Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: pairwise granger causality--error in manual??
From
[email protected]
To
[email protected]
Subject
st: pairwise granger causality--error in manual??
Date
Tue, 16 Mar 2010 17:38:28 +0100
Hi everybody,
Why are granger-causality tests only valid in the bivariate framework? I found a lot of times in books like Hamilton's time series analysis the comment that granger-causality tests are only valid in a bivariate framework if tested via a standard F-test.
But the STATA TS manual (Example 1, p. 420) employs a granger-causality test on three variables while its description says "vargranger — Perform pairwise Granger causality tests after var or svar".
I am quite confused now??!!
What does "pairwise" mean?? Should only the "excluded ALL" be used for interpretation??
Some addition:
I am into this stuff for a few days and found at http://www.scholarpedia.org/article/Granger_causality that when using bivariate granger causality tests but the data generating process consists of three variables, the results should be interpreted carefully. What I don't get of the scholarpedia article is WHY it is not allowed to simply use the F-test not in the bivariate but the trivariate setting, then??
Kind regards
Dedder
--
GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/