Granger Causality in VECM

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

cjr977
Posts: 2
Joined: Sun Apr 02, 2017 8:26 am

Granger Causality in VECM

Postby cjr977 » Mon May 01, 2017 7:02 am

Hi all,

I have estimated a VEC model for a set of 10 macroeconomic variables using five cointegrating equations, as suggested by the Johansen test. Once I run Granger causality tests (Wald), for the model of interest I have found that one variable unidirectionally Granger causes the dependent variable. Additionally, the IRFs show a large response to innovations in the variable that is found to Granger cause y. However, within the VECM framework, the coefficients for the lagged values of the x variable in question are insignificant. Does this suggest that the impulse is resulting from the long-run relationship between the variables, or is this suggestive of a misspecified/unstable model/another issue with the model?

I can, of course, provide any further details if needed. I would greatly appreciate any guidance if anyone happens to know what this result may mean!

Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 27 guests