Abstract
In this study, we compare the out-of-sample forecasting performance of several modern Value-at-Risk (VaR) estimators derived from extreme value theory (EVT). Specifically, in a multi-asset study covering 30 years of stock, bond, commodity and currency market data, we analyse the accuracy of the classic generalised Pareto peak over threshold approach and three recently proposed methods based on the Box–Cox transformation, L-moment estimation and the Johnson system of distributions. We find that, in their unconditional form, some of the estimators may be acceptable under current regulatory assessment rules but none of them can continuously pass more advanced tests of forecasting accuracy. In their conditional forms, forecasting power is significantly increased and the Box–Cox method proves to be the most promising estimator. However, it is also important to stress that the traditional historical simulation approach, which is currently the most frequently used VaR estimator in commercial banks, can not only keep up with the EVT-based methods but occasionally even outperforms them (depending on the setting: unconditional versus conditional). Thus, recent claims to generally replace this simple method by theoretically more advanced EVT-based methods may be premature.
Similar content being viewed by others
Notes
For another strand of the literature dealing with EVT in VaR copulas, see Hsu et al. (2012).
With an infinite right endpoint, we would allow the possibility of unreasonably large outcomes. Also note that the form of (7) requires to multiply the empirical long-position returns by \(-1\) in order to model the correct tail.
Of course this is not mathematically complete because we do not exactly say what we mean by ‘a large class’. For this article, it is sufficient to know that the class contains all the common continuous distributions of statistics and actuarial science (normal, lognormal, \(\chi ^2\), Student-t, F, gamma, exponential, uniform, beta, etc.).
Similar to the GEVD, the GPD nests other distributions. The special cases \(\xi = 0\) and \(\xi =1\) yield, respectively, the exponential distribution with mean \(\delta \) and the uniform distribution on \([0,\delta ]\). Classic Pareto distributions are obtained when \(\xi < 0\) (see Hosking and Wallis 1987).
This is because \(\underset{{\lambda \rightarrow 0}}{\lim } \frac{x^\lambda -1}{\lambda } = \ln x\).
The detailed results for the variants (ii) and (iii) are available upon request.
Random GARCH returns have been produced by estimating the model, drawing randomly (with replacement) from the sample standardised residuals and then using the GARCH equations to construct a simulated return path.
The reason why the GPD distribution is used for the tails rather than the empirical distribution throughout is that the number of observations in the tails may be insufficient to obtain accurate results without using an appropriate fitted distribution.
In our robustness checks in Sect. 5.2, we summarise the results for more general GARCH variants.
This is because the approach suggested by Härdle and Tsybakov (1997) has several undesirable properties. For example, the procedure for estimating conditional variance suffers from significant bias and does not produce estimates that are constrained to be positive. Furthermore, it is sensitive to how well \(\mu (x)\) is estimated.
In the simulation study, they use an interesting stochastic process with Hansen (1994) skewed-t errors, for which the true VaR can be directly calculated. Thus, in repeated sampling, they can answer the question of how close the estimates of different VaR methods are to the true VaR.
The codes of the series are S&PCOMP, GSCITOT, GOLDBLN, BMUS10Y and BOECGBP.
The fact that heavy-tailed distributions may not possess low-order moments implies that usual significance tests for skewness and kurtosis are most likely unreliable and are not worth reporting (see Paolella 2001).
Note that the statistics take high values partially because of the large sample size (see Bali 2007).
We leave the performance of multi-step-ahead forecasts for future research because problems with the square-root-of-time scaling rule and related techniques must to be resolved first (see McNeil and Frey 2000).
Brooks et al. (2005) use only one out-of-sample period of 250 days and calculate the percentage of days for which the VaRs were exceeded by actual trading losses. Bali (2007) defines a 10-year rolling sample (in one-year increments) to estimate parameters and sets a one-year holdout sample (subsequent to the estimation) to evaluate performance. Kuester et al. (2006) use our approach.
