zbMATH — the first resource for mathematics

Two-step methods in VaR prediction and the importance of fat tails. (English) Zbl 1398.91683
Summary: This paper proposes a two-step methodology for value-at-risk prediction. The first step involves estimation of a GARCH model using quasi-maximum likelihood estimation and the second step uses model filtered returns with the skewed \(t\) distribution of A. Azzalini and A. Capitanio [J. R. Stat. Soc. B. 65, No. 2, 367–389 (2003; doi:10.1111/1467-9868.00391)]. The predictive performance of this method is compared to the single-step joint estimation of the same data generating process, to the well-known GARCH-EVT model and to a comprehensive set of other market risk models. Backtesting results show that the proposed two-step method outperforms most benchmarks including the classical joint estimation method of same data generating process and it performs competitively with respect to the GARCH-EVT model. This paper recommends two robust models to risk managers of emerging market stock portfolios. Both models are estimated in two steps: the GJR-GARCH-EVT model and the two-step GARCH-St model proposed in this study.

91G70 Statistical methods; risk measures
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
60G70 Extreme value theory; extremal stochastic processes
ismev; QRM
Full Text: DOI
[1] Aas, K. and Haff, I.H., The generalized hyperbolic skew student’s t distribution. J. Financ. Econom., 2006, 4, 275-309.
[2] Assaf, A., Extreme observations and risk assessment in the equity markets of MENA region: Tail measures and value-at-risk. Int. Rev. Financ. Anal., 2009, 18, 109-116.
[3] Azzalini, A., A class of distributions which includes the normal ones. Scand. J. Stat., 1985, 12, 171-178.
[4] Azzalini, A. and Capitanio, A., Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t distribution. J. R. Stat. Soc. B, 2003, 65, 367-389.
[5] Bali, T.G., An extreme value approach to estimating volatility and value at risk. J. Bus., 2003, 76, 83-108.
[6] Bali, T.G., An extreme value approach to estimating interest rate volatility: Pricing implications for interest rate options. Manage. Sci., 2007, 53, 323-339.
[7] Bali, T.G., Mo, H. and Tang, Y., The role of conditional skewness and kurtosis in the estimation of conditional VaR. J. Bank. Finance, 2008, 32, 269-282.
[8] Bali, T.G. and Theodossiou, P., Risk measurement of alternative distribution functions. J. Risk Insur., 2008, 75, 411-437.
[9] Bao, Y., Lee, T.H. and Saltoglu, B., Evaluating predictive performance of value-at-risk models in emerging markets: A reality check. J. Forecasting, 2006, 25, 101-128.
[10] Basel Committee on Banking Supervision. Supervisory framework for the use of backtesting in conjunction with the internal models approach to market risk capital requirement. Manuscript, Bank for International Settlements, 1996.
[11] Bhattacharyya, M., Chaudhary, A. and Yadav, G., Conditional VaR estimation using Pearson’s type IV distribution. Eur. J. Oper. Res., 2008, 191, 386-397.
[12] Bhattacharyya, M., Misra, N. and Kodase, B., MaxVaR for non-normal and heteroscedastic returns. Quant. Finance, 2009, 9, 925-935.
[13] Bollerslev, T., Generalized autoregressive conditional heteroscedasticity. J. Econom., 1986, 1, 307-327.
[14] Bollerslev, T., A conditionally heteroscedastic time series model for speculative prices and rates of returns. Rev. Econ. Stat., 1987, 69, 542-547.
[15] Bollerslev, T. and Wooldridge, J.M., Quasi-maximum likelihood estimation and inference in dynamic models with time-varying covariances. Econom. Rev., 1992, 11, 143-172.
[16] Christoffersen, P.F., Evaluating interval forecasts. Int. Econ. Rev., 1998, 39, 841-862.
[17] Coles, S., An Introduction to Statistical Modeling of Extreme Values, 2001 (Springer:London).
[18] Dimitrakopoulos, D.N., Manolis, G.K. and Spyrou, S.I., Value at risk models for volatile emerging markets equity portfolios. Q. Rev. Econ. Finance, 2010, 50, 515-526.
[19] Embrechts, P., Kluppelberg, C. and Mikosch, T., Modeling Extremal Events for Insurance and Finance, 1997 (Springer Verlag: Berlin).
