EconStor >
TÜSİAD-Koç University Economic Research Forum (ERF), Istanbul >
ERF Working Paper Series, TÜSİAD-Koç University Economic Research Forum (ERF) >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/45438
  
Title:Parameter estimation in nonlinear AR-GARCH models PDF Logo
Authors:Meitz, Mika
Saikkonen, Pentti
Issue Date:2010
Series/Report no.:TÜSİAD-Koç University Economic Research Forum working paper series 1002 [rev.]
Abstract:This paper develops an asymptotic estimation theory for nonlinear autoregressive models with conditionally heteroskedastic errors. We consider a general nonlinear autoregression of order p (AR(p)) with the conditional variance specified as a general nonlinear first order generalized autoregressive conditional heteroskedasticity (GARCH(1,1)) model. We do not require the rescaled errors to be independent, but instead only to form a stationary and ergodic martingale difference sequence. Strong consistency and asymptotic normality of the global Gaussian quasi maximum likelihood (QML) estimator are established under conditions comparable to those recently used in the corresponding linear case. To the best of our knowledge, this paper provides the first results on consistency and asymptotic normality of the QML estimator in nonlinear autoregressive models with GARCH errors.
Document Type:Working Paper
Appears in Collections:ERF Working Paper Series, TÜSİAD-Koç University Economic Research Forum (ERF)

Files in This Item:
File Description SizeFormat
638344360.pdf663.65 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/45438

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.