Open Access
August 2000 A model for long memory conditional heteroscedasticity
Liudas Giraitis, Peter M. Robinson, Donatas Surgailis
Ann. Appl. Probab. 10(3): 1002-1024 (August 2000). DOI: 10.1214/aoap/1019487516

Abstract

or a particular conditionally heteroscedastic nonlinear (ARCH) process for which the conditional variance of the observable sequence rt is the square of an inhomogeneous linear combination of rs,s<t, we give conditions under which, for integers l2,rtl has long memory autocorrelation and normalized partial sums of rtl converge to fractional Brownian motion.

Citation

Download Citation

Liudas Giraitis. Peter M. Robinson. Donatas Surgailis. "A model for long memory conditional heteroscedasticity." Ann. Appl. Probab. 10 (3) 1002 - 1024, August 2000. https://doi.org/10.1214/aoap/1019487516

Information

Published: August 2000
First available in Project Euclid: 22 April 2002

zbMATH: 1084.62516
MathSciNet: MR1789986
Digital Object Identifier: 10.1214/aoap/1019487516

Subjects:
Primary: 62M10
Secondary: 60G18

Keywords: ARCH processes , central limit theorem , diagrams , fractioinal Brownian motion , long memory , Volterra series

Rights: Copyright © 2000 Institute of Mathematical Statistics

Vol.10 • No. 3 • August 2000
Back to Top