Factors related to highway crash severity in Brazil through a multinomial logistic regression model

Detalhes bibliográficos
Autor(a) principal: Franceschi, Lucas
Data de Publicação: 2022
Outros Autores: Kaesemodel, Luciano, Vargas, Vera do Carmo Comparsi de, Konrath, Andréa Cristina, Nakamura, Luiz Ricardo, Ramires, Thiago Gentil, Barreto, Camila Belleza Maciel, Valente, Amir Mattar
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFLA
Texto Completo: http://repositorio.ufla.br/jspui/handle/1/54375
Resumo: Reducing the number of deaths by road crashes is an important priority for many countries around the world. Although focusing on the occurrence of crashes can provide safety policies that help reduce its numbers, studying their severity can provide different measures that may help further reduce the number of deaths by focusing on the most severe problems first. In this paper, a mul.nomial logis.c regression model is fi:ed to na.onwide highway crash data in Brazil from 2017 to 2019 to iden.fy and es.mate the associated factors to crash severity. Severity is classified as without injury, with injured vic ms or with fatal vic ms. Amongst other observa.ons, results indicate that pedestrian involvement in highway crashes increase drama.cally their severity. Also, condi.ons that favor greater speeds (clear weather, .mes when there are fewer vehicles on the road) are also related to an increase in crash severity, poin.ng to a propor.onal rela.on with traffic fluidity. Moreover, some observed limita.ons on the data may indicate that Brazil would benefit greatly from na.onal crash records standards and unified databases, especially crossmatching crash reports with health data.
id UFLA_8b0910eca10be6fb470a6939ee3ab64a
oai_identifier_str oai:localhost:1/54375
network_acronym_str UFLA
network_name_str Repositório Institucional da UFLA
repository_id_str
spelling Factors related to highway crash severity in Brazil through a multinomial logistic regression modelFatores relacionados à severidade de acidentes em rodovias no Brasil através de um modelo de regressão logística multinomialRoad transportationInjury severityStatistical learningHighway crashesTraffic safetyTransporte rodoviárioSeveridade de acidentesAprendizagem estatísticaAcidentes em rodoviasSegurança viáriaReducing the number of deaths by road crashes is an important priority for many countries around the world. Although focusing on the occurrence of crashes can provide safety policies that help reduce its numbers, studying their severity can provide different measures that may help further reduce the number of deaths by focusing on the most severe problems first. In this paper, a mul.nomial logis.c regression model is fi:ed to na.onwide highway crash data in Brazil from 2017 to 2019 to iden.fy and es.mate the associated factors to crash severity. Severity is classified as without injury, with injured vic ms or with fatal vic ms. Amongst other observa.ons, results indicate that pedestrian involvement in highway crashes increase drama.cally their severity. Also, condi.ons that favor greater speeds (clear weather, .mes when there are fewer vehicles on the road) are also related to an increase in crash severity, poin.ng to a propor.onal rela.on with traffic fluidity. Moreover, some observed limita.ons on the data may indicate that Brazil would benefit greatly from na.onal crash records standards and unified databases, especially crossmatching crash reports with health data.Reduzir o número de mortes por acidentes de trânsito é uma prioridade importante ao redor do mundo. O estudo da severidade dos acidentes pode melhorar as políticas públicas de segurança viária, concentrando esforços nas situações associadas a acidentes de maior severidade. Neste artigo, um modelo de regressão logística multinomial é ajustado a dados de acidentes em rodovias federais no Brasil de 2017 a 2019 para estimar os fatores associados à severidade dos acidentes. A severidade é classificada como sem lesão, com vítimas feridas ou com vítimas fatais. O envolvimento de pedestres é o principal fator identificado para aumento da severidade. Além disso, condições que favorecem maiores velocidades (como tempo limpo ou horários com menos tráfego) também estão associadas com maiores severidades. Em relação ao mês, as chances de maior severidade são menores no início do ano e maiores em agosto e em novembro. As limitações observadas indicam que o Brasil carece da adoção de padrões nacionais de registro de acidentes e de bancos de dados unificados, especialmente comparando registros de acidentes rodoviários com bancos de dados de saúde.Associação Nacional de Pesquisa e Ensino em Transportes (ANPET)2022-08-29T16:51:14Z2022-08-29T16:51:14Z2022-04-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfFRANCESCHI, L. et al. Factors related to highway crash severity in Brazil through a multinomial logistic regression model. Transportes, [S.l.], v. 30, n. 1, p. 1-16, 2022. DOI: 10.14295/transportes.v30i1.2566.http://repositorio.ufla.br/jspui/handle/1/54375Transportesreponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessFranceschi, LucasKaesemodel, LucianoVargas, Vera do Carmo Comparsi deKonrath, Andréa CristinaNakamura, Luiz RicardoRamires, Thiago GentilBarreto, Camila Belleza MacielValente, Amir Mattareng2023-05-19T18:50:00Zoai:localhost:1/54375Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2023-05-19T18:50Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false