Of course, in a regime of negative interest rates, this point of view can change because then reserves are subject to capital depreciation.
Underpredictions have potentially serious solvency implications in the context of futures margin systems because margin setting is known to be sensitive to the occurrence of large price changes (see Brooks et al. 2005).
This is consistent with the results of Kuester et al. (2006) for the NASDAQ Composite index.
Berkowitz et al. (2011) summarises tests which focus on the duration between violations because, under the null that VaR forecasts are correctly specified, this duration should be completely unpredictable.
In effect, the null hypothesis of the unconditional coverage test will be tested against the alternative of the independence test.
Thus, at a 1% level, the tests require the critical values \(\chi ^2(4) = 13.28\) and \(\chi ^2(5) = 15.09\), respectively (see Domitrescu et al. 2012).
The Basel three-zone framework deems a VaR model acceptable (green zone) if the number of violations of the 99%-VaR is below the 1%-binomial 95% quantile. A model is disputable (yellow zone) up to the 99.99% quantile and is deemed seriously flawed (red zone) whenever more violations occur (see Kuester et al. 2006; Campbell 2007). Thus, with the decision rule ‘reject the null hypothesis of a valid VaR model whenever the model scores red’, the procedure can be interpreted as a significance test, i.e., basically as a one-sided version of the unconditional coverage test (see Ziggel et al. 2014).
Our results indicate that, at least for our dataset, the 5% quantile is still not large enough for the normal assumption to be adequate.
A detailed investigation of this issue is bejond the scope of this article but might be an interesting topic for future research.
Detailed results are available upon request.
Thus, not only the means and the dispersion of extremes are time-varying but also the tail index which measures the fatness of the distribution (or the weight of the tails).
Note that we have also experimented with alternative threshold quotas q. However, both increasing and decreasing our initial value of 10% negatively influences VaR estimator performance. This indicates that the 10% suggestion of McNeil and Frey (2000) is a quite good guideline for a variety of different time series.
Kuester et al. (2006) also show that conditional historical simulation is quite robust to the choice of window length but also that there are some non-EVT parametric methods that outperform this method even as the sample size shrinks.
We have also implemented the bootstrap-based procedures of Escanciano and Olmo (2010) which are designed to address the issue that classic coverage tests are affected by model misspecification in conditional VaR models.
Reinhart and Rogoff (2008), Bartram and Bodnar (2009) and Bordo and Landon-Lane (2010) provide comparisons of the global financial crisis to other crises. Ben-David et al. (2012), Fratzscher (2012) and Flannery et al. (2013) discuss its consequences for hedge fund stock trading, international capital flows and bank opaqueness, respectively.
Nevertheless, ES has its own shortcomings. For example, it is not consistent with right tail risk as measured by the convex order of degree three (see Hürlimann 2004).
