The Granger Non-Causality Test in Cointegrated Vector Autoregressions

Hiroaki Chigira and Taku Yamamoto

Hi-Stat Discussion Paper Series from Institute of Economic Research, Hitotsubashi University

Abstract: In general, Wald tests for the Granger non-causality in vector autoregressive (VAR) process are known to have non-standard asymptotic properties for cointegrated systems. However, that may have standard asymptotic properties depending on the rank of the submatrix of cointegration. In this paper, we propose a procedure for conducting Granger non-causality tests that are based on discrimination of these asymptotic properties. This paper also investigate the finite sample performance of our testing procedure, and compare the testing procedure with conventional causality tests in levels VAR’s.

Keywords: Vector autoregression; Cointegration; Granger causality; Hypothesis testing (search for similar items in EconPapers)
JEL-codes: C12 C32 (search for similar items in EconPapers)
Date: 2003-12
New Economics Papers: this item is included in nep-ecm, nep-ets and nep-rmg
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://hi-stat.ier.hit-u.ac.jp/research/discussion/2003/pdf/D03-07.pdf (application/pdf)

Related works:
Working Paper: The Granger Non-Causality Test in Cointegrated Vector Autoregressions (2003)
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:hst:hstdps:d03-07

Access Statistics for this paper

More papers in Hi-Stat Discussion Paper Series from Institute of Economic Research, Hitotsubashi University Contact information at EDIRC.
Bibliographic data for series maintained by Tatsuji Makino ().