Quantifying the impact of different copulas in a generalized CreditRisk + framework An empirical study

Kevin Jakob; Matthias Fischer

Dependence Modeling (2014)

  • Volume: 2, Issue: 1, page 1-21
  • ISSN: 2300-2298

Abstract

top
Without any doubt, credit risk is one of the most important risk types in the classical banking industry. Consequently, banks are required by supervisory audits to allocate economic capital to cover unexpected future credit losses. Typically, the amount of economical capital is determined with a credit portfolio model, e.g. using the popular CreditRisk+ framework (1997) or one of its recent generalizations (e.g. [8] or [15]). Relying on specific distributional assumptions, the credit loss distribution of the CreditRisk+ class can be determined analytically and in real time. With respect to the current regulatory requirements (see, e.g. [4, p. 9-16] or [2]), banks are also required to quantify how sensitive their models (and the resulting risk figures) are if fundamental assumptions are modified. Against this background, we focus on the impact of different dependence structures (between the counterparties of the bank’s portfolio) within a (generalized) CreditRisk+ framework which can be represented in terms of copulas. Concretely, we present some results on the unknown (implicit) copula of generalized CreditRisk+ models and quantify the effect of the choice of the copula (between economic sectors) on the risk figures for a hypothetical loan portfolio and a variety of parametric copulas.

How to cite

top

Kevin Jakob, and Matthias Fischer. " Quantifying the impact of different copulas in a generalized CreditRisk + framework An empirical study ." Dependence Modeling 2.1 (2014): 1-21. <http://eudml.org/doc/266918>.

@article{KevinJakob2014,
abstract = {Without any doubt, credit risk is one of the most important risk types in the classical banking industry. Consequently, banks are required by supervisory audits to allocate economic capital to cover unexpected future credit losses. Typically, the amount of economical capital is determined with a credit portfolio model, e.g. using the popular CreditRisk+ framework (1997) or one of its recent generalizations (e.g. [8] or [15]). Relying on specific distributional assumptions, the credit loss distribution of the CreditRisk+ class can be determined analytically and in real time. With respect to the current regulatory requirements (see, e.g. [4, p. 9-16] or [2]), banks are also required to quantify how sensitive their models (and the resulting risk figures) are if fundamental assumptions are modified. Against this background, we focus on the impact of different dependence structures (between the counterparties of the bank’s portfolio) within a (generalized) CreditRisk+ framework which can be represented in terms of copulas. Concretely, we present some results on the unknown (implicit) copula of generalized CreditRisk+ models and quantify the effect of the choice of the copula (between economic sectors) on the risk figures for a hypothetical loan portfolio and a variety of parametric copulas.},
author = {Kevin Jakob, Matthias Fischer},
journal = {Dependence Modeling},
keywords = {copula; credit risk; model risk; quantitative finance; CreditRisk+; capital requirements; CreditRisk},
language = {eng},
number = {1},
pages = {1-21},
title = { Quantifying the impact of different copulas in a generalized CreditRisk + framework An empirical study },
url = {http://eudml.org/doc/266918},
volume = {2},
year = {2014},
}

TY - JOUR
AU - Kevin Jakob
AU - Matthias Fischer
TI - Quantifying the impact of different copulas in a generalized CreditRisk + framework An empirical study
JO - Dependence Modeling
PY - 2014
VL - 2
IS - 1
SP - 1
EP - 21
AB - Without any doubt, credit risk is one of the most important risk types in the classical banking industry. Consequently, banks are required by supervisory audits to allocate economic capital to cover unexpected future credit losses. Typically, the amount of economical capital is determined with a credit portfolio model, e.g. using the popular CreditRisk+ framework (1997) or one of its recent generalizations (e.g. [8] or [15]). Relying on specific distributional assumptions, the credit loss distribution of the CreditRisk+ class can be determined analytically and in real time. With respect to the current regulatory requirements (see, e.g. [4, p. 9-16] or [2]), banks are also required to quantify how sensitive their models (and the resulting risk figures) are if fundamental assumptions are modified. Against this background, we focus on the impact of different dependence structures (between the counterparties of the bank’s portfolio) within a (generalized) CreditRisk+ framework which can be represented in terms of copulas. Concretely, we present some results on the unknown (implicit) copula of generalized CreditRisk+ models and quantify the effect of the choice of the copula (between economic sectors) on the risk figures for a hypothetical loan portfolio and a variety of parametric copulas.
LA - eng
KW - copula; credit risk; model risk; quantitative finance; CreditRisk+; capital requirements; CreditRisk
UR - http://eudml.org/doc/266918
ER -

