J4 ›› 2013, Vol. 26 ›› Issue (4): 79-84.doi: 10.3976/j.issn.1002-4026.2013.04.017

• 交通运输专栏 • 上一篇    下一篇

基于负二项回归模型的高速公路交通事故影响因素分析

夏萍萍,魏丽英,马壮林   

  1. 1.北京交通大学交通运输学院,北京 100044; 2.长安大学汽车学院,陕西 西安 710064
  • 收稿日期:2013-01-24 出版日期:2013-08-20 发布日期:2013-08-20
  • 作者简介:夏萍萍(1989-),女,硕士研究生,研究方向为城市交通规划与管理和道路交通安全。Email:12120925@bjtu.edu.cn
  • 基金资助:

    国家自然科学基金青年基金项目(71101008);中央高校基本科研业务费专项资金(CHD2011JC112);高等学校博士学科点专项科研基金(20090009110011)

Negative binomial regression model based analysis for influential factors of expressway traffic accidents

 XIA Ping-Ping, WEI Li-Ying, MA Zhuang-Lin   

  1. 1. School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China;  2. School of Automobile, Chang’an University, Xi′an 710064, China
  • Received:2013-01-24 Online:2013-08-20 Published:2013-08-20

摘要:

        为了分析高速公路平纵线形和其他交通相关因素对交通安全的影响,从时间和空间角度选取9个自变量,构建基于负二项回归的高速公路交通事故时空分析模型。以某高速公路典型危险路段为例,进行模型拟合与检验。结果表明,基于负二项回归的高速公路交通事故时空分析模型拟合效果良好,事故率与路段弯曲比和连续下坡累积效应呈正相关,与平均坡度和大车比例呈负相关。

关键词: 交通工程, 高速公路交通事故, 负二项回归, 时空分析模型

Abstract:

       We constructed a negative binomial regression based expressway traffic accidents temporalspatial analysis model from nine independent variables in time and space domains to analyze the impacts of expressway horizontal and vertical alignments and other traffic related factors on traffic safety. We then perform model fitting and test, taking a typical dangerous expressway section as an example. Results show that the negative binomial regression based expressway traffic accidents temporalspatial analysis model has better fitting effect. Accident rate is positively relative to curve proportion and cumulative effect of continuous downhill, while negatively relative to mean gradient and large car proportion.

Key words: traffic engineering, expressway traffic accidents, negative binomial regression, temporalspatial analysis model

中图分类号: 

  • U491.3

开放获取 本文遵循知识共享-署名-非商业性4.0国际许可协议(CC BY-NC 4.0),允许第三方对本刊发表的论文自由共享(即在任何媒介以任何形式复制、发行原文)、演绎(即修改、转换或以原文为基础进行创作),必须给出适当的署名,提供指向本文许可协议的链接,同时表明是否对原文作了修改,不得将本文用于商业目的。CC BY-NC 4.0许可协议详情请访问 https://creativecommons.org/licenses/by-nc/4.0