References
Abad P, Benito S, López C (2014) A comprehensive review of value at risk methodologies. Span Rev Financ Econ 12(1):15–32
Alexander C (2008) Market risk analysis. Vol. IV—value-at-risk models. Wiley, Chichester
Anderson S (2013) A history of the past 40 years in financial crises. Int Financ Rev 2000:48–52
Angelidis T, Benos A, Degiannakis S (2004) The use of GARCH models in VaR estimation. Stat Methodol 1(1–2):105–128
Artzner P, Delbaen F, Eber J, Heath D (1999) Coherent measures of risk. Math Financ 9(3):203–228
Auer B (2015) Does the choice of performance measure influence the evaluation of commodity investments? Int Rev Financ Anal 38:142–150
Auer B, Schuhmacher F (2015) Liquid betting against beta in Dow Jones Industrial Average stocks. Financ Anal J 71(6):30–43
Baker GA (1934) Transformation of non-normal frequency distributions into normal distributions. Ann Math Stat 5(2):113–123
Bali T (2003) The generalized extreme value distribution. Econ Lett 79(3):423–427
Bali T (2007) A generalized extreme value approach to financial risk measurement. J Money Credit Bank 39(7):1613–1649
Bali T, Neftci S (2003) Disturbing extremal behavior of spot rate dynamics. J Empir Financ 10(4):455–477
Bali T, Theodossiou P (2007) A conditional-SGT-VaR-approach with alternative GARCH models. Ann Oper Res 151(1):241–267
Bali T, Weinbaum D (2007) A conditional extreme value volatility estimator based on high frequency data. J Econ Dyn Control 31(2):361–397
Bali T, Mo H, Tang Y (2008) The role of autoregressive conditional skewness and kurtosis in the estimation of conditional VaR. J Bank Financ 32(2):269–282
Balkema A, de Haan L (1974) Residual life time at great age. Ann Probab 2(5):792–804
Barone-Adesi G, Giannopoulos K (2001) Non-parametric VaR techniques: myths and realities. Econ Notes 30(2):167–181
Bartram S, Bodnar G (2009) No place to hide: the global crisis in equity markets in 2008/2009. J Int Money Financ 28(8):1246–1292
Basel Committee on Banking Supervision (1995) An internal model-based approach to market risk capital requirements. www.bis.org
Basel Committee on Banking Supervision (1996a) Overview of the amendment to the capital accord to incorporate market risks. www.bis.org
Basel Committee on Banking Supervision (1996b) Supervisory framework for the use of “backtesting” in conjunction with the internal models approach to market risk capital requirements. www.bis.org
Basel Committee on Banking Supervision (2009) Revisions to the Basel II market risk framework. www.bis.org
Basel Committee on Banking Supervision (2011a) Basel III: a global regulatory framework for more resilient banks and banking systems. www.bis.org
Basel Committee on Banking Supervision (2011b) Messages from the academic literature on risk measurement for the trading book. www.bis.org
Baur D, Lucey B (2010) Is gold a hedge or a safe haven? An analysis of stocks, bonds and gold. Financ Rev 45(2):217–229
Baur D, McDermott T (2010) Is gold a safe haven? International evidence. J Bank Financ 34(8):1886–1898
Ben-David I, Franzoni F, Moussawi R (2012) Hedge fund stock trading in the financial crisis of 2007–2009. Rev Financ Stud 25(1):1–54
Berkowitz J (2001) Testing density forecasts with applications to risk management. J Bus Econ Stat 19(4):465–474
Berkowitz J, O’Brien J (2002) How accurate are value-at-risk models at commercial banks? J Financ 57(3):1093–1111
Berkowitz J, Christoffersen P, Pelletier D (2011) Evaluating value-at-risk models with desk-level data. Manag Sci 57(12):2213–2227
Bianchi R, Drew M, Fan J (2015) Combining momentum with reversal in commodity futures. J Bank Financ 59:423–444
Bollerslev T (1986) Generalized autoregressive conditional heteroskedasticity. J Econom 31(3):307–327
