Invariance of the first difference in ARFIMA models

A desirable property for an estimator of the fractional ARFIMA parameter is to be first difference invariant. This paper investigates the effects on the fractional parameter estimator in nonstationary ARFIMA(p,d,q) processes before and after applying a first difference. We consider semiparametric an...

Full description

Saved in:
Bibliographic Details
Published inComputational statistics Vol. 21; no. 3-4; pp. 445 - 461
Main Authors Olbermann, Barbara P., Lopes, Sílvia R. C., Reisen, Valdério A.
Format Journal Article
LanguageEnglish
Published Heidelberg Springer Nature B.V 01.12.2006
Subjects
Computer simulation
Economic models
Estimators
Invariants
Mathematical models
Monte Carlo methods
Monte Carlo simulation
Samples
Statistical analysis
Statistics
Studies
Online AccessGet full text

Cover

More Information
Summary:A desirable property for an estimator of the fractional ARFIMA parameter is to be first difference invariant. This paper investigates the effects on the fractional parameter estimator in nonstationary ARFIMA(p,d,q) processes before and after applying a first difference. We consider semiparametric and parametric approaches for estimating d. The study is based on a Monte Carlo simulation for different sample sizes. The Brazilian exchange rate series is given as an application of the methodology.[PUBLICATION ABSTRACT]
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0943-4062
1613-9658
DOI:10.1007/s00180-006-0005-0