A hierarchical Archimedean copula for portfolio credit risk modelling

Natalia Puzanova
Authors registered in the RePEc Author Service: Natalia Tente

No 2011,14, Discussion Paper Series 2: Banking and Financial Studies from Deutsche Bundesbank

Abstract: I introduce a novel, hierarchical model of tail dependent asset returns which can be particularly useful for measuring portfolio credit risk within the structural framework. To allow for a stronger dependence within sub-portfolios than between them, I utilise the concept of nested Archimedean copulas, but modify the nesting procedure to ensure the compatibility of copula generators by construction. This makes sampling straightforward. Moreover, I provide details on a particular specification based on a gamma mixture of powers. This model allows for lower tail dependence, resulting in a more conservative credit risk assessment than a comparable Gaussian model. I illustrate the extent of model risk when calculating VaR or Expected Shortfall for a credit portfolio.

Keywords: portfolio credit risk; nested Archimedean copula; tail dependence; hierarchical dependence structure (search for similar items in EconPapers)
JEL-codes: C46 C63 G21 (search for similar items in EconPapers)
Date: 2011
New Economics Papers: this item is included in nep-ban, nep-ecm and nep-rmg
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/52132/1/672240238.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:zbw:bubdp2:201114

Access Statistics for this paper

More papers in Discussion Paper Series 2: Banking and Financial Studies from Deutsche Bundesbank Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().