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. In order to investigate the higher-order moment risk measure between multiple markets or multiple financial assets and effectively capture the high-order moment dynamic characteristics of the time series of yield, under the conditions of current expectations and volatility, The paper proposes a multi-dimensional high-order moment model that can effectively solve the problem of dimensionality disaster.Based on the multidimensional S_U distribution, the dynamic conditional correlation (DCC) and autoregressive conditional density (MDC) The time-varying parameters of the conditional higher-order moment model are estimated.The empirical results show that the higher-order moment model of the multi-dimensional condition fits the higher order moment dynamic characteristic of the time series of the yield well, compared with the previous higher order moment model, Which can effectively solve the dimensionality calamity problem of high-order moment models. It shows that the model can capture the high-order moment risk features among multiple markets in China and improve the measurement ability of higher-order moment models with multi-dimensional conditions.