VECM-selection of cointegrating equations

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Javo
Posts: 1
Joined: Fri Sep 04, 2015 7:58 am

VECM-selection of cointegrating equations

Postby Javo » Fri Sep 04, 2015 8:34 am

Hello, I hope you have some advice for me on this. I would like to run a VEC model with five endogenous variables, all I(1). I tested for cointegration after running a VAR (using all my 5 variables) and both, the trace statistic, and the maximum Eigenvalue tests suggest the existence of two (2) cointegrating equations. Yet I am struggling to choose which of my five endogenous variables are the ones that are cointegrated?

I am aware that the usual answer would be that it depends in your specific model and what the theory suggests about this. Yet I can think of theoretical considerations could support long-term cointegrating relations for at least four of the variables that I am using, but I have to choose only two. Is there a formal way to guide this decision?

Many thanks in advance!

Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 1 guest