Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/72511
Title: A Bayesian dichotomous model with asymmetric link for fraud in insurance
Authors: Bermudez, Ll.
Perez, J. M.
Ayuso, M.
Gómez Déniz, Emilio 
Vázquez Polo, Francisco José 
UNESCO Clasification: 530202 Modelos econométricos
Keywords: Bayesian Statistics
Logit Model
Gibbs Sampling
Automobile Insurance
Fraud
Issue Date: 2008
Journal: Insurance: Mathematics and Economics 
Abstract: Standard binary models have been developed to describe the behavior of consumers when they are faced with two choices. The classical logit model presents the feature of the symmetric link function. However, symmetric links do not provide good fits for data where one response is much more frequent than the other (as it happens in the insurance fraud context). In this paper, we use an asymmetric or skewed logit link, proposed by Chen et al. [Chen, M., Dey, D., Shao, Q., 1999. A new skewed link model for dichotomous quantal response data. J. Amer. Statist. Assoc. 94 (448), 1172-1186], to fit a fraud database from the Spanish insurance market. Bayesian analysis of this model is developed by using data augmentation and Gibbs sampling. The results show that the use of an asymmetric link notably improves the percentage of cases that are correctly classified after the model estimation. (C) 2007 Elsevier B.V. All rights reserved.
URI: http://hdl.handle.net/10553/72511
ISSN: 0167-6687
DOI: 10.1016/j.insmatheco.2007.08.002
Source: Insurance Mathematics & Economics[ISSN 0167-6687],v. 42 (2), p. 779-786, (Abril 2008)
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

45
checked on Dec 4, 2022

WEB OF SCIENCETM
Citations

37
checked on Oct 2, 2022

Page view(s)

22
checked on Nov 20, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.