臺灣博碩士論文加值系統

一般化自我迴歸條件異質變異數模型可對條件分配做不同的假設，本研究比較在不同條件分配假設下，它們在模型配適、波動度預測、與價格分配預測上的表現。我們對模型假設了三種不同的條件分配：常態分配、偏斜 t 分配、與複合卜瓦松(跳躍)分配，以捕捉資產報酬的一般特性。實證分析建立在非線性不對稱一般化自我迴歸條件異質變異數模型的基礎上，並以S&P 500與FTSE 100指數為實證資料。實證結果顯示，在模型配適上的表現，跳躍模型與偏斜 t 模型較常態模型為優；但這樣的優勢不見於低波動度期間。在波動度預測上，跳躍模型表現最佳。而在價格分配預測上，雖然三者差異不多，但跳躍模型與偏斜 t 模型的預測仍比常態模型精確。

This study compares the performance of alternative GARCH models with different conditional distributions on model fitting, volatility forecasting, and density prediction. Three conditional distributions: normal, skewed-t, and compound Poisson, are assumed in order to model the stylized facts of returns in the stochastic innovation. Based on the NGARCH framework, parameters are estimated from the S&P 500 index and FTSE 100 index. The empirical results suggest that the NGARCH-jump model and the NGARCH-skewed-t model significantly raise performance in terms of model fitting, but the differences diminish when models are estimated in relatively low-volatility periods. In volatility forecasting, the NGARCH-jump model outperforms the others. Although the differences are not significant, the skewed-t model and the jump model provide more accurate estimated densities than the normal model.

1.Introduction--------------------------------------------1
2. Literature Review--------------------------------------4
3. The Empirical Models-----------------------------------6
3.1 The NGARCH Model with Normal Innovations----------6
3.2 The NGARCH Model with a Skewed Student t Distribution----------------------------------------------7
3.3 The NGARCH Model with Jump Dynamics---------------9
4. Performance Measures----------------------------------12
4.1 Model Fitting------------------------------------12
4.2 Volatility Forecasting---------------------------14
4.3 Density Prediction-------------------------------17
5. Data--------------------------------------------------21
6. Empirical Results-------------------------------------25
6.1 Model Fitting------------------------------------25
6.2 Volatility Forecasting---------------------------30
6.3 Density Prediction-------------------------------35
7. Conclusions-------------------------------------------40
Reference------------------------------------------------42
Appendix-------------------------------------------------44

[1] Akgiray, V. (1989), ‘Conditional Heteroscedasticity in Time Series of Stock Returns: Evidence and Forecast’, Journal of Business, 62: 55-80.
[2] Andersen, T. G., T. Bollerslev, F. X. Diebold and H. Ebens (2001), ‘The Distribution of Realized Stock Return Volatility’, Journal of Financial Economics, 61: 43-76.
[3] Berkowitz, J. (2001), ‘Testing Density Forecasts, With Applications to Risk Management’, Journal of Business and Economic Statistics, 19: 465-474.
[4] Blair, B. J., S. H. Poon and S. J. Taylor (2001), ‘Forecasting S&P 100 Volatility: The Incremental Information Content of Implied Volatilities and High-frequency Index Returns’, Journal of Econometrics, 105: 5-26.
[5] Bollerslev, T. (1986), ‘Generalized Autoregressive Conditional Heteroskedasticity’, Journal of Econometrics, 31: 307-327.
[6] Bollerslev, T. (1987), ‘A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return’, Review of Economics and Statistics, 69: 542-547.
[7] Chan, W. H. and J. M. Maheu (2002), ‘Conditional Jump Dynamics in Stock Market Returns’, Journal of Business and Economic Statistics, 20: 377-389.
[8] Christoffersen, P. and K. Jacobs (2004), ‘Which GARCH Model for Option Valuation?’, Management Science, 50: 1204-1221.
[9] Diebold, F. X., T. A. Gunther and A. S. Tay (1998), ‘Evaluating Density Forecasts with Applications to Financial Risk Management’, International Economic Review, 39: 863-883.
[10] Duan, J. C., P. Ritchken and Z. Sun (2005), ‘Jump Starting GARCH: Pricing and Hedging Options with Jumps in Returns and Volatilities’, Working paper, Toronto University.
[11] Duan, J. C., P. Ritchken and Z. Sun (2006), ‘Approximating GARCH-jump Model, Jump-diffusion Processes and Option Pricing’, Mathematical Finance, 16: 21-52.
[12] Engle, R. F. (1982), ‘Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation’, Econometrica, 50: 987-1007.
[13] Engle, R. F. and V. K. Ng (1993), ‘Measuring and Testing the Impact of News on Volatility’, Journal of Finance, 48: 1749-1778.
[14] Glosten, L. R., R. Jagannathan and D. E. Runkle (1993), ‘On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks’, Journal of Finance, 48: 1779-1801.
[15] Hensen B. E. (1994), ‘Autoregressive Conditional Density Estimation’, International Economic Review, 35: 705-730.
[16] Maheu, J. M. and T. H. McCurdy (2004), ‘News Arrival, Jump Dynamics, and Volatility Components for Individual Stock Returns’, Journal of Finance, 59: 755-793.
[17] Nelson, D. B. (1991), ‘Conditional Heteroscedasticity in Asset Returns: A New Approach’, Econometrica, 59: 347-370.
[18] Poon, S. H. and C. W. J. Granger (2003), ‘Forecasting Financial Market Volatility: A Review’, Journal of Economic Literature, 41: 478-539.
[19] Press, S. J. (1967), ‘A Compound Events Model for Security Prices’, Journal of Business, 40: 317-335.
[20] Taylor, S. J. (2005), Asset Price Dynamics, Volatility, and Prediction, Princeton and Oxford: Princeton University Press.
[21] Wang, Y. H. (2006), ‘The Impact of Jump Dynamics on Density Prediction’, Working paper, National Central University.
[22] Wang, Y. H. and C. C. Hsu (2007), ‘Short-memory, Long-memory and Jump Dynamics in Global Financial Markets’, Journal of Financial Studies, 15: 43-68.