References

top
  1. [1] Artzner, P., Delbaen, F., Eber, J.-M., and Heath, D. (1999). Coherent measures of risk. Math. Finance, 9:203-228. Zbl0980.91042
  2. [2] BaFin. (2012). Erläuterung zu den MaRisk in der Fassung vom 14.12.2012, Dec 2012. 
  3. [3] Barndorff-Nielsen, O. E. (1977). Exponentially decreasing distributions for the logarithm of particle size. Proc. R. Soc. A, 353:401-419. 
  4. [4] Board of Governors of the Federal Reserve System. (2011). Supervisory guidance on model risk management. Letter 11-7. http://www.federalreserve.gov 
  5. [5] Dobric, J. and Schmid, F. (2005). Nonparametric estimation of the lower tail dependence in bivariate copulas. J. Appl. Stat., 32:387-407. [Crossref] Zbl1121.62364
  6. [6] Ebmeyer, D., Klaas, R., and Quell, P. (2006). The role of copulas in the CreditRisk+ framework. In Copulas. Risk Books London. 
  7. [7] Fang, K.-T., Kotz, S., and Wang, K. (1990). Symmetric Multivariate and Related Distributions. Chapman & Hall/CRC London. 
  8. [8] Fischer, M. and Dietz, C. (2011/12). Modeling sector correlations with CreditRisk+: The common background vector model. The Journal of Credit Risk, 7:23-43. 
  9. [9] Fischer, M. and Dörflinger, M. (2010). A note on a non-parametric tail dependence estimator. Far East J. Theor. Stat., 32:1-5. Zbl1195.62066
  10. [10] Fischer, M. and Mertel, A. (2012). Quantifying model risk within a CreditRisk+ framework. The Journal of Risk Model Validation, 6:47-76. 
  11. [11] Frey, R., McNeil, A.J., and Nyfeler, M.A. (2001). Copulas and credit models. RISK, October: 111-114. 
  12. [12] Genest, C., Remillard, B., and Beaudoin, D. (2009). Goodness-of-t tests for copulas: A review and a power study. Insurance Math. Econom., 44:199-213. [WoS] Zbl1161.91416
  13. [13] Giese, G. (2003). Enhancing CreditRisk+. RISK, 16:73-77. 
  14. [14] Gundlach, M. and Lehrbass, F. (2003). CreditRisk+ in the Banking Industry. Springer- Verlag Berlin Heidelberg. Zbl1046.91001
  15. [15] Han, C. and Kang, J. (2008). An extended CreditRisk+ framework for portfolio credit risk management. The Journal of Credit Risk, 4:63-80. 
  16. [16] Hering, C., Hofert, M., Mai, J., and Scherer, M. (2010). Constructing hierarchical Archimedean copulas with Lévy subordinators. J. Multivariate Anal., 101(6):1428-1433. Zbl1194.60017
  17. [17] Hofert, M., Kojadinovic, I., Mächler, M., and Yan, J. (2012). copula: Multivariate Dependence with Copulas, R package version 0.999-5 edition. URL: http://CRAN. R-project.org/package=copula. 
  18. [18] Jaworski, P., Durante, F., Härdle, W., and Rychlik, T. (2010). Copula Theory and Its Applications. Springer-Verlag Berlin Heidelberg. Zbl1194.62077
  19. [19] Joe, H. (1997). Multivariate Models and Dependence Concepts. Chapman & Hall/CRC London. 
  20. [20] Li, D.X. (2000). On default correlation: A copula function approach. Journal of Fixed Income, 9:43-54. 
  21. [21] Luethi, D. and Breymann, W. (2011). ghyp: A package on the generalized hyperbolic distribution and its special cases. URL: http://CRAN.R-project.org/package= ghyp. 
  22. [22] Mai, J.F. and Scherer, M. (2009). Bivariate extreme-value copula with discrete pickands dependence measure. Extremes, 14:311-324. Zbl1329.62270
  23. [23] McNeil, A.J. (2008). Sampling nested Archimedean copulas. J. Stat. Comput. Simul., 78:567-581. Zbl1221.00061
  24. [24] McNeil, A.J., Frey, R., and Embrechts, P. (2005). Quantitative Risk Management. Princeton University Press. Zbl1089.91037
  25. [25] Merton, R.C. (1973). On the pricing of corporate debt: The risk structure of interest rates. Journal of Finance, 29:449-470. 
  26. [26] Moschopoulos, P.G. (1985). The distribution of the sum of independendent gamma random variables. Ann. Inst. Statist. Math., 37:541-544. Zbl0587.60015
  27. [27] Nelsen, R.B. (2006). An Introduction to Copulas. Springer New York. Zbl1152.62030
  28. [28] Oh, D.H. and Patton, A.J. (2012). Modelling dependence in high dimension with factor copulas. Manuscript, Duke University. URL: http://public.econ.duke.edu/~ap172/Oh_Patton_MV_factor_copula_6dec12.pdf 
  29. [29] Okhrin, O. and Ristig, A. (2012). Hierarchical Archimedean Copulae: The HAC Package. Humbold Universität Berlin. URL: http://cran.r-project.org/web/ packages/HAC/index.html. 
  30. [30] Okhrin, O., Okhrin, Y., and Schmid, W. (2013). Properties of hierarchical Archimedean copulas. Statistics & Risk Modeling, 30:21-54. Zbl06156806
  31. [31] Paolella, M.S. (2007). Intermediate Probability: A Computational Approach. John Wiley & Sons Chichester. Zbl1149.60002
  32. [32] Savu, C. and Trede, M. (2010). Hierarchical Archimedean Copulas. Quant. Finance, 10:295-304. Zbl1270.91086
  33. [33] Sklar, A. (1959). Fonctions de répartition á n dimensions et leurs marges. Publ. Inst. Stat. Univ. Paris, 8:229-231. Zbl0100.14202
  34. [34] Szpiro, G. (2009). Eine falsch angewendete Formel und ihre Folgen. Neue Züricher Zeitung, 18 März. 
  35. [35] Wilde, T. (1997). CreditRisk+ A Credit Risk Management Framework. Working Paper, Credit Suisse First Boston. 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.