本研究利用全面效用函數最佳化模型(Full-Scale optimization model)與均異模型(Mean Variance model)來建構資產配置，除了過去文獻採用的風險性資產外，本文獻多加了無風險性資產，並比較兩種方法樣本內與樣本外的效果。本研究採用一年期定存利率、FTSE 100、FTSE250做為投資組合的，研究樣本期間為2004至2012年。
Markowitz的投資組合理論至今仍為許多投資理論的研究重心，但許多學者認為均異模型不足完整描述不同報酬類型，以及不同的效用函數，紛紛建議採用全面效用最佳化模型，並實證出利用全面效用函數在避險基金與股票型基金表現會優於均異模型。本研究採用不同時期的樣本期間發現，樣本內與樣本外配置會影響兩者的優劣，不似過去文獻所得出的結果。
本研究發現:(一)全面效用最佳化相對於均異模型會傾向投資於高風險高報酬性資產。(二)均異模型因為只考慮到二階動差，但三階動差(符號為正)，在樣本外為負時，會造成全面效用最佳化表現比均異模型差。(三)加入無風險性資產可以改善投資組合過度集中的情形。

The study applies Full-scale optimization model and Mean-Variance Model to construct asset allocation. In addition to using risky asset, we also add risk-free asset to compare the utility of the two approach in the sample and out of the sample. We use 1-year deposit, FTSE 100, and FTSE 250 as our investment portfolio and the period is from 2004 to 2012.
Although Markowitz’s investment portfolio still plays an important role nowadays, many scholars suspect that Mean Variance Model can not describe different type of return and utility function. They suggest use Full Scale Optimization to allocate asset and the empirical results indicate that Full Scale optimization is better. However, our empirical results which is used different-period data indicates that in-sample data and out-of sample data influence the results. In other word, we have different results.
Our results are as follows. First, Full Scale Optimization Model tends to increase weight of risky asset and high return asset compare to Mean Variance Model. Second, Mean Variance Model does not include the third and higher moment. Therefore, when the return of out-of-sample data is negative, the performance of Full Scale optimization may be worse than Mean Variance Model. Third, Adding risk-free asset can be more diversification.

參考文獻
1. Adler, T. and M. Kritzman, 2007, “Mean–variance versus full-scale optimization: In and out of sample”, Journal of Asset Management, Vol. 7 Issue 5, 302-311.
2. Kroll, Y., H. Levy, and HM. Markowitz, 1984, “Mean‐Variance versus Direct Utility Maximization”, The Journal of Finance, Vol. 39, 47-61.
3. Cremers, J-H, M Kritzman, and S.Page, 2003, “Portfolio formation with higher moments and plausible utility”, Revere Street Working Paper Series 272-312.
4. Cremers, J-H, M Kritzman, and S.Page, 2005, “Optimal hedge fund allocations”, The Journal of Portfolio Management, Vol. 31, 70-81.
5. Hagströmer, B. and JM. Binner, 2009, “Stock portfolio selection with full-scale optimization and differential evolution”, Applied Financial Economics, Vol. 19, 1559-1571.
7. Kahneman, D. and A. Tversky, 1979, “Prospect theory: An analysis of decision under risk”, Econometrica: Journal of the Econometric Society 263-291.
8. Maringer, D., 2008, “Risk preferences and loss aversion in portfolio optimization”, In Computational methods in financial engineering 27-45.
9. Markowitz H., 1952, “Portfolio selection”, The journal of finance,Vol. 7, 77-91
11. Sharpe WF. 2007, “Expected utility asset allocation”, Financial Analysts Journal 18-30.
12. Tobin J. 1958. “Liquidity preference as behavior towards risk”, The Review of Economic Studies, Vol. 25, 65-86.
13. Xu H, Ruef M. 2004. “The myth of the risk-tolerant entrepreneur”, Strategic Organization Vol. 2, 331-355.