Skip to main content
Article
Testing for Cointegration in the Presence of Moving Average Errors
Journal of Time Series Econometrics
  • Mindy Mallory, University of Illinois at Urbana-Champaign
  • Sergio H Lence, Iowa State University
Document Type
Article
Publication Version
Published Version
Publication Date
1-1-2012
DOI
10.1515/1941-1928.1124
Abstract
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.
Comments

This article is from Journal of Time Series Econometrics 4 (2012): 1, doi:10.1515/1941-1928.1124. Posted with permission.

Copyright Owner
De Gruyter
Language
en
File Format
application/pdf
Citation Information
Mindy Mallory and Sergio H Lence. "Testing for Cointegration in the Presence of Moving Average Errors" Journal of Time Series Econometrics Vol. 4 Iss. 2 (2012) p. 1 - 68
Available at: http://works.bepress.com/sergio_lence/17/