dc.title.none.fl_str_mv Factors related to highway crash severity in Brazil through a multinomial logistic regression model
Fatores relacionados à severidade de acidentes em rodovias no Brasil através de um modelo de regressão logística multinomial
title Factors related to highway crash severity in Brazil through a multinomial logistic regression model
spellingShingle Factors related to highway crash severity in Brazil through a multinomial logistic regression model
Franceschi, Lucas
Road transportation
Injury severity
Statistical learning
Highway crashes
Traffic safety
Transporte rodoviário
Severidade de acidentes
Aprendizagem estatística
Acidentes em rodovias
Segurança viária
title_short Factors related to highway crash severity in Brazil through a multinomial logistic regression model
title_full Factors related to highway crash severity in Brazil through a multinomial logistic regression model
title_fullStr Factors related to highway crash severity in Brazil through a multinomial logistic regression model
title_full_unstemmed Factors related to highway crash severity in Brazil through a multinomial logistic regression model
title_sort Factors related to highway crash severity in Brazil through a multinomial logistic regression model
author Franceschi, Lucas
author_facet Franceschi, Lucas
Kaesemodel, Luciano
Vargas, Vera do Carmo Comparsi de
Konrath, Andréa Cristina
Nakamura, Luiz Ricardo
Ramires, Thiago Gentil
Barreto, Camila Belleza Maciel
Valente, Amir Mattar
author_role author
author2 Kaesemodel, Luciano
Vargas, Vera do Carmo Comparsi de
Konrath, Andréa Cristina
Nakamura, Luiz Ricardo
Ramires, Thiago Gentil
Barreto, Camila Belleza Maciel
Valente, Amir Mattar
author2_role author
author
author
author
author
author
author
dc.contributor.author.fl_str_mv Franceschi, Lucas
Kaesemodel, Luciano
Vargas, Vera do Carmo Comparsi de
Konrath, Andréa Cristina
Nakamura, Luiz Ricardo
Ramires, Thiago Gentil
Barreto, Camila Belleza Maciel
Valente, Amir Mattar
dc.subject.por.fl_str_mv Road transportation
Injury severity
Statistical learning
Highway crashes
Traffic safety
Transporte rodoviário
Severidade de acidentes
Aprendizagem estatística
Acidentes em rodovias
Segurança viária
topic Road transportation
Injury severity
Statistical learning
Highway crashes
Traffic safety
Transporte rodoviário
Severidade de acidentes
Aprendizagem estatística
Acidentes em rodovias
Segurança viária
description Reducing the number of deaths by road crashes is an important priority for many countries around the world. Although focusing on the occurrence of crashes can provide safety policies that help reduce its numbers, studying their severity can provide different measures that may help further reduce the number of deaths by focusing on the most severe problems first. In this paper, a mul.nomial logis.c regression model is fi:ed to na.onwide highway crash data in Brazil from 2017 to 2019 to iden.fy and es.mate the associated factors to crash severity. Severity is classified as without injury, with injured vic ms or with fatal vic ms. Amongst other observa.ons, results indicate that pedestrian involvement in highway crashes increase drama.cally their severity. Also, condi.ons that favor greater speeds (clear weather, .mes when there are fewer vehicles on the road) are also related to an increase in crash severity, poin.ng to a propor.onal rela.on with traffic fluidity. Moreover, some observed limita.ons on the data may indicate that Brazil would benefit greatly from na.onal crash records standards and unified databases, especially crossmatching crash reports with health data.
publishDate 2022
dc.date.none.fl_str_mv 2022-08-29T16:51:14Z
2022-08-29T16:51:14Z
2022-04-07
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv FRANCESCHI, L. et al. Factors related to highway crash severity in Brazil through a multinomial logistic regression model. Transportes, [S.l.], v. 30, n. 1, p. 1-16, 2022. DOI: 10.14295/transportes.v30i1.2566.
http://repositorio.ufla.br/jspui/handle/1/54375
identifier_str_mv FRANCESCHI, L. et al. Factors related to highway crash severity in Brazil through a multinomial logistic regression model. Transportes, [S.l.], v. 30, n. 1, p. 1-16, 2022. DOI: 10.14295/transportes.v30i1.2566.
url http://repositorio.ufla.br/jspui/handle/1/54375
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Associação Nacional de Pesquisa e Ensino em Transportes (ANPET)
publisher.none.fl_str_mv Associação Nacional de Pesquisa e Ensino em Transportes (ANPET)
dc.source.none.fl_str_mv Transportes
reponame:Repositório Institucional da UFLA
instname:Universidade Federal de Lavras (UFLA)
instacron:UFLA
instname_str Universidade Federal de Lavras (UFLA)
instacron_str UFLA
institution UFLA
reponame_str Repositório Institucional da UFLA
collection Repositório Institucional da UFLA
repository.name.fl_str_mv Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)
repository.mail.fl_str_mv nivaldo@ufla.br || repositorio.biblioteca@ufla.br
_version_ 1807835135585812480