In classical Markowitz＇s Mean-Variance model, parameters such as the mean and covari- ance of the underlying assets＇ future return are assumed to be known exactly. However, this is not always the case. The parameter...In classical Markowitz＇s Mean-Variance model, parameters such as the mean and covari- ance of the underlying assets＇ future return are assumed to be known exactly. However, this is not always the case. The parameters often correspond to quantities that fall within a range, or can be known ambiguously at the time when investment decision must be made. In such situations, investors determine returns on investment and risks etc. and make portfolio decisions based on experience and economic wisdom. This paper tries to use the concept of interval numbers in the fuzzy set theory to extend the classical mean-variance portfolio selection model to a mean-downside semi-variance model with consideration of liquidity requirements of a bank. The semi-variance constraint is employed to control the downside risk, filling in the existing interval portfolio optimization model based on the linear semi-absolute deviation to depict the downside risk. Simulation results show that the model behaves robustly for risky assets with highest or lowest mean historical rate of return and the optimal investment proportions have good stability. This suggests that for these kinds of assets the model can reduce the risk of high deviation caused by the deviation in the decision maker＇s experience and economic wisdom.展开更多
甄别和确定风险因素的贡献是资产或资产组合风险管理的重要研究内容。近十年,下端风险越来越受到关注,在险价值(Value at Risk,VaR)和预期不足(Expected Shortfall,ES)是资产组合风险管理中两个常用的风险度量工具。Kuan等[1]在一类条...甄别和确定风险因素的贡献是资产或资产组合风险管理的重要研究内容。近十年,下端风险越来越受到关注,在险价值(Value at Risk,VaR)和预期不足(Expected Shortfall,ES)是资产组合风险管理中两个常用的风险度量工具。Kuan等[1]在一类条件自回归模型(CARE)下提出了基于expectile的VaR度量-EVaR。本文扩展了Kuan等[2]的CARE模型到带有异方差的数据,引入ARCH效应提出了一个线性ARCH-Expectile模型,旨在确定资产或资产组合的风险来源以及评估各风险因素的贡献大小,并应用expectile间接评估VaR和ES风险大小。同时给出了参数的两步估计算法,并建立了参数估计的大样本理论。最后,将本文所提出的方法应用于民生银行股票损益的风险分析,从公司基本面、市场流动性和宏观层面三个方面选取影响股票损益的风险因素,分析结果表明,各风险因素随股票极端损失大小的水平不同,其风险因素的来源及其大小和方向也是随之变化的。展开更多
引入VaR(Value at Risk)的极值理论对世界原油现货市场的价格风险进行研究.在对WTI和Brent原油现货市场的实证研究中将极值理论的阈值模型与簇值方法相结合,对阈值u和模型参数的估计方法提出了改进,取得了较为理想的VaR估计结果.在此基...引入VaR(Value at Risk)的极值理论对世界原油现货市场的价格风险进行研究.在对WTI和Brent原油现货市场的实证研究中将极值理论的阈值模型与簇值方法相结合,对阈值u和模型参数的估计方法提出了改进,取得了较为理想的VaR估计结果.在此基础上讨论了两市场价格风险的不同特征以及同一市场中厂商风险和采购风险的不同特征.得到了一些有意义的结论.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos.71301017,71731003,71671023,11301050 and 51375067the National Social Science Foundation of China under Grant No.16BTJ017+1 种基金China Postdoctoral Science Foundation Funded Project under Grant No.2016M600207the Doctoral Fund of Liaoning Province under Grant No.20131017
文摘In classical Markowitz＇s Mean-Variance model, parameters such as the mean and covari- ance of the underlying assets＇ future return are assumed to be known exactly. However, this is not always the case. The parameters often correspond to quantities that fall within a range, or can be known ambiguously at the time when investment decision must be made. In such situations, investors determine returns on investment and risks etc. and make portfolio decisions based on experience and economic wisdom. This paper tries to use the concept of interval numbers in the fuzzy set theory to extend the classical mean-variance portfolio selection model to a mean-downside semi-variance model with consideration of liquidity requirements of a bank. The semi-variance constraint is employed to control the downside risk, filling in the existing interval portfolio optimization model based on the linear semi-absolute deviation to depict the downside risk. Simulation results show that the model behaves robustly for risky assets with highest or lowest mean historical rate of return and the optimal investment proportions have good stability. This suggests that for these kinds of assets the model can reduce the risk of high deviation caused by the deviation in the decision maker＇s experience and economic wisdom.
文摘甄别和确定风险因素的贡献是资产或资产组合风险管理的重要研究内容。近十年,下端风险越来越受到关注,在险价值(Value at Risk,VaR)和预期不足(Expected Shortfall,ES)是资产组合风险管理中两个常用的风险度量工具。Kuan等[1]在一类条件自回归模型(CARE)下提出了基于expectile的VaR度量-EVaR。本文扩展了Kuan等[2]的CARE模型到带有异方差的数据,引入ARCH效应提出了一个线性ARCH-Expectile模型,旨在确定资产或资产组合的风险来源以及评估各风险因素的贡献大小,并应用expectile间接评估VaR和ES风险大小。同时给出了参数的两步估计算法,并建立了参数估计的大样本理论。最后,将本文所提出的方法应用于民生银行股票损益的风险分析,从公司基本面、市场流动性和宏观层面三个方面选取影响股票损益的风险因素,分析结果表明,各风险因素随股票极端损失大小的水平不同,其风险因素的来源及其大小和方向也是随之变化的。
文摘引入VaR(Value at Risk)的极值理论对世界原油现货市场的价格风险进行研究.在对WTI和Brent原油现货市场的实证研究中将极值理论的阈值模型与簇值方法相结合,对阈值u和模型参数的估计方法提出了改进,取得了较为理想的VaR估计结果.在此基础上讨论了两市场价格风险的不同特征以及同一市场中厂商风险和采购风险的不同特征.得到了一些有意义的结论.
