Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió acceptadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/106464
Copula-based regression modeling of bivariate disability severity of temporary and permanent motor injuries
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
The analysis of factors influencing the severity of the personal injuries suffered by victims of motor accidents is an issue of major interest. Yet, most of the extant literature has tended to address this question by focusing on either the severity of temporary disability or the severity of permanent injury. In this paper, a bivariate copula-based regression model for temporary disability and permanent injury severities is introduced for the joint analysis of the relationship with the set of factors that might influence both categories of injury. Using a motor insurance database with 21,361 observations, the copula-based regression model is shown to give a better performance than that of a model based on the assumption of independence. The inclusion of the dependence structure in the analysis has a higher impact on the variance estimates of the injury severities than it does on the point estimates. By taking into account the dependence between temporary and permanent severities a more extensive factor analysis can be conducted. We illustrate that the conditional distribution functions of injury severities may be estimated, thus, providing decision makers with valuable information.
Matèries (anglès)
Citació
Citació
AYUSO, Mercedes, BERMÚDEZ, Lluís, SANTOLINO, Miguel. Copula-based regression modeling of bivariate disability severity of temporary and permanent motor injuries. _Accident Analysis and Prevention_. 2016. Vol. 89, núm. April, pàgs. 142-150. [consulta: 23 de gener de 2026]. ISSN: 0001-4575. [Disponible a: https://hdl.handle.net/2445/106464]