Asymptotic Normality of the QMLE Estimator of ARCH in the Nonstationary Case
证明线性ARCH模型中拟极大似然估计量在参数处于非平稳区域时仍具有相合性和渐近正态性，扩展了现有理论的适用范围。
We establish consistency and asymptotic normality of the quasi-maximum likelihood estimator in the linear ARCH model. Contrary to the existing literature, we allow the parameters to be in the region where no stationary version of the process exists. This implies that the estimator is always asymptotically normal. Copyright The Econometric Society 2004.