Bollerslev T, Chou R, Kroner K (1992) ARCH-modeling in finance: a review of the theory and empirical evidence. J Econom 52(1–2):5–59
Bollerslev T, Engle R, Nelson D (1994) ARCH models. In: Engle R, McFadden D (eds) Handbook of econometrics, vol 4. Elsevier, Amsterdam, pp 2959–3038
Bordo M, Landon-Lane J (2010) The global financial crisis of 2007-08: Is it unprecedented? NBER Working Paper No. 16589
Boulter T, Wongchan V (2013) Thai hedging practices post-Asian financial crisis. Rev Pac Basin Financ Mark Polic 16(1):1350003:1–1350003:25
Bowman K, Shenton L (2004) Johnson’s system of distributions. In: Encyclopedia of statictical sciences. Wiley, New York
Box G, Cox D (1964) An analysis of transformations. J Roy Stat Soc B 26(2):211–252
Brooks C, Clare AD, Dalle Molle JW, Persand G (2005) A comparison of extreme value theory approaches for determining value at risk. J Empir Financ 12(2):339–352
Campbell S (2007) A review of backtesting and backtesting procedures. J Risk 9(2):1–17
Campbell J, Grossman S, Wang J (1993) Trading volume and serial correlation in stock returns. Q J Econ 108(4):905–939
Campbell J, Lo A, MacKinlay A (1997) The econometrics of financial markets. Princeton University Press, Princeton
Campbell R, Huisman R, Koedijk K (2001) Optimal portfolio selection in a value-at-risk framework. J Bank Financ 25(9):1789–1804
Candelon B, Colletaz G, Hurlin C, Tokpavi S (2011) Backtesting value-at-risk: a GMM duration-based test. J Financ Econom 9(2):314–343
Carroll R, Härdle W, Mammen E (2002) Estimation in an additive model when the components are linked parametrically. Econom Theory 18(4):886–912
Castillo E (1988) Extreme value theory in enginering. Academic Press, New York
Chen J (2014) Measuring market risk under the basel accords: VaR, stressed VaR, and expected shortfall. IEB Int J Financ 8:184–201
Chen Y, Lu J (2012) Value at risk estimation. In: Duan J, Härdle W, Gentle J (eds) Handbook of computational finance. Springer, Berlin, pp 307–334
Cheng W, Hung J-C (2011) Skewness and leptokurtosis in GARCH-type VaR estimation of petroleum and metal asset returns. J Empir Financ 18(1):160–173
Christoffersen P (1998) Evaluating interval forecasts. Int Econ Rev 39(4):841–862
Christoffersen P (2003) Elements of financial risk management. Academic Press, New York
Ciner C, Gurdgiev V, Lucey B (2013) Hedges and safe havens: an examination of stocks, bonds, gold, oil and exchange rates. Int Rev Financ Anal 29:202–211
Claessens S, Kose M (2013) Financial crises: explanations, types, and implications. IMF Working Paper No. 13/28
Cont R (2001) Empirical properties of asset returns: stylized facts and statistical issues. Quant Financ 1(2):223–236
Cox D, Hinkley D (1974) Theoretical statistics. Chapman and Hall, London
Danielsson J, de Vries C (2000) Value-at-risk and extreme returns. Ann Econ Stat 60:239–270
Danielsson J, Morimoto Y (2000) Forecasting extreme financial risk: a critical analysis of practical methods for the Japanese market. Monet Econ Stud 18(2):25–48
De Haan L, Resnick S (1980) A simple asymptotic estimate for the index of a stable distribution. J Roy Stat Soc 42(1):83–87
Diebold J, Guégan D (1993) Tail behaviour of the stationary density of general non-linear autoregressive processes of order 1. J Appl Probab 30(2):315–329
Diebold FX, Schuermann T, Stroughair J (2000) Pitfalls and opportunities in the use of extreme value theory in risk management. J Risk Financ 1(2):30–35
Domitrescu E, Hurlin C, Pham V (2012) Backtesting value-at-risk: from dynamic quantile to dynamic binary tests. Finance 33(1):79–122
Dwyer G (September 2009) Stock prices in the financial crisis. Notes from the Vault, Federal Reserve Bank of Atlanta
Efron B (1982) The jackknife, the bootstrap, and other resampling plans. Society for Industrial and Applied Mathematics, Philadelphia
