本文主要探討在資產配置時，財務資料的不同特徵對於投資組合績效有多少程度的影響，以及如果使用考量參數不確定性的資產配置方法，是否可以降低資料特徵對於投資組合績效的影響。文中使用了三組模擬資料，用以表達財務資料的三種不同特徵，分別為發生極端事件之機率較常態分佈高、資產波動度的群聚現象以及資產間的相關性。在資產配置的文獻中，有許多對於參數不確定性的解決方法，而本文是根據文獻上以投資人效用函數出發並極大化投資人期望效用函數的決策方法，找出參數不確定性下的資產配置 ; 此外交易成本的設定，亦參考文獻上，使用二次式形式的交易成本作為資產配置時交易成本的考量。根據是否考量參數不確定性以及交易成本，本文中共考慮了七種均數–變異數資產配置方法。最後，根據不同模擬資料的績效評估結果我們發現，考量交易成本以及參數不確定性下的多期配置其績效相較於靜態資產配置方法來的佳且穩定 ; 此外資產間的相關性對於靜態及多期配置下的資產配置都有很明顯的影響。因此藉由本文可讓讀者了解到財務資料特徵對於資產配置的績效影響，以及文獻上考量交易成本及參數不確定性的資產配置方法。

In this article, we mainly discuss the impact of different characteristics of financial data on the performance of different asset allocation methods. Three sets of simulation data are used to express three different characteristics of financial data, namely, the probability of extreme events is higher than the normal distribution, the clustering phenomenon of asset volatility, and the correlation between assets. In the literature of asset allocation, there are many solutions to parameter uncertainty, and the method we use to deal with parameter uncertainty is to start from the investor’s utility function and use investment decision-making methods to find assets allocation under parameter uncertainty. In addition, the setting of transaction costs also refers to the literature, using the quadratic form of transaction costs as the consideration in asset allocation. Based on whether to consider parameter uncertainty and transaction costs, we consider seven different mean - variance asset allocation methods. According to the performance evaluation results of different simulation data, we found that the performance of multi-period allocation under transaction costs and parameter uncertainty is less influenced by the different characteristics of finance data. In addition, the correlation between assets has a significant impact on asset allocation under static and multi-period asset allocations. Overall, readers can understand the impact of the characteristics of financial data on the performance of asset allocation, as well as the asset allocation method that considers transaction costs and parameter uncertainties in the literature.

[1] Adame García, Victor & Rodrrguez, Fernando & Sosvilla-Rivero, Simón. (2017). Resolution of Optimization Problems and Construction of Efficient Portfolios: An Application to the Euro Stoxx 50 Index. SSRN Electronic Journal.

[2] Campbell, J., Lo, A., & MacKinlay, A. (1997). The Econometrics of Financial Markets. Princeton, New Jersey: Princeton University Press.

[3] Constantinides, G. M. “Multiperiod Consumption and Investment Behavior with Convex Transactions Costs.”Management Science, 25 (1979), 1127–1137.

[4] Davis, M., & Norman, A. (1990). Portfolio Selection with Transaction Costs. Mathematics of Operations Research, 15(4), 676-713.

[5] DeMiguel, V., Martín-Utrera, A., & Nogales, F. (2015). Parameter Uncertainty in Multiperiod Portfolio Optimization with Transaction Costs. Journal of Financial and Quantitative Analysis, 50(6), 1443-1471.

[6] Garleanu, N. and Pedersen, L.H. (2013), Dynamic Trading with Predictable Returns and Transaction Costs. Journal of Finance, 68: 2309-2340.

[7] Goldfarb, D. and Iyengar, G. (2003) Robust Portfolio Selection Problems. Mathematics of Operations Research, 28, 1-38.

[8] Kan, R., & Zhou, G. (2007). Optimal Portfolio Choice with Parameter Uncertainty. Journal of Financial and Quantitative Analysis, 42(3), 621-656.

[9] Ledoit, O., & Wolf, M. (2004). A well-conditioned estimator for large-dimensional convariance matrices. Journal of Multivariate Analysis, 88(2), 365–411.

[10] MacKinlay, A., & Pástor, Ľ. (2000). Asset Pricing Models: Implications for Expected Returns and Portfolio Selection. Review of Financial Studies, 13(4), 883-916.

[11] Mainik, Georg & Mitov, Georgi & Rüschendorf, Ludger, 2015. "Portfolio optimization for heavy-tailed assets: Extreme Risk Index vs. Markowitz," Journal of Empirical Finance, Elsevier, vol. 32(C), pages 115-134.

[12] Markowitz, H. (1952), PORTFOLIO SELECTION. Journal of Finance, 7: 77-91.

[13] McNeil, Alexander & Frey, Rüdiger & Embrechts, P. (2005). Quantitative Risk Management: Concepts, Techniques, and Tools.

[14] Pfaff, B. (2016). Financial Risk Modelling and Portfolio Optimization with R, Wiley, London, 2nd edn.

[15] Ravi Jagannathan & Tongshu Ma, 2003. "Risk Reduction in Large Portfolios: Why Imposing the Wrong Constraints Helps," Journal of Finance, American Finance Association, vol. 58(4), 1651-1684.

[16] Rebonato, Riccardo & Jaeckel, Peter. (2000). The Most General Methodology to Create a Valid Correlation Matrix for Risk Management and Option Pricing Purposes. Journal of Risk. 2. 17-27.

[17] Tu, Jun and Zhou, Guofu, (2010), Incorporating Economic Objectives into Bayesian Priors: Portfolio Choice under Parameter Uncertainty, Journal of Financial and Quantitative Analysis, 45(4), 959-986.

[18] Tu, Jun and Zhou, Guofu, (2011), Markowitz meets Talmud: A combination of sophisticated and naive diversification strategies, Journal of Financial Economics, 99(1), 204-215.

[19] Victor DeMiguel, Lorenzo Garlappi, Raman Uppal (2009). Optimal Versus Naive Diversification: How Inefficient is the 1/N Portfolio Strategy?, Review of Financial Studies, 22(5), 1915–1953.

[20] Wenbo Hu & Alec N. Kercheval (2010) Portfolio optimization for student t and skewed t returns, Quantitative Finance, 10(1), 91-105.

[21] Xia, Yihong, (2001), Learning about Predictability: The Effects of Parameter Uncertainty on Dynamic Asset Allocation, Journal of Finance, 205-246.