带有外生变变量的动态条件相关模型
DYNAMIC CONDITIONAL CORRELATION MODELS WITH EXOGENOUS VARIABLES
在动态条件相关模型的条件相关等式中加入了外生变量. 外生变量使得等式中的参数随之变化, 该变化反映出外生变量对序列条件相关性的影响. 所提出模型新增的参数不需限制即可以保证条件相关阵的正定性. 同时, 给出了有效的两步极大似然方法来进行参数估计. 最后, 在美国股票市场作为外生变量的条件下, 运用所提出的模型对亚洲地区股票市场进行了研究, 并对实验结果进行了分析.
This paper incorporates exogenous variables into the correlation equation of dynamic conditional correlation (DCC) models. The exogenous variables drive the parameters in the equation to change correspondingly, which reflects the influence of exogenous variables on the conditional correlation of the series. The parameters added in the proposed model need no constraint to make sure of the positivity of conditional correlation matrices. Meanwhile, an effective two-step maximum likelihood method is given to estimate the parameters. Finally, we use the proposed model to study the Asian stock market by treating American stock market as an exogenous variable, and analyze the experiment results.
多元条件异方差模型 / 动态条件相关 / 外生变量 / 两步极大似然估计 / 亚洲股票市场. {{custom_keyword}} /
/
〈 | 〉 |