Abstract
A traditional Monte Carlo simulation using linear correlations induces estimation bias in measuring portfolio value-at-risk (VaR), due to the well-documented existence of fat-tail, skewness, truncations, and non-linear relations in return distributions. In this paper, we consider the above issues in modeling VaR and evaluate the effectiveness of using copula-extreme-value-based semiparametric approaches. To assess portfolio risk in six Asian markets, we incorporate a combination of extreme value theory (EVT) and various copulas to build joint distributions of returns. A backtesting analysis using a Monte Carlo VaR simulation suggests that the Clayton copula-EVT evinces the best performance regardless of the shapes of the return distributions, and that in general the copulas with the EVT provide better estimations of VaRs than the copulas with conventionally employed empirical distributions. These findings still hold in conditional-coverage-based backtesting. These findings indicate the economic significance of incorporating the down-side shock in risk management.
Similar content being viewed by others
Notes
To prevent unreasonably large price movements on the market, several emerging markets impose limitations on daily stock price movements, meaning that the change in an individual stock in each trading day cannot exceed a certain fixed percentage point in comparison with the previous day’s closing price. For instance, in Taiwan, the change in a stock price cannot exceed 7%, and the ceiling in Korea is 15%. With this sort of imposed narrow price range on its stock market, a country’s stock return distribution is easily truncated so as to have no distribution tail.
According to Yang and Lim (2004) capital flows to the East Asian economics have steadily increased in 1990s. Although the capital flows turned to weak in 1998 due to the financial crisis, the flows resumed and remain strong since 1999.
Lee and Tan (1999) pointed out that during the early stage of the currency turmoil, most central banks tend to opt for market interventions in support of the sudden depreciation of the local currency value.
See Nelsen (2006) for a detailed derivation.
See Embrechts et al. (2005) for a detailed derivation.
Since the six countries have their own business days, the number of observations varied for each country. Indonesia had 1,957 observations, Korea had 1,968 observations, Malaysia had 1,967 observations, Singapore had 2,004 observations, Taiwan had 1,997 observations, and Thailand had 1,961 observations.
In general there are 250 business days in a year. As explained in the previous footnote, the length of the data in each country is from 1957 to 2004 days; therefore, each model generates from 1707 to 1754 dynamic VaRs.
To present the results in their corresponding p values, we applied a one-tail hypothesis. Thus, if the observed number of violations is lower than the expected number, we test whether the observed number is higher than the lower bound of the 95% confidence interval, while if the observed number of violations is higher than the expected number, we test whether the observed number of violations is lower than the upper bound of the 95% confidence interval.
The situation of Korea is not applicable to the IND and CC tests, because in the results for Korea there exists no π11.
References
Aggarwal R, Mougoue M (1998) Common stochastic trends among Asian currencies: evidence for Japan, Asians, and the Asian Tigers. Rev Quant Financ Acc 10:193–206
Ajayi R, Mougoué M (1996) On the dynamic relationship between stock prices and exchange rates. J Financ Res 19:193–207
Ang A, Chen J (2002) Asymmetric correlations of equity portfolios. J Financ Econ 63:443–494
Angelidis T, Benos A, Degiannakis S (2007) A robust VaR model under different time periods and weighting schemes. Rev Quant Financ Acc 28:187–201
Baixauli JS, Alvarez S (2006) Evaluating effects of excess kurtosis on VaR estimates: evidence for international stock indices. Rev Quant Financ Acc 27:27–46
Bali T (2007) A generalized extreme value approach to financial risk measurement. J Money Credit Bank 39:1613–1649
Balkema A, De Haan L (1974) Residual life time at great age. Ann Probab 2:792–804
Bartram S, Taylor S, Wang Y (2007) The Euro and European financial market dependence. J Bank Financ 31:1461–1481
Beirlant J, Goegebeur Y, Segers J, Teugels J (2004) Statistics of extremes: theory and applications. Wiley, West Sussex, p 13
Boyer B, Gibson M, Loretan M (1999) Pitfalls in tests for changes in correlations. Board of Governors of the Federal Reserve System, International Finance Discussion Papers No. 597R, p. 5
Chen X, Fan Y (2006) Estimation of copula-based semiparametric time series models. J Econom 130:307–335
Cherubini U, Luciano E, Vecchiato W (2004) Copula methods in finance. Wiley, Hoboken, NJ
Christoffersen P (1998) Evaluating international forecasts. Int Econ Rev 39:841–862
Coles S (2001) An introduction to statistical modeling of extreme values. Springer, Berlin
