Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

TESTING FOR AUTOCORRELATION IN DYNAMIC LINEAR MODELS*

TESTING FOR AUTOCORRELATION IN DYNAMIC LINEAR MODELS* If the disturbances of a linear model are autocorrelated, ordinary .>ast squares ( LS) estimates of the coefficient parameters are inefficient but unbiased. However, in a dynamic equation where lagged values of the dependent variable appear as regressors, least squares estimates are biased and generally inconsistent. For this reason it is important to have available tests against autocorrelation, particularly when it is a dynamic model which is proposed to be estimated by OLS. But the standard tests based on OLS residuals, notably that of Durbin and Watson [4] and the extensions by Schmidt [ 101 and Wallis [ 121 , are invalid when some of the regressors are lagged values of the dependent variable. These tests are attractive because they avoid the obvious approach of estimating the model with the disturbance process incorporated explicitly and making inference from estimates of parameters in the disturbance process. This latter approach is available in the case of dynamic models but is not widely practised because of the relatively heavy computational requirement to obtain maximum likelihood (ML) estimates of the parameters. Thus the importance of the seminal contribution of Durbin [S] who showed that it was possible to construct (asymptotically) valid tests http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Australian Economic Papers Wiley

TESTING FOR AUTOCORRELATION IN DYNAMIC LINEAR MODELS*

Australian Economic Papers , Volume 17 (31) – Dec 1, 1978

Loading next page...
 
/lp/wiley/testing-for-autocorrelation-in-dynamic-linear-models-qHIoxAKKOp

References (10)

Publisher
Wiley
Copyright
Copyright © 1978 Wiley Subscription Services, Inc., A Wiley Company
ISSN
0004-900X
eISSN
1467-8454
DOI
10.1111/j.1467-8454.1978.tb00635.x
Publisher site
See Article on Publisher Site

Abstract

If the disturbances of a linear model are autocorrelated, ordinary .>ast squares ( LS) estimates of the coefficient parameters are inefficient but unbiased. However, in a dynamic equation where lagged values of the dependent variable appear as regressors, least squares estimates are biased and generally inconsistent. For this reason it is important to have available tests against autocorrelation, particularly when it is a dynamic model which is proposed to be estimated by OLS. But the standard tests based on OLS residuals, notably that of Durbin and Watson [4] and the extensions by Schmidt [ 101 and Wallis [ 121 , are invalid when some of the regressors are lagged values of the dependent variable. These tests are attractive because they avoid the obvious approach of estimating the model with the disturbance process incorporated explicitly and making inference from estimates of parameters in the disturbance process. This latter approach is available in the case of dynamic models but is not widely practised because of the relatively heavy computational requirement to obtain maximum likelihood (ML) estimates of the parameters. Thus the importance of the seminal contribution of Durbin [S] who showed that it was possible to construct (asymptotically) valid tests

Journal

Australian Economic PapersWiley

Published: Dec 1, 1978

There are no references for this article.