To read this content please select one of the options below:

Regression‐based cointegration estimators with applications

G.C. Lim (University of Melbourne, Parkville, Victoria, Australia)
Vance L. Martin (University of Melbourne, Parkville, Victoria, Australia)

Journal of Economic Studies

ISSN: 0144-3585

Article publication date: 1 February 1995

762

Abstract

Provides a framework for understanding the relationships between alternative cointegrating estimators with special attention given to single equation procedures. The approach consists of augmenting the long‐run model with general short‐run dynamic specifications and identifying the specific assumptions implied by each of these estimators about the short‐run dynamics. Understanding this hierarchical structure between estimators is important since it shows the conditions when consistent and asymptotically efficient parameter estimates may be obtained from standard econometric packages. Since the alternative estimators are shown to be nested in a general framework, this suggests that general‐to‐specific methodology may be adopted to test between these alternative specifications. To highlight the salient characteristics of the alternative estimators, the framework is related to two theoretical economic models: stock prices and money demand; and applied to the demand for imports and testing of the crowding out hypothesis.

Keywords

Citation

Lim, G.C. and Martin, V.L. (1995), "Regression‐based cointegration estimators with applications", Journal of Economic Studies, Vol. 22 No. 1, pp. 3-22. https://doi.org/10.1108/01443589510076061

Publisher

:

MCB UP Ltd

Copyright © 1995, MCB UP Limited

Related articles