Validation of loss given default in the advanced IRB approach

Guilherme Fernandes Sanches () and Andre Santos ()
Additional contact information
Guilherme Fernandes Sanches: BNDES

Brazilian Review of Finance, 2016, vol. 14, issue 2, 299-321

Abstract: The goal of our paper is to contribute to the discussion about the most important aspects of the loss given default validation process, with special attention to the brazilian case, as the Central Bank of Brazil determines in Circular no 3.648/2013. The authors suggest the application of a few non-linear statistical measures to the study of dependence between default frequency and loss given default, likeKendall ad Somers statistics and non-binary receiver operation characterisc (ROC). An estimation methodology for Downturn LGD is proposed, having as foundation a correlation adjustment derivedfrom expected loss and ordination of quantiles of the forecasted LGD distribution according to the dependence level for different credit portfolios.

Keywords: LGD; validation; IRB approaches; credit risk; Basel Accords; LGD; validation; IRB approaches; credit risk; Basel Accords (search for similar items in EconPapers)
JEL-codes: G18 G28 G32 G38 (search for similar items in EconPapers)
Date: 2016
References: Add references at CitEc
Citations:

Downloads: (external link)
http://bibliotecadigital.fgv.br/ojs/index.php/rbfin/article/download/60908/60805 (application/pdf)
http://bibliotecadigital.fgv.br/ojs/index.php/rbfin/article/view/60908 (text/html)

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:brf:journl:v:14:y:2016:i:2:p:299-321

Access Statistics for this article

Brazilian Review of Finance is currently edited by Marcio Laurini

More articles in Brazilian Review of Finance from Brazilian Society of Finance
Bibliographic data for series maintained by Marcio Laurini ().