Please use this identifier to cite or link to this item:
Title: Copula-based regression modeling of bivariate disability severity of temporary and permanent motor injuries
Author: Ayuso, Mercedes
Bermúdez, Lluís
Santolino, Miguel
Keywords: Econometria
Anàlisi de regressió
Lesions corporals
Variables (Matemàtica)
Accidents de circulació
Regression analysis
Personal injuries
Variables (Mathematics)
Traffic accidents
Issue Date: Apr-2016
Publisher: Elsevier
Abstract: 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.
Note: Versió postprint del document publicat a:
It is part of: Accident Analysis and Prevention, 2016, vol. 89, num. April, p. 142-150
Related resource:
ISSN: 0001-4575
Appears in Collections:Articles publicats en revistes (Matemàtica Econòmica, Financera i Actuarial)

Files in This Item:
File Description SizeFormat 
657222.pdf10.84 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons