摘要
应用图模型方法讨论传统时间序列的ARCH(自回归条件异方差)效应,证明了ARCH模型的系数等于变换后模型在给定其它时间序列变量条件下的偏相关系数,并提出了一种新的ARCH效应检验方法.
The effect of ARCH (autoregressive conditional heteroskedasticity) of traditional time series was discussed by applying graphical modeling. And the conclusion that the coefficients of ARCH model are equal to the changed model's partial correlation coefficients under the condition of given time series variable was obtained. Then a new approach of effect testing of ARCH was proposed.
出处
《温州大学学报(自然科学版)》
2010年第4期1-5,共5页
Journal of Wenzhou University(Natural Science Edition)
基金
国家自然科学基金项目(10671044)
浙江省教育厅科研项目(Y200804757)
关键词
图模型方法
ARCH模型
偏相关系数
Graphical Modeling
ARCH Model
Partial Correlation Coefficient