Quasi-maximum likelihood estimation in GARCH processes when some coefficients are equal to zero

详细信息    查看全文

• 作者：Christian Francq ; Jean-Michel Zakoian
• 关键词：Boundary of the parameter space ; Conditional heteroskedasticity ; GARCH model ; Quasi-maximum likelihood estimation ; Non-normal asymptotic distribution
• 刊名：Stochastic Processes and their Applications
• 出版年：2007
• 出版时间：September 2007
• 年：2007
• 卷：117
• 期：9
• 页码：1265-1284
• 全文大小：418 K

文摘

The asymptotic distribution of the quasi-maximum likelihood (QML) estimator is established for generalized autoregressive conditional heteroskedastic (GARCH) processes, when the true parameter may have zero coefficients. This asymptotic distribution is the projection of a normal vector distribution onto a convex cone. The results are derived under mild conditions. For an important subclass of models, no moment condition is imposed on the GARCH process. The main practical implication of these results concerns the estimation of overidentified GARCH models.