Some frequency domain properties of fractionally cointegrated processes
Claudio Morana
Applied Economics Letters, 2004, vol. 11, issue 14, 891-894
Abstract:
The paper shows that the multiple squared coherence at the zero frequency for fractionally differenced (fractionally) cointegrated processes is equal to one, while the simple squared coherences assume a value greater than zero but lower than one. In the bivariate case the multiple and simple squared coherence coincide and, therefore, the simple squared coherence at the zero frequency assumes a unitary value. It is also found that processes that are not fractionally cointegrated show, in general, positive, but lower than one, multiple and simple squared coherences at the zero frequency. In the case the dependent and independent variables are driven by different long memory factors, i.e. in the case when the dependent variable is orthogonal at the zero frequency to any of the regressors, the squared multiple coherence will assume a zero value, as any of the squared simple coherences. It is finally shown that all the above results also hold for the series in levels, as the frequency tends to zero.
Date: 2004
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)
Downloads: (external link)
http://www.informaworld.com/openurl?genre=article& ... 40C6AD35DC6213A474B5 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:apeclt:v:11:y:2004:i:14:p:891-894
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RAEL20
DOI: 10.1080/1350485042000261289
Access Statistics for this article
Applied Economics Letters is currently edited by Anita Phillips
More articles in Applied Economics Letters from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().