Template-type: ReDIF-Paper 1.0
Author-Name: Jurgen A. Doornik
X-Author-Email:jurgen.doornik@nuffield.ox.ac.uk 
X-Author-Homepage:
Author-Workplace-Name:Nuffield College, Oxford University
X-Author-Workplace-Homepage:
Author-Name: Marius Ooms
X-Author-Email: 
Author-Homepage:http://www.nuff.ox.ac.uk/ 
Author-Workplace-Name:Dept of Economics, Free University of Amsterdam
X-Author-Workplace-Homepage:
Title:Computational Aspects of Maximum Likelihood Estimation of Autoregressive Fractionally Integrated Moving Average Models
Abstract:
 We discuss computational aspects of likelihood-based estimation of univariate ARFIMA (p,d,q) models.  We show how efficient computation and simulation is feasible, even for large samples.  We also discuss the implementation of analytical bias corrections.
Classification-JEL:C22, C63
Keywords:Long memory, Bias, Modified profile likelihood, Restricted maximum likelihood estimator, Time-series regression model likelihood  
X-Note:
Length:14 pages
Creation-Date: 2001-11-29
X-Revision-Date:
Number:2001-W27
X-Publication-Status:
X-Price:
File-URL: http://www.nuff.ox.ac.uk/Economics/papers/2001/w27/ArfimaNum.pdf
File-Format: application/pdf
X-File-Restriction:
X-File-Function:
X-File-Size:
Handle: RePEc:nuf:econwp:0127