Testing for Cointegration in the Presence of Moving Average Errors

Mindy Mallory 1  and Sergio H. Lence 2
  • 1 University of Illinois at Urbana-Champaign
  • 2 Iowa State University


This study explores performance of the Johansen cointegration statistics on data containing negative moving average (NMA) errors. Monte Carlo experiments demonstrate that the asymptotic distributions of the statistics are sensitive to NMA parameters, and that using the standard 5% asymptotic critical values results in severe underestimation of the actual test sizes. We demonstrate that problems associated with NMA errors do not decrease as sample size increases; instead, they become more severe. Further we examine evidence that many U.S. commodity prices are characterized by NMA errors. Pretesting data is recommended before using standard asymptotic critical values for Johansen’s cointegration tests.

Purchase article
Get instant unlimited access to the article.
Log in
Already have access? Please log in.

Journal + Issues

The Journal of Time Series Econometrics (JTSE) serves as an internationally recognized outlet for important new research in both theoretical and applied classical and Bayesian time series, spatial and panel data econometrics. The scope of the journal includes papers dealing with estimation, testing and other methodological aspects involved in the application of time series and spatial analytic techniques to economic, financial and related data.