为了考察多个市场或多个金融资产之间的高阶矩风险度量问题,有效地捕获收益率时间序列高阶矩动态特征,在考虑当前预期和波动性条件下,推导了高阶中心矩和协矩之间的关系,提出了能够有效解决维数灾祸问题的多维条件高阶矩模型.在多维S_U分布基础上,采用动态条件相关性(DCC)和自回归条件密度技术,通过智能优化算法对条件高阶矩模型的时变参数进行估计.实证研究结果表明,多维条件高阶矩模型较好的拟合了收益率时间序列高阶矩动态特征,与之前的高阶矩模型相比,能够有效解决高阶矩模型的维数灾祸问题,表明该模型能够捕捉到我国多个市场之间高阶矩风险特征,提高多维条件高阶矩模型测度能力.
Considering factors of anticipation and volatility,to measure the dynamic character of higher moments risk and investigate impacts of the risk on multi-financial markets or assets,a model of multivariate conditional higher order moments,which can solve the problem of 'dimension disaster',was proposed with the determination of the formulas between moments and co-moments.Time-varying parameters of higher order moments were estimated using Dynamic Conditional Correlation,Autoregressive conditional density and ...