El-Aroui M, Diebold J (2002) On the use of the peaks over thresholds method for estimating out-of-sample quantiles. Comput Stat Data Anal 39(4):453–475
Eling M, Schuhmacher F (2007) Does the choice of performance measure influence the evaluation of hedge funds? J Bank Financ 31(9):2632–2647
Embrechts P, Klppelberg C, Mikosch T (1997) Modelling extremal events: for insurance and finance. Springer, Berlin
Embrechts P, Resnick S, Samorodnitsky G (1999) Extreme value theory as a risk management tool. N Am Actuar J 3(2):30–41
Engle R, Manganelli S (2004) CAViaR: conditional autoregressive value at risk by regression quantiles. J Bus Econ Stat 22(4):367–381
Engle R, Patton A (2001) What good is a volatility model? Quant Financ 1(2):237–245
Escanciano J, Olmo J (2010) Backtesting parametric value-at-risk with estimation risk. J Bus Econ Stat 28(1):36–51
Fan J (1992) Design-adaptive nonparametric regression. J Am Stat Assoc 87:998–1004
Fan J, Yao Q (1998) Efficient estimation of conditional variance functions in stochastic regression. Biometrika 85(3):645–660
Ferreira A, De Haan L (2015) On the block maxima method in extreme value theory: PWM estimators. Ann Stat 43(1):276–298
Fisher RA, Tippett LHC (1928) Limiting forms of the frequency distribution of the largest or smallest member of a sample. Math Proc Camb Philos Soc 24(2):180–190
Flannery M, Kwan S, Nimalendran M (2013) The 2007–2009 financial crisis and bank opaqueness. J Financ Intermed 22(1):55–84
Florence G, Ramachandran K (2011) Estimation of parameters of Johnson’s system of distributions. J Mod Appl Stat Methods 10(2):494–504
Fratzscher M (2012) Capital flows, push versus pull factors and the global financial crisis. J Int Econ 88(2):341–356
Gaglianone W, Lima L, Linton O, Smith D (2011) Evaluating value-at-risk models via quantile regressions. J Bus Econ Stat 29(1):150–160
Gençay R, Selçuk F (2004) Extreme value theory and value-at-risk: relative performance in emerging markets. Int J Forecast 20(2):287–303
Gilli M, Këllezi E (2006) An application of extreme value theory for measuring financial risk. Comput Econ 27(2):207–228
Gnedenko B (1943) Sur La Distribution Limite Du Terme D’une Série Aléatoire. Ann Math 4(3):423–453
Gumbel E (1958) Statistics of extremes. Columbia University Press, New York
Hafner C (1998) Nonlinear time series analysis with applications to foreign exchange rate volatility. Physica, Heidelberg
Hansen B (1994) Autoregressive conditional density estimation. Int Econ Rev 35(3):705–730
Härdle W, Tsybakov A (1997) Local polynomial estimators of the volatility function in nonparametric autoregression. J Econom 81(1):223–242
Hill B (1975) A simple general approach to inference about the tail of a distribution. Ann Stat 3(5):1163–1174
Ho L, Burridge P, Cadle J, Theobald M (2000) Value-at-risk: applying the extreme value approach to Asian markets in the recent financial turmoil. Pac Basin Financ J 8(2):249–275
Hoel P (1954) A test for Markoff chains. Biometrika 41(3/4):430–433
Hosking J (1989) Some theoretical results concerning L-moments. IBM Research Division, Technical Report
Hosking J (1990) L-moments: analysis and estimation of distributions using linear combinations of order statistics. J R Stat Soc B 52(1):105–124
Hosking J, Wallis J (1987) Parameter and quantile estimation for the generalized Pareto distribution. Technometrics 29(3):339–349
Hosking J, Wallis J, Wood E (1985) Estimation of the generalized extreme value distribution by the method of probability weighted moments. Technometrics 27(3):251–261
Hosking J, Wallis J (1997) Regional frequency analysis: an approach based on L-moments. Cambridge University Press, Cambridge
Hsieh D (1993) Implications of nonlinear dynamics for financial risk management. J Financ Quant Anal 28(1):41–64
