Use este identificador para citar ou linkar para este item: http://repositorio.ufla.br/jspui/handle/1/54375
Título: Factors related to highway crash severity in Brazil through a multinomial logistic regression model
Título(s) alternativo(s): Fatores relacionados à severidade de acidentes em rodovias no Brasil através de um modelo de regressão logística multinomial
Palavras-chave: Road transportation
Injury severity
Statistical learning
Highway crashes
Traffic safety
Transporte rodoviário
Severidade de acidentes
Aprendizagem estatística
Acidentes em rodovias
Segurança viária
Data do documento: 7-Abr-2022
Editor: Associação Nacional de Pesquisa e Ensino em Transportes (ANPET)
Citação: 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.
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.
URI: http://repositorio.ufla.br/jspui/handle/1/54375
Aparece nas coleções:DES - Artigos publicados em periódicos

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
ARTIGO_Factors related to highway crash severity in Brazil through a multinomial logistic regression model.pdf1,14 MBAdobe PDFVisualizar/Abrir


Este item está licenciada sob uma Licença Creative Commons Creative Commons