投資組合風險值衡量：歐洲國家交易所基金的實證

Portfolio Value-at-Risk Evaluation: Empirical Evidence from European Country-Specific Exchange-Traded Funds

范氏莊(PHAM THI TRANG)

指導教授 ： 湯美玲

國立虎尾科技大學/管理學院/財務金融系碩士班/碩士(2017年)

摘要

風險值是進行財務風險管理的重要工具之一。本研究以八個歐洲國家的交易所基金(ETFs)為投資標的，建構了ETFs投資組合，並以兩種方法：變異數－共變異數法(variance-covariance approach)與歷史模擬法(historical simulation approach)計算ETFs投資組合之風險值。其中ETFs投資組合內的個別交易所基金的配置權重，主要是以三種不同的投資策略，包括：等權(EW)方法、EWMA方法、以及GARCH方法所決定，並且針對變異數－共變異數法中的EWMA方法以及GARCH方法，進一步再區分為根據夏普指數(Sharpe ratio)所建構的夏普指數投資組合(VC-EWMA-SR, VC-GARCH-SR)，以及採用半變異數(semi-variance)為基礎所決定投資組合權重的半變異數－修正後夏普指數投資組合(VC-EWMA-MSR.SEMI, VC-GARCH- MSR.SEMI)。本研究結果顯示，這些根據不同投資配置策略下所建構的共十種ETFs投資組合中，以變異數－共變異數法中的EWMA策略以及GARCH策略所對應建構的：半變異數－修正後夏普指數ETFs投資組合(VC-EWMA-MSR.SEMI, VC-GARCH-MSR.SEMI)，具有最佳及次佳的投資組合風險值表現，其均具有顯著優於等權(EW)投資組合此基準比較標的(EW-VC)之風險值績效。而進一步的回溯測試亦證明這些不同ETFs投資組合的風險值估算均具有精確性。
關鍵字：變異數－共變異數法; 歷史模擬法; 半變異數; 交易所基金; 回溯測試

關鍵字

變異數－共變異數法 ； 歷史模擬法 ； 半變異數 ； 交易所基金 ； 回溯測試

並列摘要

Value at Risk (VaR) has become one of the most popular methodologies for financial risk management. Besides, since ETFs have several advantages over index funds, their development and popularity is grown enormously over the past years, especially in Europe. Therefore, in this paper, we use two main approaches, namely, Variance Covariance approach and Historical Simulation approach to estimate VaR of eight European country-specific ETF portfolios. In particular, three different allocative strategies, including equally weighted moving average (EW), EWMA and GARCH models for constructing ETFs portfolios based on these two approaches are respectively developed. Moreover, we also introduce the Sharpe ratio and Modified Sharpe ratio, which apply the semi-variance and variance in turn for referring them to determine the optimally allocative weights for ETFs portfolios. Finally, we conduct two backtesting techniques to examine the validation of estimation with regard to the prediction of future risks. Our empirical results exhibit that the EWMA (Variance-Covariance) model using modified Sharpe ratio as measuring downside risk followed by the GARCH model (Variance-Covariance) can indeed outperform others and beat a benchmark as well.
Key words: Variance-Covariance Approach; Historical Simulation; Semi-Variance; Exchange-Traded Funds; Backtesting

並列關鍵字

Variance-Covariance Approach ； Historical Simulation ； Semi-Variance ； Exchange-Traded Funds ； Backtesting

參考文獻

[1] Hiller, R.S., Eckstein, J., (1993), “Stochastic Dedication: Designing fixed income portfolios using massively parallel benders decomposition”, Management Science, Vol.39, No.11, pp.1422-1438.

[2] Birge, J.R., Rosa, C.H., (1995), “Modeling investment uncertainty in the costs of global CO2 emission policy”, European Journal of Operational Research, Vol.83, No.3, pp.46-488.

[3] Mulvey, J.M., Vaderbei, R.J., Zenios, S.A., (1995), “Robust optimization of large-scale systems”, Operations Research, Vol.43, No.2, pp.264-281.

[4] Vladimirou, H., Zenios, S.A., (1997), “Stochastic linear programs with restricted recourse”, European Journal of Operational Research, Vol.101, No.1, pp.177-192.

[5] Basak, S., Shapiro, A., (1999), “Value-at-risk based risk management: Optimal Policies and Asset Prices”, Working paper, The Wharton School.