| Summary: | 碩士 === 國立暨南國際大學 === 資訊管理學系 === 103 === The high uncertainty of asset returns could mislead the predictions of asset allocations so that the portfolio rebalance could be inefficiency or low performance. The robust portfolios deal with uncertainty based on the scenarios. Researchers have integrated the robust mechanism into Conditional Value-at-Risk (CVaR) for portfolio selection, which the extreme loss is considered for risk averison (Zhu and Fukushima, 2009; Huang et al., 2010). However, the extreme loss could be ignored if the expected return is higher than the expected loss. Because Worst-case robust Omega ratio model (WCOmega, Kapsos et al., 2014) extends the CVaR by integrating the maximization of portfolio returns and the minimization of portfolio loss (Kapsos et al., 2014). This study proposes the portfolio selection model which revises WCOmega model and considers transaction cost and short selling to simulate the real investment in the financial market. The comparsion of the proposed model with two other robust portfolio models the Worst-case Conditional Value-at-Risk (WCVaR) and the Relative Robust Conditional Value-at-Risk (RRCVaR) is based on Sharpe ratio, Omega ratio, weight, the ratio of short selling and transaction cost to explore the performance of market value and realized return. Moreover, the similarity among these models state the differences of asset allocation which is determined by the model characteristics. Two data sets, the funds and Standard & Poor's 500 index (S&P 500) are used to show the characteristics of the model comparison under different market trends. The results show that the proposed WCOmega has better performance than the modified CVaR related models.
|
|---|