Hsu C, Huang C, Chiou W (2012) Effectiveness of copula-extreme value theory in estimating value-at-risk: empirical evidence from Asian emerging markets. Rev Quant Financ Acc 39(4):447–468
Huang Y, Lin B (2004) Value-at-risk analysis for Taiwan stock index futures: fat tails and conditional asymmetries in return innovations. Rev Quant Financ Account 22(2):79–95
Huisman R, Koedijk K, Kool C, Palm F (2001) Tail index estimates in small samples. J Bus Econ Stat 19(2):208–216
Hürlimann W (2004) Distortion risk measures and economic capital. N Am Actuar J 8(1):86–96
Hwang S, Vallis Pereira P (2006) Small sample properties of GARCH estimates and persistence. Eur J Financ 12(6–7):473–494
Jenkinson A (1955) The frequency distribution of the annual maximum (minimum) values of meteorological elements. Q J R Meteorol Soc 81(348):158–171
Johnson N (1949) Systems of frequency curves generated by methods of translation. Biometrika 36(1/2):149–176
Jorion P (2007) Value at risk: the new benchmark for managing financial risk, 3rd edn. Mc-Graw-Hill, New York
Jou Y, Wang C, Chiu W (2013) Is the realized volatility good for option pricing during the recent financial crisis? Rev Quant Financ Acc 40(1):171–188
Kinateder H (2016) Basel II versus III—a comparative assessment of minimum capital requirements for internal model approaches. J Risk 18(3):25–45
Kuester K, Mittnik S, Paolella M (2006) Value-at-risk prediction: a comparison of alternative strategies. J Financ Econom 4(1):53–89
Kupiec P (1995) Techniques for verifying the accuracy of risk measurement models. J Deriv 3(2):73–84
Landwehr J, Matalas N, Wallis J (1979) Probability weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles. Water Resour Res 15(5):1055–1064
Lange K, Little R, Taylor J (1989) Robust statistical modeling using the t distribution. J Am Stat Assoc 84(408):881–896
Leadbetter M, Lindgren G, Rootzén H (1983) Extremes and related properties of random sequences and processes. Springer, New York
Lee C, Su J (2012) Alternative statistical distributions for estimating value-at-risk: theory and evidence. Rev Quant Financ Account 39(3):309–331
Linsmeier T, Pearson N (2000) Value at risk. Financ Anal J 56(2):47–67
Linton O, Nielsen J (1995) A Kernel method of estimating structured nonparametric regression based on marginal integration. Biometrika 82(1):93–100
Ljung G, Box G (1978) On a measure of lack of fit in time series models. Biometrika 65(2):297–303
Longin F (2000) From value at risk to stress testing: the extreme value approach. J Bank Financ 24(7):1097–1130
Lopez J (1997) Regulatory evaluation of value-at-risk models. Federal Reserve Bank of New York, Staff Report No. 33
Lopez J (1999) Methods for evaluating value-at-risk estimates. Fed Reserve Bank San Franc Econ Rev 2:3–17
Marimoutou V, Raggad B, Trabelsi A (2009) Extreme value theory and value at risk: application to oil market. Energy Econ 31(4):519–530
Martins-Filho C, Yao F (2006) Estimation of value-at-risk and expected shortfall based on nonlinear models of return dynamics and extreme value theory. Stud Nonlinear Dyn Econom 10(2):1–41 Article 4
McNeil A (1999) Extreme value theory for risk managers. In: Internal modeling and CAD II. Risk Books, London, pp 93–113
McNeil A, Frey R (2000) Estimation of tail-related risk measures for heteroscedastic financial time series: an extreme value approach. J Empir Financ 7(3–4):271–300
Nadarajah S, Zhang B, Chan S (2014) Estimation methods for expected shortfall. Quant Financ 14(2):271–291
Neftci S (2000) Value at risk calculations, extreme events, and tail estimation. J Deriv 7(3):23–37
Ofek E, Richardson M (2003) DotCom mania: the rise and fall of internet stock prices. J Financ 58(3):1113–1137