[20] Fama, E., The behavior of stock market prices. J. Bus., 1965, 38, 34-105.
[21] Fernandez, V., Risk management under extreme events. Int. Rev. Financ. Anal., 2005, 14, 113-148.
[22] Fernandez, C. and Steel, M.F.J., On Bayesian modeling of fat tails and skewness. J. Am. Stat. Assoc., 1998, 93, 359-371.
[23] Furiò, D. and Climent, F.J., Extreme value theory versus traditional GARCH approaches applied to financial data: A comparative evaluation. Quant. Finance, 2013, 13, 45-63.
[24] Gençay, R. and Selçuk, F., Extreme value theory and value-at-risk: Relative performance in emerging markets. Int. J. Forecasting, 2004, 20, 287-303.
[25] Gençay, R., Selçuk, F. and Ulugülyağcı, A., High volatility, thick tails and extreme value theory in value-at-risk estimation. Insur. Math. Econ., 2003, 33, 337-356.
[26] Giot, P. and Laurent, S., Modelling daily Value-at-Risk using realized volatility and ARCH type models. J. Empir. Finance, 2004, 11, 379-398.
[27] Glosten, L.R., Jagannathan, R. and Runkle, D.E., On the relation between the expected value and the volatility of the nominal excess return on stocks. J. Finance, 1993, 48, 1779-1801.
[28] Hansen, B.E., Autoregressive conditional density estimation. Int. Econ. Rev., 1994, 35, 705-730.
[29] Kuester, K., Mittnik, S. and Paolella, M.S., Value-at-risk prediction: A comparison of alternative strategies. J. Financ. Econom., 2006, 4, 53-89.
[30] Lee, S.W. and Hansen, B.E., Asymptotic theory for the GARCH(1,1) quasi-maximum likelihood estimator. Econom. Theory, 1994, 10, 29-52.
[31] Longin, F.M., From value at risk to stress testing: The extreme value approach. J. Bank. Finance, 2000, 24, 1097-1130.
[32] Mabrouk, S. and Saadi, S., Parametric value-at-risk analysis: Evidence from stock indices. Q. Rev. Econ. Finance, 2012, 52, 305-321.
[33] Mandelbrot, B., The variation of certain speculative prices. J. Bus., 1963, 36, 394-419.
[34] McNeil, A.J., Extreme value theory for risk managers. Internal Modeling CAD II: Qualifying and Quantifying Risk Within a Financial Institution. British Banker’s Association, pp. 99-113, 1999 (RISK Books: London).
[35] McNeil, A.J. and Frey, R., Estimation of tail related risk measures for heteroscedastic financial time series. J. Empir. Finance, 2000, 7, 271-300.
[36] McNeil, A.J., Frey, R. and Embrechts, P., Quantitative Risk Management: Concepts, Techniques, and Tools, 2005 (Princeton University Press: Princeton, NJ).
[37] Nelson, D.B., Conditional heteroscedasticity in asset returns: A new approach. Econometrica, 1991, 59, 347-370.
[38] Newey, W.K. and Steigerwald, D.G., Asymptotic bias for quasi-maximum likelihood estimators in conditional heteroscedasticity models. Econometrica, 1997, 65, 587-599.
[39] Pickands, J., Statistical inference using extreme order statistics. Ann. Stat., 1975, 3, 119-131.
[40] Pritsker, M., The hidden dangers of historical simulation. J. Bank. Finance, 2006, 30, 561-582.
[41] Rossignolo, A.F., Fethi, M.D. and Shaban, M., Value-at-risk models and Basel capital charges: Evidence from emerging and Frontier stock markets. J. Financ. Stab., 2012, 8, 303-319.
[42] Silva, A.L. and Mendes, B.V.M., Value-at-risk and extreme returns in Asian stock markets. Int. J. Bus., 2003, 8, 17-40.
[43] Theodossiou, P., Financial data and the skewed generalized t distribution. Manage. Sci., 1998, 44, 1650-1661.
[44] Zakoian, J.M., Threshold heteroskedasticity models. J. Econ. Dyn. Control, 1994, 15, 931-955.
[45] Zhu, D. and Galbraith, J.W., A generalized asymmetric Student-t distribution with application to financial econometrics. J. Econom., 2010, 157, 297-305.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.