投資人在建構投資組合時，若投資標的不多，使用單一模型便可將各資產報酬的預測做得非常好。但當投資組合變得龐大時，在實務上可能沒有任何單一模型所做出來的結果是令人滿意的。因此，Pesaran,  Schleicher and Zaffaroni(2008)以AIC及SBC值篩選出表現較好的數個單一模型來建構平均模型，解決了單一模型在龐大資產下表現不佳的問題。本研究沿用平均模型的想法，但利用兩個不同的篩選模型準則來建構平均模型。最後經實證結果顯示，此兩個篩選準則下所建構的平均模型在VaR回顧測試的表現的確優於任何單一模型。為了測試平均模型的實用性，本研究期間歷經數次重大金融危機，挑選的標的資產也為重要被影響的市場，投資組合中標的資產彼此間正相關度也相當的高。在面臨雞蛋放在同一個籃子裡的投資組合且標的資產皆為空頭的投資波段中，本研究將平均模型於風險值限制式限制下，透過效用函數極大化計算各標的資產的動態投資權重並套用於實證數據，若不考慮交易成本，所做出來的結果能在這段期間內創造近一倍的收入。但同期間若單獨投資各標的資產的情況下，皆是呈現負報酬。因此，平均模型於龐大資產組合下不僅有良好的風險捕捉能力，透過效用函數與風險值限制式的結合，更可創造出合理的獲利空間。

The paper follows Pesaran, Schleicher and Zaffaroni(2008)'s spirit to consider the problem of model uncertainty in the case of multi-asset volatility models and discusses the use of model averaging techniques as a way of dealing with the risk of inadvertently using false models in portfolio management. We adopt model selection criteria of Kupiec’s(1995) LR value of likelihood ratio test or missing times of VaR backtesting other than the minimum AIC or SBC value. The model averaging idea and the VaR diagnostic tests are illustrated by an application to portfolios of daily reurns on two stock index and four future contracts. The empirical evidence supports the use of model averaging strategies dominate single models.

目錄----------------------------------------------------- I
圖目錄--------------------------------------------------III
表目錄---------------------------------------------------IV
第一章 緒論-----------------------------------------------1
第一節 研究背景與動機-------------------------------------1
第二節 研究目的-------------------------------------------4
第三節 研究架構-------------------------------------------6
第二章 資料與方法-----------------------------------------7
第一節 研究樣本與資料來源---------------------------------7
第二節 單根檢定-------------------------------------------7
第三節 實證模型------------------------------------------13
第四節 風險值診斷檢定------------------------------------23
第三章 實證結果分析--------------------------------------27
第一節 基本敘述統計量分析--------------------------------27
第二節 報酬序列單根檢定----------------------------------28
第三節 風險值回顧測試------------------------------------29
第四節 風險值限制下利用效用函用極大化平均模型的實證表現--32
第四章 結論與建議----------------------------------------47
第一節 結論----------------------------------------------47
第二節 建議----------------------------------------------48
參考文獻-------------------------------------------------50

圖目錄
圖1-1 研究流程--------------------------------------------5

表目錄
表4-1 標的資產報酬序列基本敘述統計量---------------------27
表4-2 單根檢定 ------------------------------------------28
表4-3 下方風險值失誤次數統計-----------------------------30
表4-4 Kupiec檢定結果-------------------------------------31
表4-5 風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日報酬基本敘述統計量(效用函數風險趨避係數=1)-32
表4-6 風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日報酬基本敘述統計量(效用函數風險趨避係數=5)-32
表4-7 風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日報酬基本敘述統計量(效用函數風險趨避係數=1，加
      入未投資項權重估計)--------------------------------33
表4-8 風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日報酬基本敘述統計量(效用函數風險趨避係數=5，加
      入未投資項權重估計)--------------------------------34
表4-9 風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日平均報酬成對t檢定(效用函數風險趨避係數=1)--35
表4-10風險值限制式下利用效用函數極大化各平均模型動態投資組
      合的每日平均報酬成對t檢定(效用函數風險趨避係數=5)--36
表4-11風險值限制式下利用效用函數極大化(風險趨避係數=1)各平
      均模型動態投資組合的每日平均報酬與各標的資產每日平均
      報酬的成對t檢定------------------------------------37
表4-12風險值限制式下利用效用函數極大化(風險趨避係數=5)各平
      均模型動態投資組合的每日平均報酬與各標的資產每日平均
      報酬的成對t檢定------------------------------------38
表4-13風險值限制式下利用效用函數極大化(風險趨避係數=1)各平
      均模型動態投資組合的每日報酬變異數的差異性檢定-----40
表4-14風險值限制式下利用效用函數極大化(風險趨避係數=5)各平
      均模型動態投資組合的每日報酬變異數的差異性檢定-----42
表4-15風險值限制式下利用效用函數極大化(風險趨避係數=1)各平
      均模型動態投資組合的每日報酬變異數與各標的資產每日報
      酬變異數的差異性檢定-------------------------------43
表4-16風險值限制式下利用效用函數極大化(風險趨避係數=5)各平
      均模型動態投資組合的每日報酬變異數與各標的資產每日報
      酬變異數的差異性檢定-------------------------------44
表4-17風險值限制式下利用效用函數極大化(風險趨避係數=1)各平
      均模型動態投資組合的每日報酬變異數與風險值限制式下利
      用效用函數極大化(風險趨避係數=5)各平均模型動態投資組
      合的每日報酬變異數的差異性檢定--------------------45

