Zero-inflated and over-dispersed data models: Empirical evidence from insurance claim frequencies
Assurances et gestion des risques · 2018
DOI: 10.7202/1043358ar ↗Kurz gefasst
Fachartikel in der Zeitschrift Assurances et gestion des risques, 2018. Verfasst von Imen Karaa und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
The main objective of this paper is to model automobile claim frequency by using standard count regression and zero-inflated regression models. The use of the latter model is mainly motivated by its ability to handle the over dispersion and zero-inflation phenomenon. The sample data consist of claims data obtained from one randomly selected automobile insurance company in Tunisia for a single year, 2009, containing beginning drivers and drivers who have had a license for less than three years. Our estimation results show that many exogenous variables can explain the frequency of claims; they are not taken into account in calculating the basic insurance premium. Moreover, the ZI binomial negative regression outperforms the standard count models and the ZI Poisson model in handling zero-inflated and additional over dispersed claim count data.
Zitieren
APA
Karaa, I., & Chabchoub, H. (2018). Zero-inflated and over-dispersed data models: Empirical evidence from insurance claim frequencies. Assurances et gestion des risques. https://doi.org/10.7202/1043358ar
Vancouver
Karaa I, Chabchoub H. Zero-inflated and over-dispersed data models: Empirical evidence from insurance claim frequencies. Assurances et gestion des risques. 2018. doi:10.7202/1043358ar
BibTeX
@article{Karaa2018,
author = {Karaa, Imen and Chabchoub, Habib},
title = {Zero-inflated and over-dispersed data models: Empirical evidence from insurance claim frequencies},
journal = {Assurances et gestion des risques},
year = {2018},
doi = {10.7202/1043358ar}
}
EUVIMED