Long memory or shifting means in geophysical time series?

In the literature many papers state that long-memory time series models such as Fractional Gaussian Noises (FGN) or Fractionally Integrated series (FI(d)) are empirically indistinguishable from models with a non-stationary mean, but which are mean reverting. We present an analysis of the statistical...

Full description

Bibliographic Details
Main Authors: Rea, W., Reale, M., Brown, J., Oxley, Leslie
Format: Conference Paper
Published: 2011
Online Access:http://hdl.handle.net/20.500.11937/48365
_version_ 1848758088909193216
author Rea, W.
Reale, M.
Brown, J.
Oxley, Leslie
author_facet Rea, W.
Reale, M.
Brown, J.
Oxley, Leslie
author_sort Rea, W.
building Curtin Institutional Repository
collection Online Access
description In the literature many papers state that long-memory time series models such as Fractional Gaussian Noises (FGN) or Fractionally Integrated series (FI(d)) are empirically indistinguishable from models with a non-stationary mean, but which are mean reverting. We present an analysis of the statistical cost of model mis-specification when simulated long memory series are analysed by Atheoretical Regression Trees (ART), a structural break location method. We also analysed three real data sets, one of which is regarded as a standard example of the long memory type. We find that FGN and FI(d) processes do not account for many features of the real data. In particular, we find that the data sets are not H-self-similar. We believe the data sets are better characterized by non-stationary mean models. © 2010 IMACS. Published by Elsevier B.V. All rights reserved.
first_indexed 2025-11-14T09:38:26Z
format Conference Paper
id curtin-20.500.11937-48365
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:38:26Z
publishDate 2011
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-483652018-03-29T09:07:34Z Long memory or shifting means in geophysical time series? Rea, W. Reale, M. Brown, J. Oxley, Leslie In the literature many papers state that long-memory time series models such as Fractional Gaussian Noises (FGN) or Fractionally Integrated series (FI(d)) are empirically indistinguishable from models with a non-stationary mean, but which are mean reverting. We present an analysis of the statistical cost of model mis-specification when simulated long memory series are analysed by Atheoretical Regression Trees (ART), a structural break location method. We also analysed three real data sets, one of which is regarded as a standard example of the long memory type. We find that FGN and FI(d) processes do not account for many features of the real data. In particular, we find that the data sets are not H-self-similar. We believe the data sets are better characterized by non-stationary mean models. © 2010 IMACS. Published by Elsevier B.V. All rights reserved. 2011 Conference Paper http://hdl.handle.net/20.500.11937/48365 10.1016/j.matcom.2010.06.007 restricted
spellingShingle Rea, W.
Reale, M.
Brown, J.
Oxley, Leslie
Long memory or shifting means in geophysical time series?
title Long memory or shifting means in geophysical time series?
title_full Long memory or shifting means in geophysical time series?
title_fullStr Long memory or shifting means in geophysical time series?
title_full_unstemmed Long memory or shifting means in geophysical time series?
title_short Long memory or shifting means in geophysical time series?
title_sort long memory or shifting means in geophysical time series?
url http://hdl.handle.net/20.500.11937/48365