基于ARFIMA-GARCH模型的混成检验
PORTMANTEAU TEST BASED ON THE ARFIMA-GARCH MODEL

本文研究了ARFIMA-GARCH模型的混成检验问题.基于拟极大指数似然估计，给出了平方残差自相关函数的渐近性，进而建立了基于平方残差自相关函数的混成检验统计量.通过实例分析，表明可利用基于平方残差自相关函数的混成检验统计量来诊断检验由拟极大指数似然估计方法拟合的ARFIMA-GARCH模型.
In this paper, we study the portmanteau test problem of ARFIMA-GARCH model. Based on the quasi-maximum exponential likelihood estimator, the asymptotic of squared residual autocorrelation function is given, and the portmanteau test statistic based on squared residual autocorrelation function is established. By the analysis of a real example, it is showed that we can use the portmanteau test statistic based on squared residual autocorrelation function to the diagnostic test of ARFIMA-GARCH model fitting by quasi-maximum exponential likelihood estimator