應用狀態空間模型與基因類神經網路濾波技術於風險值預測之研究：以台股指數與台指期貨爲例

Using SSM and GANN Filter for an Empirical Investigation of Value at Risk: Taking Taiwan Stock Spot and Futures Indexes as an Example

10.6226/NTURM2010.20.2.307

古永嘉(Yeong-Jia Goo)；許世璋(Shih-Chang Hsu)

類神經網路 ； 狀態空間模型 ； 風險值 ； artificial neural network ； state space model ； value at risk

臺大管理論叢

20卷2期（2010 / 06 / 01）

307 - 342

繁體中文

以往針對風險值的估計，大致以GARCH模型估計波動度後，再以蒙地卡羅模擬法估計風險值績效。本研究延伸過去的方式，試圖以Bi-GARCH模型估計波動度後，分別以狀態空間及基因類神經網路兩種模型，應用於波動度濾化(Filtering)的處理，之後再與傳統GARCH模型，藉由回溯測試以及Kupiec概似比檢定對風險值估計模型的績效進行比較。本研究以台灣發行量加權股價指數與股價指數期貨結算價格為研究標的，取樣期間為2002年1月1日至2004年12月1日之日資料，共計745筆。研究發現，無論在台股指數現貨或期貨，經由狀態空間與基因類神經網路濾化後之風險值的模式績效，不論短長期或多空階段之評比，皆遠優於傳統估算法。

Previous researchers usually use GARCH models in estimating volatility in evaluating value at risk (VaR) performance. In this study, Bi-GARCH models were adopted in estimating volatility. The estimated volatility is then filtered by using both State Space Models (SSM) and Generic Algorithm-Artificial Neural Network (GANN) models. The VaR performances of these models are compared using back-testings and Kupiec likelihood tests. A total of 745 daily data of Taiwan stock indexes of spot and futures ranging from Jan. 2, 2002 to Dec. 31, 2004 were collected. The results show that the filtered GANN and SSM models are better then traditional estimation methods for the evaluation of VaR for both stock spot and futures indexes.

1. Akaike, H.(1976).Canonical correlations analysis of time series and the use of an information criterion.New York, NY:Academic Press.
2. Akgiray, V.(1989).Conditional heteroskedasticity in time series of stock returns: Evidence and forecasts.Journal of Business,62(1),55-80.
3. Alexander, C. O.,Leigh, C. T.(1997).On the covariance matrices used in value at risk models.Journal of Derivatives,4(3),50-62.
4. Andersen, T. G.,Bollerslev, T.(1998).Answering the skeptics: Yes, standard volatility models do provide accurate forecasts.International Economic Review,39(4),885-905.
5. Bachman, D.,Choi, J. J.,Jeon, B. N.,Kopecky, K. J.(1996).Common factor in international stock prices: Evidence from a cointegration study.International Review of Financial Analysis,5(1),39-53.
6. Ball, C. A.,Torous, W. N.(2000).Stochastic correlation across international stock markets.Journal of Empirical Finance,7(3/4),373-388.
7. Beder, T. S.(1995).VaR: Seductive but dangerous.Financial Analysts Journal,51(5),12-24.
8. Berndt, E. K.,Hall, B. H.,Hall, R. E.,Hausman, J. A.(1974).Estimation and inference in nonlinear structural model.Annals of Economic and Social Measurement,3(4),653-665.
9. Bollerslev, T.(1986).Generalized autoregressive conditional hetreoscedasticity.Journal of Econometrics,31(2),307-327.
10. Brooks, C.,Persand, G.(2003).Volatility forecasting for risk management.Journal of Forecasting,22(1),1-22.
11. Chang, K. H.,Wu, C. S.(1998).A gray time series model on forecasting the Chinese New Year effect in the Taiwan stock market.Journal of Gray System,1(1),55-63.
12. Chu, S. H.,Freund, S.(1996).Volatility estimation for stock index options: A GARCH approach.Quarterly Review of Economics and Finance,36(4),431-450.
13. Figlewski, S.(1997).Forecasting volatility.Financial Markets, Institutions and Instruments,6(1),1-88.
14. Figlewski, S.,Green, T. C.(1999).Market risk and model risk for a financial institution writing options.Journal of Finance,54(4),1465-1499.
15. Gloria, G. R.,Lee, T. H.,Mishra, S.(2004).Forecasting volatility: A reality check based on option pricing, utility function, value-at-risk, and predictive likelihood.International Journal of Forecasting,20(4),629-645.
16. Granger, C.,Poon, S.(2003).Forecasting volatility: A survey.Journal of Economic Literature,41(2),478-539.
17. Hendricks, D.(1996).Evaluation of value-at-risk models using historical data.Economic Policy Review,2(1),39-70.
18. Jackson, P.,Maude, D. J.,Perraudin, W.(1997).Bank capital and value at risk.Journal of Derivative,4(3),73-90.
19. Kalman, R. E.(1960).A new approach to linear filtering and prediction problems.ASME Journal of Basic Engineering,83(1),34-45.
20. Koutmons, G.,Tucker, M.(1996).Temporal relationship and dynamic interactions between spot and futures stock markets.Journal of Future Markets,16(1),55-69.
21. Kupiec, P. H.(1995).Techniques for verifying the accuracy of risk measurement models.Journal of Derivatives,3(2),73-84.
22. Lam, M.(2004).Neural network techniques for financial performance prediction: Integrating fundamental and technical analysis.Decision Support Systems,37(4),567-581.
23. Lee, W. C.(2006).Forecasting high-frequency financial data volatility via nonparametric algorithms-evidence from Taiwan financial markets.New Mathematics and Natural Computation,2(3),345-359.
24. Morgan Guaranty Trust Company of New York(1996).Riskmetrics-technical document.New York, NY:Morgan Guaranty Trust Company of New York.
25. Rumelhart, D. E.(ed.),McClelland, J. L.(ed.)(1986).Parallel distributed processing: Explorations in the microstructures of cognition.Cambridge, MA:MIT Press.
26. Tam, K. Y.,Kiang, M. Y.(1992).Managerial application of neural networks: The case of bank failure predictions.Management Science,38(7),926-947.
27. Venkatarman, S.(1997).Value at risk for mixture of normal distribution: The use of quasi-bayesian estimation techniques.Economic Perspectives,23(1),2-13.
28. 王倩茵(2003)。國立臺灣大學商學研究所=Graduate Institute of Business Administration, NTU。
29. 古永嘉、萬文隆(2002)。兩岸三地連動之研究：狀態空間模型之應用。證券櫃檯月刊，70，48-65。
30. 沈大白、柯瓊鳳、鄒武哲(1998)。風險值衡量模式之探討：以台灣上市公司權並證券為例。東吳經濟學報，22，57-76。
31. 林保霖(2002)。國立台北大學企業管理學系=Department of Business Administration, NTPU。
32. 翁勝彬(1996)。東吳大學經濟系=Department of Economics, SCU。
33. 張簡彰程(2001)。義守大學管理科學研究所=Department of Industrial Engineering and Management, ISU。
34. 陳宜玫(2000)。義守大學管理科學研究所=Department of Industrial Engineering and Management, ISU。