The Evaluation of Model Risk for Probability of Default and Expected Loss

Gourieroux, Christian and Tiomo, Andre (2019): The Evaluation of Model Risk for Probability of Default and Expected Loss.

Abstract

The quanti�cation of model risk is still in its infancy. This paper provides an operational quanti�cation of this risk for credit portfolio, when the objective is to approximate the average loss. The methodology is easy to implement and does not require the construction of any worst-case model. The required capital computed to cover for model risk depends on three components, that are an estimated impact of the incorrect model, an evaluated risk of inaccurate estimation of model risk and the prediction error hedge factor. The approach is illustrated by an application to a portfolio of corporate loans segmented by grades.

• Item Type: MPRA Paper
• Language: English
• Keywords: Model Risk, Estimation Risk, Speci�cation Risk, Expected Loss, Probability of Default, Required Capital, Prudential Regulation, Difference Estimator. 1
• Subjects: G - Financial Economics > G3 - Corporate Finance and Governance > G30 - General

References

References [1] Akaike, H. (1973) : "Information Theory and an Extension of the Maximum Likelihood Principle", in Proc. 2nd Int. Symp. Information Theory, eds. B., Petrov and F., Csaki, 267-281, Budapest, Akademiai Kiado. [2] Akaike, H. (1974) : "A New Look at the Statistical Model Identi�cation", IEEE Trans. Autom. Control, 19, 716-723. [3] Alexander, C., and J., Sarabia (2012) : "Quantile Uncertainty and Valueat- Risk Model Risk", Risk Analysis, 32, 1293-1308. [4] Barrieu, P., and C., Ravanelli (2015) : "Robust Capital Requirements with Model Risk", Economic Notes, 44, 1-28. [5] Bertram, P., Sibbertsen, P., and G., Stahl (2015) : "About the Impact of Model Risk on Capital Reserves : A Quantitative Analysis", Journal of Risk, 17, 5. [6] Board of Governors of the Federal Reserve System (2013) : "Applying the Requirement for Conservatism to the Parameters in the Advanced Approaches", Basel Coordination Committee (BCC 13-5), Division of Banking, Supervision and Regulation, Washington D.C. [7] Branco, C. (2011) : "Addressing the Issue of Conservatism in Probability of Default Estimates : A Validation Tool", The Journal of Risk and Model Validation, Vol 5, 3-19. [8] Breuer, T., and I., Csiszar (2016) : "Measuring Distribution Model Risk", Mathematical Finance, 26, 395-411. [9] Castor, N., and L., Gerhardsson (2017) : "Estimation of Probability of Default in Low Default Portfolio", DP Lund Univ. [10] Cattaneo, M., Jansson, M., and X., Ma (2018) : "Two Step Estimation and Inference with Possibly Many Included Covariates", Review of Economic Studies, forthcoming. [11] Chat�eld, C. (1993) : "Calculating Interval Forecasts", Journal of Business and Economic Statistics, 11, 121-135. [12] Cochran, W. (1977) : "Sampling Techniques", 3rd edition, Wiley. 26 [13] Cont, R. (2004) : "Model Undertainty and its Impact on the Pricing of Derivative Instruments", Mathematical Finance, 16, 519-547. [14] Cox, D. (1961) : "Test of Separate Families of Hypotheses", in Proc. 4th Berkeley Symposium on Mathematical Statistics and Probability, Vol 1, Univ. of California Press, Berkeley, 105-123. [15] Crouhi, M., Galai, D., and R., Mark (1998) : "Model Risk", Journal of Financial Engineering, 7, 267-288. [16] Danielsson, J., Ergun, L., and C., De Vries (2018) : "Challenges in Implementing Worst-Case Analysis", September, Bank of Canada. [17] Danielsson, J., James, K., Valenzuela, M., and I., Zei (2016) : "Model Risk of Risk Models", Journal of Financial Stability, 23, 79-91. [18] Derman, E. (1996) : "Model Risk", Quantitative Strategies Research Notes, Goldman Sachs. [19] Detering, N., and N., Packam (2016) : "Model Risk of Contingent Claims", Quantitative Finance, 