Simple procedures for testing autoregressive versus moving average errors in regression models

Colin R Mckenzie, Michael Mcaleer, Len Gill

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper develops several simple separate (or non-nested) procedures for testing autoregressive versus moving average errors in regression models. These asymptotically valid tests are straightforward to calculate: after estimating both models by maximum likelihood methods, the procedure involves testing the significance of variables added to a linearized version of the null model, the added variables being the predictions, or the residuals from the specified alternative model, or the difference of the predictions of the two models. Some small sample evidence on the properties of the tests is presented, as is an empirical application on the Australian unexpected inflation rate series. JEL Classification Numbers: C12, C22, C52, E31.

Original languageEnglish
Pages (from-to)239-252
Number of pages14
JournalJapanese Economic Review
Volume50
Issue number3
Publication statusPublished - 1999 Sep
Externally publishedYes

Fingerprint

Regression model
Testing
Moving average
Prediction
Inflation rate
Small sample
JEL classification
Alternative models
Maximum likelihood

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Simple procedures for testing autoregressive versus moving average errors in regression models. / Mckenzie, Colin R; Mcaleer, Michael; Gill, Len.

In: Japanese Economic Review, Vol. 50, No. 3, 09.1999, p. 239-252.

Research output: Contribution to journalArticle

@article{858c2b2df6244b19b65a78d999fee84a,
title = "Simple procedures for testing autoregressive versus moving average errors in regression models",
abstract = "This paper develops several simple separate (or non-nested) procedures for testing autoregressive versus moving average errors in regression models. These asymptotically valid tests are straightforward to calculate: after estimating both models by maximum likelihood methods, the procedure involves testing the significance of variables added to a linearized version of the null model, the added variables being the predictions, or the residuals from the specified alternative model, or the difference of the predictions of the two models. Some small sample evidence on the properties of the tests is presented, as is an empirical application on the Australian unexpected inflation rate series. JEL Classification Numbers: C12, C22, C52, E31.",
author = "Mckenzie, {Colin R} and Michael Mcaleer and Len Gill",
year = "1999",
month = "9",
language = "English",
volume = "50",
pages = "239--252",
journal = "Japanese Economic Review",
issn = "1352-4739",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Simple procedures for testing autoregressive versus moving average errors in regression models

AU - Mckenzie, Colin R

AU - Mcaleer, Michael

AU - Gill, Len

PY - 1999/9

Y1 - 1999/9

N2 - This paper develops several simple separate (or non-nested) procedures for testing autoregressive versus moving average errors in regression models. These asymptotically valid tests are straightforward to calculate: after estimating both models by maximum likelihood methods, the procedure involves testing the significance of variables added to a linearized version of the null model, the added variables being the predictions, or the residuals from the specified alternative model, or the difference of the predictions of the two models. Some small sample evidence on the properties of the tests is presented, as is an empirical application on the Australian unexpected inflation rate series. JEL Classification Numbers: C12, C22, C52, E31.

AB - This paper develops several simple separate (or non-nested) procedures for testing autoregressive versus moving average errors in regression models. These asymptotically valid tests are straightforward to calculate: after estimating both models by maximum likelihood methods, the procedure involves testing the significance of variables added to a linearized version of the null model, the added variables being the predictions, or the residuals from the specified alternative model, or the difference of the predictions of the two models. Some small sample evidence on the properties of the tests is presented, as is an empirical application on the Australian unexpected inflation rate series. JEL Classification Numbers: C12, C22, C52, E31.

UR - http://www.scopus.com/inward/record.url?scp=0032871726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032871726&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032871726

VL - 50

SP - 239

EP - 252

JO - Japanese Economic Review

JF - Japanese Economic Review

SN - 1352-4739

IS - 3

ER -