Oja H (1981) On location, scale, skewness and kurtosis of univariate distributions. Scand J Stat 8(3):154–168
Paolella M (2001) Testing the stable Paretian assumption. Math Comput Modell 34:1095–1112
Patton A (2004) On the out-of-sample importance of skewness and asymmetric dependence for asset allocation. J Financ Econom 2(1):130–168
Pérignon C, Smith D (2010) The level and quality of value-at-risk disclosure by commercial banks. J Bank Financ 34(9–11):362–377
Pflug G, Römisch W (2007) Modeling, measuring and managing risk. World Scientific, Singapore
Pickands J (1975) Statistical inference using extreme order statistics. Ann Stat 3(1):119–131
Pritsker M (2006) The hidden dangers of historical simulation. J Bank Financ 30(2):561–582
Reinhart C, Rogoff K (2008) Is the 2007 US-sub-prime financial crisis so different? An international comparison. Am Econ Rev 98(2):339–344
Resnick S (1987) Extreme values, regular variation, and point processes. Springer, New York
Rocco M (2014) Extreme value theory in finance: a survey. J Econ Surv 28(1):82–108
Ruppert S, Wand M (1995) An effective bandwidth selection for local least squares regression. J Am Stat Assoc 90(432):1257–1270
Scarrott C, MacDonald A (2012) A review of extreme value threshold estimation and uncertainty quantification. REVSTAT Stat J 10(1):33–60
Silvennoinen A, Teräsvirta T (2009) Multivariate GARCH models. In: Anderson T, Davis R, Kreiß J, Mikosch T (eds) Handbook of financial time series. Springer, Berlin, pp 201–229
Smith R (1984) Threshold methods for sample extremes. In: de Oliveira J (ed) Statistical extremes and applications. Springer, Dordrecht, pp 621–638
Smith R (1987) Estimating tails of probability distributions. Ann Stat 15(3):1174–1207
Tauchen G (2001) Notes on financial econometrics. J Econom 100(1):57–64
Taylor N (2014) The rise and fall of technical trading rule success. J Bank Financ 40:286–302
Tsay R (2005) Analysis of financial time series, 2nd edn. Wiley, Hoboken
Vogel R, Fennessey N (1993) L moment diagrams should replace product moment diagrams. Water Resour Res 29(6):1745–1752
von Mises R (1954) La Distribution De La Plus Grande de n Valeurs. In: AMS Selected Papers. Vol. 2. American Statistical Society, Providence, pp 271–294
Wang Q (1990) Estimation of the GEV distribution from censored samples by method of partial probability weighted moments. J Hydrol 120(1–4):103–114
Wong W (2008) Backtesting trading risk of commercial banks using expected shortfall. J Bank Financ 32(7):1404–1415
Wong K, Fan G, Zeng Y (2012) Capturing tail risks beyond VaR. Rev Pac Basin Financ Mark Polic 15(3):1250015:1–1250015:25
Yamai Y, Yoshiba T (2002) Comparative analyses of expected shortfall and value-at-risk: their estimation error, decomposition, and optimization. Monet Econ Stud 20(1):87–122
Yamai Y, Yoshiba T (2005) Value-at-risk versus expected shortfall: a practical perspective. J Bank Financ 29(4):997–1015
Ziggel D, Berens T, Weiß G, Wied D (2014) A new set of improved value-at-risk backtests. J Bank Financ 48:29–41
Acknowledgements
We thank an anonymous reviewer for valuable comments and suggestions. Generous financial support was provided by the Deutsche Bundesbank (Hauptverwaltung in Sachsen und Thüringen).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Human and Animals rights
Our research does not involve human participants and/or animals.
Informed consent
Informed consent is not relevant in the context of our study.
Rights and permissions
About this article
Cite this article
Mögel, B., Auer, B.R. How accurate are modern Value-at-Risk estimators derived from extreme value theory?. Rev Quant Finan Acc 50, 979–1030 (2018). https://doi.org/10.1007/s11156-017-0652-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11156-017-0652-y