Mixed signals among tests for cointegration
Article first published online: 11 FEB 2004
Copyright © 2004 John Wiley & Sons, Ltd.
Journal of Applied Econometrics
Volume 19, Issue 1, pages 89–98, January/February 2004
How to Cite
Gregory, A. W., Haug, A. A. and Lomuto, N. (2004), Mixed signals among tests for cointegration. J. Appl. Econ., 19: 89–98. doi: 10.1002/jae.733
- Issue published online: 11 FEB 2004
- Article first published online: 11 FEB 2004
- Manuscript Revised: 25 NOV 2002
- Manuscript Received: 24 SEP 2001
This paper illustrates that, under the null hypothesis of no cointegration, the correlation of p-values from a single-equation residual-based test (i.e., ADF or ) with a system-based test (trace or maximum eigenvalue) is very low even as the sample size gets large. With data-generating processes under the null or ‘near’ it, the two types of tests can yield virtually any combination of p-values regardless of sample size. As a practical matter, we also conduct tests for cointegration on 132 data sets from 34 studies appearing in this Journal and find substantial differences in p-values for the same data set. Copyright © 2004 John Wiley & Sons, Ltd.