Files

684374.pdf (104.44 KB)

Document type

Article

Version

Accepted version

Publication date

2019-03

Publication license

cc-by-nc-nd (c) Elsevier B.V., 2019
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/164643

Multivariate count data generalized linear models: Three approaches based on the Sarmanov distribution

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

https://doi.org/10.1016/j.insmatheco.2019.01.001

Abstract

Starting from the question: What is the accident risk of an insured individual?, we consider that the customer has contracted policies in different insurance lines: motor and home. Three models based on the multivariate Sarmanov distribution are analyzed. Driven by a real data set that takes into account three types of accident risks, two for motor and one for home, three trivariate Sarmanov distributions with generalized linear models (GLMs) for marginals are considered and fitted to the data. To estimate the parameters of these three models, we discuss a method for approaching the maximum likelihood (ML) estimators. Finally, the three models are compared numerically with the simpler trivariate Negative Binomial GLM and with elliptical copula based models.

Subject

Models lineals (Estadística), Anàlisi multivariable, Teoria de distribucions (Anàlisi funcional), Teoria de l'estimació

Subject (English)

Linear models (Statistics), Multivariate analysis, Theory of distributions (Functional analysis), Estimation theory

Citation

Collections

Articles publicats en revistes (Econometria, Estadística i Economia Aplicada)

Citation

BOLANCÉ LOSILLA, Catalina and VERNIC, Raluca. Multivariate count data generalized linear models: Three approaches based on the Sarmanov distribution. Insurance Mathematics and Economics. 2019. Vol. 85, num. 89-103. ISSN 0167-6687. [consulted: 8 of June of 2026]. Available at: https://hdl.handle.net/2445/164643

Export metadata

JSON - METS

Share record