Journal Information  ·  Mission  ·  Editorial Board  ·  Directory of Economists Submissions  ·  New Submission  ·  Submit a Revision Table of Contents  ·  Refereed Content            Notes            Comments            Preliminary Results  ·  Research       Announcements  ·  Letters to the Editor  ·  Conference       Announcements  ·  Search Email Notification Service and Directory of Research Economists  ·  Add me to Directory  ·  Modify my Profile General  ·  Submission Guidelines  ·  PDF Conversion  ·  Copyright  ·  Electronic Publishing  ·  Archiving  ·  Sponsors and       Endorsements  ·  Economic Links     David O. Cushman "Further evidence on the size and power of the Bierens and Johansen cointegration procedures" (2003, Vol. 3, No. 25.)     Although both the Johansen (1991, 1994) trace test and Bierens (1997a,b) nonparametric lambda-min test for cointegration have good size properties in Monte Carlo studies by Hubrich, Lutkepohl, and Saikkonen (2001) and Boswijk, Lucas, and Taylor (2000), the Bierens test has very low power. In contrast, Bierens reports good power for his procedure. Meanwhile, Hubrich et al. and Boswijk et al. do not include Bierens' companion method for estimating the number of cointegrating vectors, nor do they investigate the effect of serial correlation on Bierens' test. In the present paper, inclusion of the estimation step does not significantly degrade size of the Bierens procedure, even with serial correlation, but power is not improved. Serial correlation does degrade the size of the Johansen test, but it remains superior. Analysis of Bierens' (1997b) Monte Carlo results suggests that their indication of high power reflects the test's lack of scale invariance.     Keywords :   Bierens nonparametric cointegration test, Johansen cointegration test, Monte Carlo     Manuscript Received : 5/12/2003   Manuscript Accepted : 10/8/2003   This abstract has been downloaded 1356 times.