1.Akaike, H., 1973, Information Theory and an Extension of the Maximum Likelihood Principle, Eds. B. X. Petrov and F. Csaki, pp. 267-281. Budapest:Akademiai Kiado.
2.Akgiray, V., 1989, Conditional Heteroskedasticity in Time Series of Stock Returns:Evidence and Forecasts, Journal of Business 62, pp. 55~80.
3.Alexander, C., 2001. Orthogonal GARCH. In: Alexander, C. (Ed.), Mastering risk, vol. 2. Financial Times - Prentice Hall, London, pp.21-38.
4.Baillie, R. and R. DeGennaro, 1990, Stock Returns and Volatility. Journal of financial and quantitative analysis, Vol. 25, no 2, pp.203-214.
5.Beveridge, S. and C. Nelson, 1981, A New Approach to Decomposition of Economic Time Series into Permanent and Transitory Components with Particular Attention to Measurement of the Business Cycle, Journal of Monetary 
Economics,7, pp.151-174.
6.Bollerslev, T., 1986, Generalized Autoregressive Conditional Heteroskedasticity. Journal of Econometrics,31, pp.302-327.
7.Bollerslev, T., 1987, A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return. Review of Economics and Statistics,Vol. 69(3), pp. 542-548.
8.Bollerslev, T., 1990, Modelling the Coherence in Short-Run Nominal Exchange Rates:A Multivariate Generalized ARCH Approach, Review of Economic Studies Vol. 72, pp. 498-505.
9.Bollerslev, T., R. Chou and K. Kroner, 1992, ARCH Modeling in Finance: A Review of the Theory and Empirical Evidence. Journal of Econometrics, Vol. 52, 
No. 1-2, pp. 5-59.
10.DeJong, D., J. Nankervis, N. Savin and C. Whiteman, 1992, Interation Versus Trend Stationarity in Time Series, Econometrica 60, pp. 423-433.
11.Dickey, D. and W. Fuller, 1979, Distribution of the Estimators for Autoregres- sive Time Series with a Unit Root, Journal of the American Statistical Associa- 
tion, 74:pp. 427-431.
12.Engle, R., 1982, Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of UK Inflation, Econometrica vol. 50, pp. 987-1008.
13.Engle, R., 2002, Dynamic Conditional Correlation — a Simple Class of Multivariate GARCH Models. Journal of Business and Economic Statistics, 20, pp. 339-350
14.Granger, C.,and P Newbold, 1977, Forecasting economic time series. Academic Press, New York.
15.J.P. Morgan, 1996, RiskMetrics Technical Document, Fourth Edition.
16.Hiraki, T., E. Maberly and N. Takezawa, 1995, The Information Content of End-of-the-day Index Futures Returns: International Evidence from the Osaka Nikkei 225 Futures Contract. Journal of Banking and Finance,Vol. 19, pp.921-936.
17.Kwiatkowski, D., P. Phillips, P. Schmidt and Y. Shin, 1992, Testing the Null Hypothesis of Stationarity Against the Alternative of a Unit Root: How Sure Are We That Economic Time Series Have a Unit Root?. Journal of Econometrics,1992, Vol. 54, No. 1-3, pp. 159-178.
18.Kupiec, P., 1995, Technique for Verifying the Accuracy of Risk Measurement Models, Journal of Derivatives, Vol. 3, pp. 73-84.
19.Lamoureux, C. and W. Lastrapes, 1990, Heteroskedasticity in Stock Return Data: Volume Versus GARCH Effects, Journal of Finance, American Finance Association,Vol. 45(1), pp. 221-229.
20.Nabeya, S. and K. Tanaka, 1988, Asymptotic Theory of a Test for the Constancy of Regression Coefficients Against the Random Walk Alternative, Ann. Statist. Vol. 16, No. 1, pp. 218-235.
21.Najand, M. and K. Yung, 1994, Conditional Heteroskedasticity and the Weekend Effect in S&P 500 Index Futures. Journal of Business, Finance and Accounting Vol. 21, No. 4, pp. 603-612.
22.Newey, W. and K. West, 1987, A Simple, Positive Semi-definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix,Econometrica, Vol. 55(3), pp. 703-708.
23.Pesaran, M., C. Schleicher and P. Zaffaroni, 2008, Model Averaging in Risk Management with an Application to Futures Markets, Journal of Empirical Finance16, pp. 280-305.
24.Phillips, P., 1987, Time Series Regression with a Unit Root, Econometrica, 55, pp.277-301.
25.Phillip, P. and P. Perron, 1988, Testing for a Unit Root in Time Series Regression,Biomerika, 75:pp. 335-346.
26.Said, S. and D. Dickey, 1984, Testing for Unit Roots in Autoregressive- Moving Average Models with Unknown Order, Biometrica 71:pp. 599-607.
27.Schwarz, G., 1978, Estimating the Dimension of a Model, Annals of Statistics 6:pp. 461-464.
28.Schwert, G., 1989, Stock Volatility and The Crash Of '87, Papers 89-101, Rochester, Business - General.