ALTERNATIVE APPROACHES TO ESTIMATING VAR FOR HEDGE FUND PORTFOLIOS Turan G. Bali and Suleyman Gokcan
INTRODUCTION
NonNormally distributed returns are the norm in financial return series. The most widely documented departure from Normality is too many large returns, both positive and negative (and high autocorrelation in large returns). This nonNormal reality is a problem for traditional parametric risk measurement, which relies on the assumption of Normality.
If returns were Normally distributed, then a 2.5 daily standard deviation loss event would happen about one day a year. In practice, a rule of thumb is to expect a 4 standard deviation loss event about once a year.
Bali and Gokcan put forward an alternative parametric approach to VaR estimation that is robust to these types of deviations from the Normal probability distribution.
In the usual parametric VaR calculation, the standard deviation of portfolio returns is multiplied by a constant, e.g., 2.33, which is based on the known quantiles of the Normal distribution. In their alternative method, this multiplicative constant is modified to incorporate information about the skewness and excess kurtosis in the return distribution.
Bali and Gokcan examine the returns to 17 hedge fund strategy indexes, all of which exhibit statistically significant departures from Normality, including the negative skewness we have come to expect in hedge fund returns.
They show that their alternative to the standard parametric VaR results in a very close correspondence to the empirically observed tail percentiles they examine, much closer than the usual parametric approach, which significantly underestimates the empirical tail percentile. Their estimates are also better than when they estimate VaR using an extreme value approach, a result they argue that is further enhanced by the greater ease of applying their approach.
return to top
BIBLIOGRAPHY
 Agarwal, V., and N. Naik, 2000, “Performance Evaluation of Hedge Funds with Option Based and BuyandHold Strategies.” Review of Financial Studies, 17(1), pp. 6398.
http://www.GloriaMundi.org/picsresources/rbvann.pdf
 Amin G., and Kat H., 2003. "Hedge Fund Performance 19902000: Do The “Money Machines” Really Add Value?" Journal of Financial and Quantitative Analysis 38, pp. 251274.
http://www.GloriaMundi.org/picsresources/rbgahk.pdf
 Andersen, T. G., T. Bollerslev, and S. Lange, 1999. “Forecasting Financial Market Volatility: Sampling Frequency visàvis Forecast Horizon,” Journal of Empirical Finance 6(5), 457477.
 Asness, C. S., R. J. Krail, and J. M. Liew, 2001. “Do Hedge Funds Hedge?” Journal of Portfolio Management, Fall, pp. 619.
 Bali, T. G., 2003, “An Extreme Value Approach to Estimating Volatility and Value at Risk,” Journal of Business, 76(1), pp. 83108.
http://www.GloriaMundi.org/picsresources/rbtb.pdf
 Castillo, E., 1988, Extreme Value Theory in Engineering, (San Diego: Academic Press).
view at Amazon.com
 Cornish, E.A., and Fisher, R.A., 1937, “Moments and Cumulants in the Specification of Distributions.” Review of the International Statistical Institute, pp. 307320.
 De Souza C., and Gokcan S., 2004, "Allocation Methodologies and Customizing Hedge Fund MultiManager MultiStrategy Products." Journal of Alternative Investments, 6(4), pp. 721.
 Dickey, D., and W. A. Fuller, 1979, “Distribution of the Estimates for Autoregressive Time Series with a Unit Root,” Journal of the American Statistical Association, 74, pp. 427431.
 Dowd, K., 1998, Beyond Value at Risk: The New Science of Risk Management (John Wiley & Sons).
vivw at Amazon.com
 Duffie, D., and J. Pan, 1997, “An Overview of Value at Risk.” Journal of Derivatives (Spring), pp. 749.
 Embrechts, P., C. Kluppelberg, and T. Mikosch, 1997, Modeling Extremal Events (Berlin: SpringerVerlag).
view at Amazon.com
 Fung, W., and D. A. Hsieh, 1999, "Is MeanVariance Analysis Applicable to Hedge Funds," Economics Letters 62, 5358.
http://www.GloriaMundi.org/picsresources/rbfh.pdf
 Geman, H., and Kharoubi, C., 2003, “Hedge Funds Revisited: Distributional Characteristics, Dependence Structure and Diversification,” Journal of Risk, 5(4).
 Gourieroux, C., and J. Jasiak, 1999, “Truncated Local Likelihood and Nonparametric Tail Analysis,” DP 99, CREST.
 Gourieroux, C., Laurent, J. P., and O. Scaillet, 2000, “Sensitivity Analysis of Values at Risk,” Journal of Empirical Finance 7, pp. 225245.
http://www.GloriaMundi.org/picsresources/rbgour.pdf
 Gumbell, E.J., 1958, Statistics of Extremes (New York: Columbia University Press).
view at Amazon.com
 Gupta, A., and B. Liang, 2001, “Do Hedge Funds Have Enough Capital? A Value at Risk Approach,” Working Paper, Case Reserve Western University.
http://www.GloriaMundi.org/picsresources/rbgbl.pdf
 Harrel, F., and C. Davis, 1982, “A New Distribution Free Quantile Estimation,” Biometrica 69, pp. 635640.
 Hull, J, and A. White, 1998, “Value at Risk When Daily Changes in Market Variables Are Not Normally Distributed.” Journal of Derivatives, 5(3), pp. 919.
http://www.GloriaMundi.org/picsresources/rbhw.pdf
 Jorion, P., 1996, “Risk^{2}: Measuring the Risk in Value at Risk,” Financial Analysts Journal, 52, pp. 4756.
 Jorion, P., 2000, “Risk Management Lessons From Long Term Capital Management,” European Financial Management 6, pp. 277300.
http://www.GloriaMundi.org/picsresources/pjltm.pdf
 Jorion, P., 2001, ValueatRisk: The New Benchmark for Controlling Market Risk (Chicago: McGrawHill).
 Leadbetter, M.R., G., Lindgren, and H.Rootzen, 1983, Extremes and Related Properties of Random Sequences and Processes (New York: SpringerVerlag).
 Longin, F. M., 2000, “From Value at Risk to Stress Testing: The Extreme Value Approach,” Journal of Banking and Finance 24(7), pp. 10971130.
 McNeil, A. J., and R. Frey, 2000, “Estimation of TailRelated Risk Measures for Heteroscedastic Financial Time Series: An Extreme Value Approach.” Journal of Empirical Finance, 7, pp. 271300.
 Pickands, J., 1975, “Statistical Inference Using Extreme Order Statistics.” Annals of Statistics 3, pp. 119131.
 Venkataraman, S., 1997, “Value at Risk for a Mixture of Normal Distributions: The Use of QuasiBayesian Estimation Techniques.” Economic Perspectives, Federal Reserve Bank of Chicago, (March/April), pp. 213.
http://www.GloriaMundi.org/picsresources/rbsubu.pdf
return to top
ERRATA AND OTHER MATERIAL
 Other research by Turan G. Bali:
SSRN website
 Homepage of Turan G. Bali:
http://faculty.baruch.cuny.edu/tbali/
return to top
