這篇論文主要在研究S&P 500 Index and Index Future兩市場間的互動關係, 並利用ECM-EGARCH與人工智慧模型進行價格預測, 再進一部比較各個模型的預測能力.

　　經過實證結果顯示:
1. S&P500 指數和指數期貨兩個市場長期存在共整合的關係. 換句話說, 兩市場長期會達到一個穩定的均衡.
2.兩市場的價格變動短期存在著互相領先與落後的關係, 而長期兩市場是彼此交互影響
3.在S&P500指數期貨價格預測的精準性測試中,基因演算法和類神經網路都比EGARCH好. 而現貨價格的預測, 則是類神經網路比基因演算法和EGARCH好
4.在S&P500指數期貨和現貨的方向性預測測試中,基因演算法的預測能力最好

Abstract
　　This paper is mainly to explore the lead-lag relationship of prices changes, the dynamic interactions between spot and futures market and the predicting ability of ECM combined with EGARCH, Genetic Algorithm, and Back-Propagation Network respectively by using intraday data of the S&P500 index and the index futures in CME. All tests start from the stationary test. When the time series of the two markets are stationary in the same orders, we examine whether a long-run equilibrium exists between the two markets via the cointegration test applied by Johansen in 1988. And then we explore further the interactions of the first-movement between spot and futures market by using the bivariate EC-EGARCH models. Therefore, we can understand the interactions of prices changes between the S&P500 spot and index futures market from 1983 to 1998.

　　The empirical results from this study are summarized as follows：
1. There is a long-run cointegrated relationship between the S&P500 spot and index futures market.
2. The feedback phenomenon of lead-lag relationship of prices changes exists between the S&P500 spot and index futures market in the short term, but in the long-term, they will affect mutually.
3. The accuracy of predicting price of EC-EGARCH combined GA and BNP are better than EC-EGARCH, and the accuracy of predicting price of EC-EGARCH combined GA and BNP are not much different.
4. The accuracy of predicting price of EC-EGARCH combined BNP are better than EC-EGARCH combined GA, and the accuracy of the predicting price of EC-EGARCH combined GA is better than EC-EGARCH.
5. The actuality of the predicting direction for the S&P 500 index future by EC-EGARCH+GA is better than EC-EGARCH during the period between 1983 and 1986, the period between 1987 and 1990, and the period between 1995 and 1998. And the actuality of the predicting direction for the S&P 500 index future by EC-EGARCH+GA is better than EC-EGARCH+BPN during the period between 1991 and 1995.
6. The degree of correct of the predicting direction for the S&P 500 index by EC-EGARCH+GA is better than EC-EGARCH during the period between 1987 and 1990, the period between 1991 and 1994, and the period between 1995 and 1998. But the actuality of the predicting direction for the S&P 500 index by EC-EGARCH+GA is as the same as EC-EGARCH+BPN during the four periods.

Akaike, Hizotogu, ‘fitting autoregressive Model for Prediction,’ Annals of Institute of Statistical Mathematics January 1969, pp.243-247.
Abhyankar, A.H., “Return and Volatility Dynamics in the FT-SE 100 Stock Index and Stock Index Futures Markets.” Journal of Futures Market, 15, 1995, pp.457-488.
Alan, L.Tucker ,“Financial Futures, Option, & Swaps” West Publishing Company first edition, 1992.
Antoniou, A.and Holmes,P., “Futures Trading, Information and Spot Price Volatility: Evidence for the FTSE-100 Stock Index Futures Contract Using GARCH.” Journal of Banking and Finance, 19, 1995, pp.117-129.
Bisignano, W.H., “Assets Markets and Relative Prices inExchange Rate Determination, “ Sozialaissenschaftliche Annalen, 1977, pp.69-89
Bollerslev, T., “Generalized Autoregressive Conditional Heteroskedasticity.” Journal of Econometrics, 31, 1986, pp.307-327.
Chan, K.,Chan K.C.and Karolyi G.A., “Intraday of Volatility in the Stock Index and Stock Futures Markets.” The Review of Financial Studies, 4, 1991, pp.657-684.
Dickey, D.A. and Fuller W.A., “Distribution of the Estimators for Autoregressive Time Series with a Unit Root.” Journal of the American Statistics Association, 74, 1979, pp.427-431.
Dickey, D.A. and Fuller W.A., “The Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root.” Econometrica, 1981, pp.1057-1072.
Engle, R.F. and Granger C.W.J., “Co-integration and an Error Correction : Representation, Estimation and Testing.” Econometrica, 55, 1987, pp.251-276.
Granger, C.W.J., “Investigating Causality Relations by Econometric Models and Cross-Spectral Methods.” Journal of Econometrics, 37, 1969, pp.424-438.
Granger, C.W.J., “Testing for Causality-A Personal Viewpoint” Journal of Economic Dynamics and Control, 2, 1980, pp.329-352.
Harris, L., “The October 1987 S&P 500 Stock-Futures Basis.” The Journal of Finance, 44, 1989, pp.77-99.
Iihara, Y., Kato K. and Tokunaga T., “Intraday Return Dynamics between the Cash and the Futures Markets in Japan.” The Journal of Futures Markets, 2, 1996, pp.147-162.
Johansen, Soren and Juselius Katarina, “Maximum Likelihood Estimation and Inference on Cointegration with Application to the Demand for Money Vector.” Oxford Bulletin of Economics and Statistics, 52(2), 1990, pp.169-210.
Johansen, Soren ,“Statistical Analysis of Cointegration Vector., ” Journal of Economics Dynamics and Control, 12, 1988, pp.231-254.
Kawaler, I.G., Koch P.D. and Koch T.W., “Intraday Relationships between Volatility in S&P500 Futures Prices and Volatility in the S&P500 Index.” Journal of Banking and Finance, 14, 1990, pp.373-397.
Koutmos, G. and Tucker M., “Temporal Relationships and Dynamics Interactions between Spot and Futures Stock Markets.” Journal of Futures Markets, 16(1), 1996, pp.55-69.
Nelson, D.B, “Conditional Heteroskedasticity in Asset Returns : A New Approach.” Econometrica, 59, March 1991, pp.2347-370.
Stoll, H.R. and Whaley R.E., “The Dynamics of Stock Index and Stock Index Futures Returns.” Journal of Financial and Quantitative Analysis, 25, Dec.1990, pp.441-468.