Generalized Extreme Value Regression for Binary Rare Events Data: an Application to Credit Defaults

Raffaella Calabrese () and Silvia Osmetti
Additional contact information
Silvia Osmetti: Department of Statistics, University Cattolica del Dacro Cuore, Milan

No 201120, Working Papers from Geary Institute, University College Dublin

Abstract: The most used regression model with binary dependent variable is the logistic regression model. When the dependent variable represents a rare event, the logistic regression model shows relevant drawbacks. In order to overcome these drawbacks we propose the Generalized Extreme Value (GEV) regression model. In particular, in a Generalized Linear Model (GLM) with binary dependent variable we suggest the quantile function of the GEV distribution as link function, so our attention is focused on the tail of the response curve for values close to one. The estimation procedure is the maximum likelihood method. This model accommodates skewness and it presents a generalization of GLMs with log-log link function. In credit risk analysis a pivotal topic is the default probability estimation. Since defaults are rare events, we apply the GEV regression to empirical data on Italian Small and Medium Enterprises (SMEs) to model their default probabilities.

Pages: 20 pages
Date: 2011-09-15
New Economics Papers: this item is included in nep-ban, nep-ecm, nep-ore and nep-rmg
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.ucd.ie/geary/static/publications/workingpapers/gearywp201120.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ucd:wpaper:201120

Access Statistics for this paper

More papers in Working Papers from Geary Institute, University College Dublin Contact information at EDIRC.
Bibliographic data for series maintained by Geary Tech ().