率均大于0.05;平均每年每公里的事故数比较符合正态分布, 而事故间隔时间则主要服从负指数分布, 拟合优度检验中的概率也均大于0.05;交通事故数据的统计分布特征是建立事故预测模型与事故多发点鉴别的前提条件之一, 而事故间隔时间可作为安全可靠度的度量指标。
- 交通安全 /
- 高速公路 /
- 交通事故数据分布 /
- 拟合优度检验 /
- 离散型事故数据 /
- 连续型事故数据
Abstract: In order to analyze the distribution characteristics of traffic crash data on the basic sections of freeway, traffic crash number, fatal and injury crash number, death and injury numbers of traffic crash were taken as discrete random variables, and crash interval time and average annual crash number per kilometer were taken as continuous random variables.For discrete crash data, the sections of freeway were divided by using equally divided method, dynamic clustering method and sliding window method, and crash data were fitted by using Poisson distribution, negative binomial distribution, zero-inflated Poisson distribution and zeroinflated negative binomial distribution.For continuous crash data, the sections were divided based on the toll intervals, crash data were fitted by using normal distribution and negativeexponential distribution.The goodness-of-fit tests of various fitting results were performed by using Pearson's square.Analysis result shows that in all sections, crash numbers are subject to negative binomial distribution, and in some cases, obey negative binomial distribution and Poisson distribution at the same time.Fatal and injury crash number and death number of traffic crash mainly obey zero-inflated Poisson distribution or zero-inflated negative binomial distribution.The probabilities of goodness-of-fit test are all greater than 0.05.Average annual crash number per kilometer is more subject to normal distribution, while crash interval time mainly obeys negative exponential distribution, and the probabilities of goodness-of-fit test are also greater than 0.05.The statistical distribution characteristic of traffic crash data is one of the prerequisites for establishing crash prediction model and the identification of crash black spots, and crash interval time can be used as the measurement indicator of safety reliability.
- traffic safety /
- freeway /
- distribution of traffic crash data /
- goodness-of-fit test /
- discrete crash data /
- continuous crash data

HTML全文

图 1 定长法与滑动窗法的划分原理

Figure 1. Division principles of equal-length and sliding window methods

下载: 全尺寸图片幻灯片

图 2 事故间隔时间的实际频数与理论频数

Figure 2. Actual and theoretical frequencies of crash interval times

下载: 全尺寸图片幻灯片

表 1 数据汇总

Table 1. Summary of data

下载: 导出CSV

表 2 参数估计结果

Table 2. Parameter estimation results

下载: 导出CSV

表 3 区段划分结果

Table 3. Section division results

下载: 导出CSV

表 4 区段上事故数的统计分布

Table 4. Statistical distributions of crash numbers on sections

下载: 导出CSV

表 5 区段上事故数统计分布拟合优度检验

Table 5. Goodness-of-fit test of statistical distributions of crash numbers on sections

下载: 导出CSV

表 6 事故数理论分布的拟合优度检验

Table 6. Goodness-of-fit test of theoretical distributions of crash numbers

下载: 导出CSV

表 7 聚类后区段上事故数的统计分布

Table 7. Statistical distribution of crash number on clustered sections

下载: 导出CSV

表 8 聚类后区段上事故数统计分布拟合优度检验

Table 8. Goodness-of-fit test of statistical distributions of crash numbers on clustered sections

下载: 导出CSV

表 9 滑动窗划分区段上事故数的统计分布

Table 9. Statistical distributions of crash numbers on sections divided by sliding window method

下载: 导出CSV

表 10 滑动窗划分区段上事故数统计分布拟合优度检验

Table 10. Goodness-of-fit test of statistical distributions of crash numbers on sections divided by sliding window method

下载: 导出CSV

表 11 受伤事故数的统计分布

Table 11. Statistical distribution of injury crash number

下载: 导出CSV

表 12 受伤事故数统计分布拟合优度检验

Table 12. Goodness-of-fit test of statistical distribution of injury crash number