Da Silva A, Mendes B (2003) Value-at-risk and extreme returns in Asian stock markets. Int J Bus 8:17–40
Doidge C, Griffin J, Williamson R (2006) Measuring the economic importance of exchange rate exposure. J Empir Financ 13:550–576
Embrechts P, Lindskog F, McNeil A (2003) Modeling dependence with copulas and applications to risk management. Handbook of heavy tailed distributions in finance. Elsevier, Amsterdam
Embrechts P, Frey R, McNeil A (2005) Quantitative risk management. Princeton University Press, Princeton
Engle R (2002) Dynamic conditional correlation: a simple class of multivariate GARCH models. J Bus Econ Stat 20:339–350
Engle R, Colacito R (2006) Testing and valuing dynamic correlations for asset allocation. J Bus Econ Stat 24:238–253
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 8:249–275
Hotta L, Lucas E, Palaro H (2006) Estimation of VaR using copula and extreme value theory, working paper. State University of Campinas, Campinas SP, Brazil
Joe H (1997) Multivariate models and dependence concepts. Chapman & Hall/CRC, New York
Joe H, Xu J (1996) The estimation method of inference functions for margins for multivariate models. Department of Statistics, University of British Columbia, technical report 166
Jondeau E, Rockinger M (2006) The copula-GARCH model of conditional dependencies: an international stock market application. J Int Money Financ 25:827–853
Jorion P (2007) Value-at-risk: the new benchmark for managing risk. McGraw-Hill, New Jersey
Kolari J, Moorman T, Sorescu S (2008) Foreign exchange risk and the cross-section of stock returns. J Int Money Financ 27:1074–1097
Kole E, Koedijk K, Verbeek M (2007) Selecting copulas for risk management. J Bank Financ 31:2405–2423
Lee CF, Tan KG (1999) Coping with capital mobility and the evolving financial architecture: the Southeast-Asian perspective. Rev Pac Basin Financ Mark Policies 2:231–264
Lin CH, Chien CC, Chen S (2006) Incorporating the time-varying tail-fatness into the historical simulation method for portfolio value-at-risk. Rev Pac Basin Financ Mark Policies 9:257–274
Longin F (2000) From value at risk to stress testing: the extreme value approach. J Bank Financ 24:1097–1130
Longin F, Solnik B (2001) Extreme correlation of international equity. J Financ 56:649–676
McNeil A, Frey R (2000) Estimation of tail-related risk measures for heteroscedastic financial time series: an extreme value approach. J Empir Financ 7:271–300
Mendes B, Martins de Souza R (2004) Measuring financial risks with copulas. Int Rev Financ Anal 13:27–45
Neftci S (2000) Value at risk calculations, extreme events, and tail estimation. J Deriv 7:23–38
Nelsen R (2006) An introduction to copulas. Springer, New York
Okimoto T (2008) New evidence of asymmetric dependence structures in international equity markets. J Financ Quant Anal 43:787–815
Palaro H, Hotta L (2006) Using conditional copulas to estimate value at risk. J Data Sci 4:93–115
Patro D, Wald J, Wu Y (2002) Explaining exchange rate risk in world stock markets: a panel approach. J Bank Financ 26:1951–1972
Patton A (2006a) Modeling asymmetric exchange rate dependence. Int Econ Rev 47:527–556
Patton A (2006b) Estimation of multivariate models for time series of possibly different lengths. J Appl Econom 21:147–173
Pickands J (1975) Statistical inference using extreme order statistics. Ann Stat 3:119–131
Rodriguez J (2007) Measuring financial contagion: a copula approach. J Empir Financ 14:401–423
Silvennoinen A, Teräsvirta T (2009) Modeling multivariate autoregressive conditional heteroskedasticity with the double smooth transition conditional correlation GARCH model. J Financ Econom 7:373–411
Solnik B (1987) Using financial prices to test exchange rate models. J Financ 42:141–149
Straetmans S, Verschoor W, Wolff C (2008) Extreme US stock market fluctuations in the wake of 911. J Appl Econom 23:17–42
Tastan H (2006) Estimating time-varying conditional correlations between stock and foreign exchange markets. Phys A Stat Mech Appl 360:445–458
Tsafack G (2009) Asymmetric dependence implications for extreme risk management. J Deriv 17:7–20
Wand MP, Jones MC (1995) Kernel smoothing. Chapman & Hall, London
Yang T, Lim J (2004) Crisis, contagion, and East Asian stock markets. Rev Pac Basin Financ Mark Policies 7:119–151
Zivot E, Wang J (2006) Modeling financial time series with S-Plus. Springer, New York
Acknowledgments
The authors thank Cheng-Few Lee (Editor-in-Chief) and an anonymous referee for their comments and suggestions. We are also grateful for comments and suggestions from Raj Aggarwal, Peter Chow, Harry Rosen, and seminar participants at The Graduate Center of City University of New York and at the EFA and the PBFEAM meetings. All remaining errors are our own.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hsu, CP., Huang, CW. & Chiou, WJ.P. Effectiveness of copula-extreme value theory in estimating value-at-risk: empirical evidence from Asian emerging markets. Rev Quant Finan Acc 39, 447–468 (2012). https://doi.org/10.1007/s11156-011-0261-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11156-011-0261-0