16, 1657-1374. [20] Diebold, F., and S., Mariano (1995) : "Comparing Predictive Accuracy", Journal of Business and Economic Statistics, 13, 253-263. [21] European Banking Authority (2015) : "Results from the 2014 Low Default Portfolio Exercise", EBA Report. [22] European Banking Authority (2017) : "Guidelines on PD Estimation, LGD Estimation and the Treatment of Defaulted Exposures", November. [23] European Central Bank (2017): "Guide for the Targeted Review of Internal Models (TRIM)", Banking Supervision, February. [24] European Banking Authority (2018) : "Results from the 2018 Low and High Default Portfolio Exercise", EBA Report. [25] Gourieroux, C., and A., Monfort (2019)a : "Model Risk Managements : Valuation and Governance of Pseudo-Models", CREST DP. [26] Gourieroux, C., and A., Monfort (2019) b : "Model Risk Managements : Limits and Future of Bayesian Approaches", CREST-DP. 27 [27] Gourieroux, C., and J.M., Zakoian (2013) : "Estimation-Adjusted VaR", Econometric Theory, 29, 735-770. [28] Green, T., and S., Figlewski (1999) : "Market Risk and Model Risk for a Financial Institution Writing Options", Journal of Finance, 54, 1465-1495. [29] Hansen, B. (2006) : "Inverval Forecasts and Parameter Uncertainty", Journal of Econometrics, 135, 377-398. [30] Hansen, L., and T., Sargent (2001) : "Robust Control and Model Uncertainty", 91, 60-66. [31] Horvitz, D., and D., Thompson (1952) : "A Generalization of Sampling Without Replacement from a Finite Universe", Journal of the American Statistical Association, 47, 663-685. [32] Hull, J., and W., Suo (2002) : "A Methodology for Assessing Model Risk and its Application to the Implied Volatility Function Model", Journal of Financial and Quantitative Analysis, 37, 297-318. [33] Jaschke, S., Stehle, R., and G., Stahl (2007) : "Value-at-Risk Forecasts Under Scruting : the German Experience", Quantitative Finance, 7, 621- 636. [34] Kerkhof, J., Melenberg, G., and H., Schumacher (2010) : "Model Risk and Capital Reserves", Journal of Banking and Finance, 34, 267-279. [35] Kiefer, N. (2009) : "Default Estimation of Low Default Portfolio", Journal of Empirical Finance, 16, 143-173. [36] Lawrenz, J. (2006) : "Assessing the Estimation Uncertainty of Default Probabilities", DP Univ. of Innsbruck. [37] Lv, J., and J., Liu (2014) : "Model Selection Principles in Misspeci�ed Models", JRSS B, 76, 141-167. [38] Muller, F., and M., Righi (2018) : "Model Risk Adjusted Risk Forecasting", DP Federal University of Rio Grande do Sul. [39] O�ce ot the Comptroller of the Currency (2011) : "Supervisory Guidance on Model Risk Management", SR Letter 11-7, April. 28 [40] Pluto, K., and D., Tasche (2005) : "Estimating Probabilities of Default for Low Default Portfolio", DP Deutsche Bundesbank. [41] Rebonato, R. (2001) : "Managing Model Risk", in Alexander, C. (eds), Mastering Risk, 2, 82-118. [42] Schwarz, G. (1978) : "Estimating the Dimension of a Model", Ann.Stat., 153, 12-18. [43] Sibbertsen, P., Stahl, G., and C., Luedtke (2008) : "Measuring Model Risk", Univ. Hanover, DP 409. [44] Singh, H., Rathour, A., and R., Solanki (2013) : "An Improvement over Di�erence Method of Estimation of Population Mean", JRSS, 6, 35-46. [45] Stahl, G. (1997) : "Three Cheers", Risk Magazine, Risk, 10, 67-69. [46] Takeuchi, K. (1976) : "Distribution of Information Statistics and Criteria for Adequacy of Models" (in Japanese), Math. Sci., 153, 12-18. [47] Wallis, K. (1974) "Discussion of Experience with Forecasting Univariate Time Series and the Combination of Forecasts", by P., Newbold and C., Granger, JRSS, A, 137, 155-156. [48] Yang, Z., and T., Zhu (2018) : "Bayesian Selection of Misspeci�ed Models is Overcon�dent and May Cause Spurious Posterior Probabilities for Phylogenetic Tree", Proc. Nat. Acad.Sci. USA, 115, 1854-1859 (with Supporting Information). 29