Home > Research > Publications & Outputs > A class of modified high order autoregressive m...

Research

Links

Text available via DOI:

View graph of relations

A class of modified high order autoregressive models with improved resolution of low frequency cycles.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

A class of modified high order autoregressive models with improved resolution of low frequency cycles. / Tunnicliffe Wilson, Granville; Morton, Alex S.
In: Journal of Time Series Analysis, Vol. 25, No. 2, 01.03.2004, p. 235-250.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Tunnicliffe Wilson, G & Morton, AS 2004, 'A class of modified high order autoregressive models with improved resolution of low frequency cycles.', Journal of Time Series Analysis, vol. 25, no. 2, pp. 235-250. https://doi.org/10.1046/j.0143-9782.2003.00347.x

APA

Tunnicliffe Wilson, G., & Morton, A. S. (2004). A class of modified high order autoregressive models with improved resolution of low frequency cycles. Journal of Time Series Analysis, 25(2), 235-250. https://doi.org/10.1046/j.0143-9782.2003.00347.x

Vancouver

Tunnicliffe Wilson G, Morton AS. A class of modified high order autoregressive models with improved resolution of low frequency cycles. Journal of Time Series Analysis. 2004 Mar 1;25(2):235-250. doi: 10.1046/j.0143-9782.2003.00347.x

Author

Tunnicliffe Wilson, Granville ; Morton, Alex S. / A class of modified high order autoregressive models with improved resolution of low frequency cycles. In: Journal of Time Series Analysis. 2004 ; Vol. 25, No. 2. pp. 235-250.

Bibtex

@article{be3449a09ffc44d5803eff18fe621534,
title = "A class of modified high order autoregressive models with improved resolution of low frequency cycles.",
abstract = "We consider regularly sampled processes that have most of their spectral power at low frequencies. A simple example of such a process is used to demonstrate that the standard autoregressive (AR) model, with its order selected by an information criterion, can provide a poor approximation to the process. In particular, it can result in poor multi-step predictions. We propose instead the use of a class of pth order AR models obtained by the addition of a pre-specified pth order moving average term. We present a re-parameterization of this model and show that with a low order it can provide a very good approximation to the process and its multi-step predictions. Methods of model identification and estimation are presented, based on a transformed sample spectrum, and modified partial autocorrelations. The method is also illustrated on a real example.",
author = "{Tunnicliffe Wilson}, Granville and Morton, {Alex S.}",
note = "RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research",
year = "2004",
month = mar,
day = "1",
doi = "10.1046/j.0143-9782.2003.00347.x",
language = "English",
volume = "25",
pages = "235--250",
journal = "Journal of Time Series Analysis",
issn = "0143-9782",
publisher = "Wiley-Blackwell",
number = "2",

}

RIS

TY - JOUR

T1 - A class of modified high order autoregressive models with improved resolution of low frequency cycles.

AU - Tunnicliffe Wilson, Granville

AU - Morton, Alex S.

N1 - RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research

PY - 2004/3/1

Y1 - 2004/3/1

N2 - We consider regularly sampled processes that have most of their spectral power at low frequencies. A simple example of such a process is used to demonstrate that the standard autoregressive (AR) model, with its order selected by an information criterion, can provide a poor approximation to the process. In particular, it can result in poor multi-step predictions. We propose instead the use of a class of pth order AR models obtained by the addition of a pre-specified pth order moving average term. We present a re-parameterization of this model and show that with a low order it can provide a very good approximation to the process and its multi-step predictions. Methods of model identification and estimation are presented, based on a transformed sample spectrum, and modified partial autocorrelations. The method is also illustrated on a real example.

AB - We consider regularly sampled processes that have most of their spectral power at low frequencies. A simple example of such a process is used to demonstrate that the standard autoregressive (AR) model, with its order selected by an information criterion, can provide a poor approximation to the process. In particular, it can result in poor multi-step predictions. We propose instead the use of a class of pth order AR models obtained by the addition of a pre-specified pth order moving average term. We present a re-parameterization of this model and show that with a low order it can provide a very good approximation to the process and its multi-step predictions. Methods of model identification and estimation are presented, based on a transformed sample spectrum, and modified partial autocorrelations. The method is also illustrated on a real example.

U2 - 10.1046/j.0143-9782.2003.00347.x

DO - 10.1046/j.0143-9782.2003.00347.x

M3 - Journal article

VL - 25

SP - 235

EP - 250

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

SN - 0143-9782

IS - 2

ER -