论文标题
贝叶斯矢量对宏观经济和运输对城市交通事故影响的自动回归分析
Bayesian vector autoregressive analysis of macroeconomic and transport influences on urban traffic accidents
论文作者
论文摘要
城市交通安全的宏观影响因素分析对于指导城市发展方向以减少交通事故的频率很重要。在这项研究中，开发了一种贝叶斯矢量自回旋（BVAR）模型，以探索六个宏观级别的经济和运输因素的影响，包括人口，GDP，私家车拥有，公共汽车所有权，地铁铁路行驶里程和道路平均速度对北京少量样本量运输数据的交通事故对交通事故的影响。结果表明，BVAR模型适用于小样本情况下交通事故的时间序列分析。在宏观经济因素中，从长远来看，GDP的增长被认为可以减少交通事故的数量，而人口增长对短期交通事故产生了积极影响。就宏观交通因素而言，人们认为，道路平均速度和私有车辆的所有权在长期内增加了交通事故，而公共汽车所有权和地铁铁路行驶里程具有长期的负面影响，对道路平均速度产生了最大的积极影响，并且对地铁路线的负面影响最大。这项研究表明，政府部门可以通过增加对公共交通基础设施的投资，限制私人车辆和道路速度来减少交通事故的数量。
The macro influencing factors analysis of urban traffic safety is important to guide the direction of urban development to reduce the frequency of traffic accidents. In this study, a Bayesian vector autoregressive(BVAR) model was developed to exploring the impact of six macro-level economic and transport factors, including population, GDP, private vehicle ownership, bus ownership, subway rail mileage and road average speed on traffic accidents with the small sample size transport annual report data in Beijing. The results show that the BVAR model was suitable for time series analysis of traffic accidents in small sample situations. In macroeconomic factors, GDP growth was considered to reduce the number of traffic accidents in the long term, while population growth had a positive effect on traffic accidents in the short term. With the respect to macro-transport factors, road average speed and private vehicle ownership was perceived to increase traffic accidents in long duration, whereas bus ownership and subway rail mileage had long-term negative effects, with the greatest positive effect for road average speed and the greatest negative effect for subway rail mileage. This study suggests that government departments can reduce the number of traffic accidents by increasing investment in public transportation infrastructures, limiting private vehicles and road speed.
