Mixed Signals among Tests for Cointegration

  title={Mixed Signals among Tests for Cointegration},
  author={Allan W. Gregory and Alfred Haug and Nicoletta A Lomuto},
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 Ẑα) 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… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Explore Further: Topics Discussed in This Paper


Publications referenced by this paper.
Showing 1-10 of 23 references

Tests for parameter instability in regressions with I(1) processes

Hansen BE.
Journal of Business and Economic Statistics 10: 321–335. • 1992
View 5 Excerpts
Highly Influenced

Testing for cointegration in linear quadratic models

Gregory AW.
Journal of Business and Economic Statistics 4: 347–360. • 1994
View 3 Excerpts
Highly Influenced

Testing for cointegration rank of a VAR process with an intercept

P Saikonnen, H. Lütkepohl
Econometric Theory 16: 373–406. • 2000
View 1 Excerpt

Large sample properties of posterior densities, Bayesian information criterion and the likelihood principle in nonstationary time series models

Kim JY.
Econometrica 66: 359-80. • 1998

Finding cointegration rank in high dimension systems using the Johansen test

MS Ho, Sorensen BE.
An illustration using data based Monte Carlo simulations. Review of Economics and Statistics 78: 7726–732 • 1996

Numerical distribution functions for unit root and cointegration tests

MacKinnon JG.
Journal of Applied Econometrics 11: 601–618. • 1996

Tests for cointegration: a Monte Carlo comparison

Haug AA.
Journal of Econometrics 71: 89–115. • 1996

Similar Papers

Loading similar papers…