dc.contributor |
Xarxa de Referència en Economia Aplicada (XREAP) |
dc.contributor.author |
Bolancé Losilla, Catalina |
dc.contributor.author |
Vernic, Raluca |
dc.date.accessioned |
2017-11-14T10:40:09Z |
dc.date.accessioned |
2021-01-20T16:45:47Z |
dc.date.available |
2017-11-14T10:40:09Z |
dc.date.available |
2021-01-20T16:45:47Z |
dc.date.created |
2017-11 |
dc.date.issued |
2017-11 |
dc.identifier.uri |
http://hdl.handle.net/2072/300913 |
dc.format.extent |
37 p. |
dc.language.iso |
eng |
dc.publisher |
Xarxa de Referència en Economia Aplicada (XREAP) |
dc.relation.ispartofseries |
XREAP;2017-07 |
dc.rights |
info:eu-repo/semantics/openAccess |
dc.rights |
L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.source |
RECERCAT (Dipòsit de la Recerca de Catalunya) |
dc.subject.other |
Assegurances d'accidents |
dc.subject.other |
Models lineals (Estadística) |
dc.subject.other |
Anàlisi de regressió |
dc.subject.other |
Accident insurance |
dc.subject.other |
Linear models (Statistics) |
dc.subject.other |
Regression analysis |
dc.title |
Multivariate count data generalized linear models: Three approaches based on the Sarmanov distribution |
dc.type |
info:eu-repo/semantics/workingPaper |
dc.subject.udc |
311 - Estadística |
dc.subject.udc |
33 - Economia |
dc.embargo.terms |
cap |
dc.description.abstract |
Starting from the question: “What is the accident risk of an insured?”, this paper considers a multivariate approach by taking into account three types of accident risks and the possible dependence between them. Driven by a real data set, we propose three trivariate Sarmanov distributions with generalized linear models (GLMs) for marginals and incorporate various individual characteristics of the policyholders by means of explanatory variables. Since the data set was collected over a longer time period (10 years), we also added each individual’s exposure to risk. To estimate the parameters of the three Sarmanov distributions, we analyze a pseudo-maximumlikelihood method. Finally, the three models are compared numerically with the simpler trivariate Negative Binomial GLM. |