Suppr超能文献

巴西高速公路交通事故趋势:分数阶积分法的持续性证据。

Trends in road accidents on Brazil's highways: Evidence of persistence using fractional integration.

机构信息

Federal University of Rio de Janeiro, Rio de Janeiro, Brazil.

University of Navarra, Pamplona, Spain.

出版信息

PLoS One. 2023 Jul 13;18(7):e0287302. doi: 10.1371/journal.pone.0287302. eCollection 2023.

Abstract

This paper deals with the analysis of trends in road accidents on highways in Brazil. We use time series techniques based on fractional integration that allow us to determine if exogenous shocks in the data have transitory or permanent effects depending on the order of integration of the series. Our results indicate that a low degree of long memory was detected in the series with shocks having thus transitory effects over time. We further find that the number of accidents have been reducing over time, though in the presence of negative shocks, the recovery is not going to be immediate due to the long memory nature of the data. Despite the absence of relevant investment relating to infrastructure expansion, it is worth mentioning the consolidation of a nationwide tolled road system in Brazil involving concessions to private administrators, alongside more severe traffic laws that can impose limitations on driving licences.

摘要

本文分析了巴西高速公路交通事故的趋势。我们使用基于分数整合的时间序列技术,根据序列的整合阶数来确定数据中的外生冲击是否具有暂时性或永久性影响。我们的结果表明,在受到冲击的序列中检测到了较低程度的长期记忆,因此这些冲击具有随时间推移的暂时性影响。我们还发现,随着时间的推移,事故数量一直在减少,但在存在负冲击的情况下,由于数据的长期记忆性质,恢复不会是即时的。尽管没有与基础设施扩张相关的重要投资,但值得一提的是,巴西全国范围内的收费公路系统得到了巩固,涉及向私人管理员授予特许权,同时还实施了更严格的交通法规,这些法规可能会对驾驶执照施加限制。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7baa/10343090/23ec8b9ea581/pone.0287302.g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验