下载: 导出CSV

表 13 死亡事故数的统计分布

Table 13. Statistical distribution of fatal crash number

下载: 导出CSV

表 14 死亡事故数统计分布拟合优度检验

Table 14. Goodness-of-fit test of statistical distribution of fatal crash number

下载: 导出CSV

表 15 死亡人数的统计分布

Table 15. Statistical distributions of death numbers

下载: 导出CSV

表 16 死亡人数统计分布拟合优度检验

Table 16. Goodness-of-fit test of statistical distributions of death numbers

下载: 导出CSV

表 17 平均事故数的统计分布

Table 17. Statistical distribution of average crash numbers

下载: 导出CSV

表 18 事故间隔时间的统计分布

Table 18. Statistical distribution of crash interval times

下载: 导出CSV

表 19 事故间隔时间理论分布的拟合优度检验

Table 19. Goodness-of-fit test of theoretical distributions of crash interval times

下载: 导出CSV

参考文献(25)

[1]	ZHENG Lai, ISMAIL K, MENG Xiang-hai. Traffic conflict techniques for road safety analysis: open questions and some insights[J]. Canadian Journal of Civil Engineering, 2014, 41 (7): 633-641. doi: 10.1139/cjce-2013-0558
[2]	VISTISEN D. Models and methods for hot spot safety work[D]. Copenhagen: Technical University of Denmark, 2002.
[3]	JOVANOVICD, BACKALIC T, BASIC S. The application of reliability models in traffic accident frequency analysis[J]. Safety Science, 2011, 49 (8): 1246-1251.
[4]	BACKALIC S, JOVANOVIC D, BACKALIC T. Reliability reallocation models as a support tools in traffic safety analysis[J]. Accident Analysis and Prevention, 2014, 65: 47-52. doi: 10.1016/j.aap.2013.12.004
[5]	孟祥海, 覃薇, 邓晓庆. 基于神经网络的山岭重丘区高速公路事故预测模型[J]. 公路交通科技, 2016, 33 (3): 102-108. doi: 10.3969/j.issn.1002-0268.2016.03.017 MENG Xiang-hai, QIN Wei, DENG Xiao-qing. An accident prediction model for expressways in mountainous and rolling areas based on neural network[J]. Journal of Highway and Transportation Research and Development, 2016, 33 (3): 102-108. (in Chinese). doi: 10.3969/j.issn.1002-0268.2016.03.017
[6]	袁伟, 付锐, 郭应时, 等. 道路交通事故死亡人数预测模型[J]. 交通运输工程学报, 2007, 7 (4): 112-116. doi: 10.3321/j.issn:1671-1637.2007.04.023 YUAN Wei, FU Rui, GUO Ying-shi, et al. Prediction model of death toll resulted from road traffic accidents[J]. Journal of Traffic and Transportation Engineering, 2007, 7 (4): 112-116. (in Chinese). doi: 10.3321/j.issn:1671-1637.2007.04.023
[7]	李淑庆, 彭囿朗, 肖莉英, 等. 道路交通事故发生机理研究现状与趋势分析[J]. 安全与环境学报, 2014, 14 (3): 14-19. https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201403005.htm LI Shu-qing, PENG You-lang, XIAO Li-ying, et al. Analysis of the mechanism of the road traffic accidents in-situ and the future research trends[J]. Journal of Safety and Environment, 2014, 14 (3): 14-19. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201403005.htm
[8]	LORD D, WASHINGTON S P, IVAN J N. Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory[J]. Accident Analysis and Prevention, 2005, 37 (1): 35-46. doi: 10.1016/j.aap.2004.02.004
[9]	ZENG Qiang, HUANG He-lai. Bayesian spatial joint modeling of traffic crashes on an urban road network[J]. Accident Analysis and Prevention, 2014, 67 (0): 105-112.
[10]	黄合来, 许鹏鹏, 马明, 等. 道路交通安全规划理论研究前沿[J]. 中国公路学报, 2014, 27 (9): 90-97, 118. doi: 10.3969/j.issn.1001-7372.2014.09.012 HUANG He-lai, XU Peng-peng, MA Ming, et al. Recent theoretical researches on transportation safety planning[J]. China Journal of Highway and Transport, 2014, 27 (9): 90-97, 118. (in Chinese). doi: 10.3969/j.issn.1001-7372.2014.09.012
[11]	马壮林, 邵春福, 胡大伟, 等. 高速公路交通事故起数时空分析模型[J]. 交通运输工程学报, 2012, 12 (2): 93-99. doi: 10.3969/j.issn.1671-1637.2012.02.015 MA Zhuang-lin, SHAO Chun-fu, HU Da-wei, et al. Temporal-spatial analysis model of traffic accident frequency on expressway[J]. Journal of Traffic and Transportation Engineering, 2012, 12 (2): 93-99. (in Chinese). doi: 10.3969/j.issn.1671-1637.2012.02.015
