The power of tests for equivalent ARMA models: The implications for practitioners

Tim Chenoweth, Robert Hubata, Robert St Louis

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Analysts frequently find it convenient to use the same ARMA model to make forecasts for multiple time series. The trick is to know when it is safe to assume that multiple series are generated by the same underlying process. Although several authors have developed statistical procedures for testing whether two models are equivalent, no one has shown how to determine the power of these tests. This paper shows how to determine the power of the most general test for equivalent ARMA models. It also shows how to quantify the effect of model misspecification errors on the accuracy of the forecast. An illustrative example and flowchart are then used to show how calculating the power of the test can enable the practitioner to safeguard against a serious degradation in the accuracy of the forecast.

Original languageEnglish (US)
Pages (from-to)281-292
Number of pages12
JournalEmpirical Economics
Volume29
Issue number2
DOIs
StatePublished - Jun 2004

Fingerprint

Power of Test
ARMA Model
Forecast
Multiple Time Series
Model Misspecification
Degradation
Quantify
statistical method
time series
Testing
Series
ARMA model
Model

Keywords

  • Model misspecification
  • Noncentral Chi-Square distribution
  • Power
  • Seemingly unrelated ARMA models
  • Type II errors

ASJC Scopus subject areas

  • Economics and Econometrics
  • Mathematics (miscellaneous)
  • Statistics and Probability
  • Social Sciences (miscellaneous)

Cite this

The power of tests for equivalent ARMA models : The implications for practitioners. / Chenoweth, Tim; Hubata, Robert; St Louis, Robert.

In: Empirical Economics, Vol. 29, No. 2, 06.2004, p. 281-292.

Research output: Contribution to journalArticle

@article{6cc883e74442487a9bb1aad0cc8c994f,
title = "The power of tests for equivalent ARMA models: The implications for practitioners",
abstract = "Analysts frequently find it convenient to use the same ARMA model to make forecasts for multiple time series. The trick is to know when it is safe to assume that multiple series are generated by the same underlying process. Although several authors have developed statistical procedures for testing whether two models are equivalent, no one has shown how to determine the power of these tests. This paper shows how to determine the power of the most general test for equivalent ARMA models. It also shows how to quantify the effect of model misspecification errors on the accuracy of the forecast. An illustrative example and flowchart are then used to show how calculating the power of the test can enable the practitioner to safeguard against a serious degradation in the accuracy of the forecast.",
keywords = "Model misspecification, Noncentral Chi-Square distribution, Power, Seemingly unrelated ARMA models, Type II errors",
author = "Tim Chenoweth and Robert Hubata and {St Louis}, Robert",
year = "2004",
month = "6",
doi = "10.1007/s00181-003-0167-3",
language = "English (US)",
volume = "29",
pages = "281--292",
journal = "Empirical Economics",
issn = "0377-7332",
publisher = "Physica-Verlag",
number = "2",

}

TY - JOUR

T1 - The power of tests for equivalent ARMA models

T2 - The implications for practitioners

AU - Chenoweth, Tim

AU - Hubata, Robert

AU - St Louis, Robert

PY - 2004/6

Y1 - 2004/6

N2 - Analysts frequently find it convenient to use the same ARMA model to make forecasts for multiple time series. The trick is to know when it is safe to assume that multiple series are generated by the same underlying process. Although several authors have developed statistical procedures for testing whether two models are equivalent, no one has shown how to determine the power of these tests. This paper shows how to determine the power of the most general test for equivalent ARMA models. It also shows how to quantify the effect of model misspecification errors on the accuracy of the forecast. An illustrative example and flowchart are then used to show how calculating the power of the test can enable the practitioner to safeguard against a serious degradation in the accuracy of the forecast.

AB - Analysts frequently find it convenient to use the same ARMA model to make forecasts for multiple time series. The trick is to know when it is safe to assume that multiple series are generated by the same underlying process. Although several authors have developed statistical procedures for testing whether two models are equivalent, no one has shown how to determine the power of these tests. This paper shows how to determine the power of the most general test for equivalent ARMA models. It also shows how to quantify the effect of model misspecification errors on the accuracy of the forecast. An illustrative example and flowchart are then used to show how calculating the power of the test can enable the practitioner to safeguard against a serious degradation in the accuracy of the forecast.

KW - Model misspecification

KW - Noncentral Chi-Square distribution

KW - Power

KW - Seemingly unrelated ARMA models

KW - Type II errors

UR - http://www.scopus.com/inward/record.url?scp=2942515940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942515940&partnerID=8YFLogxK

U2 - 10.1007/s00181-003-0167-3

DO - 10.1007/s00181-003-0167-3

M3 - Article

AN - SCOPUS:2942515940

VL - 29

SP - 281

EP - 292

JO - Empirical Economics

JF - Empirical Economics

SN - 0377-7332

IS - 2

ER -