[12]	王雪松, 宋洋, 黄合来, 等. 基于分层负二项模型的城郊公路安全影响因素研究[J]. 中国公路学报, 2014, 27 (1): 100-106. doi: 10.3969/j.issn.1001-7372.2014.01.014 WANG Xue-song, SONG Yang, HUANG He-lai, et al. Analysis of risk factors for suburban highways using hierarchical negative binomial model[J]. China Journal of Highway and Transport, 2014, 27 (1): 100-106. (in Chinese). doi: 10.3969/j.issn.1001-7372.2014.01.014
[13]	ABDEL-ATY M A, RADWAN A E. Modeling traffic accident occurrence and involvement[J]. Accident Analysis and Prevention, 2000, 32 (5): 633-642. doi: 10.1016/S0001-4575(99)00094-9
[14]	SHANKAR V, MANNERING F, BARFIELD W. Effect of roadway geometrics and environmental factors on rural freeway accident frequencies[J]. Accident Analysis and Prevention, 1995, 27 (3): 371-389. doi: 10.1016/0001-4575(94)00078-Z
[15]	QUDDUS M A. Modeling area-wide count outcomes with spatial correlation and heterogeneity: an analysis of London crash data[J]. Accident Analysis and Prevention, 2008, 40 (4): 1486-1497. doi: 10.1016/j.aap.2008.03.009
[16]	AMOROS E, MARTIN J L, LAUMON B. Comparison of road crashes incidence and severity between some French counties[J]. Accident Analysis and Prevention, 2003, 35 (4): 537-547. doi: 10.1016/S0001-4575(02)00031-3
[17]	CHANG Li-yen. Analysis of freeway accident frequencies: negative binomial regression versus artificial neural network[J]. Safety Science, 2005, 43 (8): 541-557.
[18]	SHANKAR V, MILTON J, MANNERING F. Modeling accident frequencies as zero-altered probability processes: an empirical inquiry[J]. Accident Analysis and Prevention, 1997, 29 (6): 829-837. doi: 10.1016/S0001-4575(97)00052-3
[19]	DONG Chun-jiao, RICHARDS S H, CLARKE D B, et al. Examining signalized intersection crash frequency using multivariate zero-inflated Poisson regression[J]. Safety Science, 2014, 70: 63-69. doi: 10.1016/j.ssci.2014.05.006
[20]	LORD D, WASHINGTON S, IVAN J N. Further notes on the application of zero-inflated models in highway safety[J]. Accident Analysis and Prevention, 2007, 39 (1): 53-57. doi: 10.1016/j.aap.2006.06.004
[21]	LEE J, MANNERING F. Impact of roadside features on the frequency and severity of run-off-roadway accidents: an empirical analysis[J]. Accident Analysis and Prevention, 2002, 34 (2): 149-161. doi: 10.1016/S0001-4575(01)00009-4
[22]	KUMARA S S P, CHIN H C. Modeling accident occurrence at signalized tee intersections with special emphasis on excess zeros[J]. Traffic Injury Prevention, 2003, 4 (1): 53-57. doi: 10.1080/15389580309852
[23]	阚伟生. 路侧事故预测模型的统计分析方法研究[J]. 道路交通与安全, 2006, 6 (12): 18-21. https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA200612005.htm KAN Wei-sheng. Statistical analysis method of roadside accidents prediction model[J]. Road Traffic and Safety, 2006, 6 (12): 18-21. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA200612005.htm
[24]	郑来, 何莎莉. 高速公路大区段交通事故预测模型研究[J]. 公路交通科技, 2017, 34 (7): 108-114. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201707015.htm ZHENG Lai, HE Sha-li. Study on traffic accident prediction model for long sections of expressway[J]. Journal of Highway and Transportation Research and Development, 2017, 34 (7): 108-114. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201707015.htm
[25]	DONG Ni, HUANG He-lai, ZHANG Liang. Support vector machine in crash prediction at the level of traffic analysis zones: assessing the spatial proximity effects[J]. Accident Analysis and Prevention, 2015, 82: 192-198.