cointegration test output in Group object

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

Varesearcher
Posts: 2
Joined: Wed May 11, 2016 6:50 am

cointegration test output in Group object

Postby Varesearcher » Thu May 12, 2016 5:24 am

I'm having trouble understanding what the output is for coefficients on the Johansen cointegration test in EViews 9. The User's Guide says I can test cointegration using an estimated VAR object, Equation object, or Group object. However, I don't understand how the results match up across those choices. Why do I get a different output of coefficients depending on whether I use Group or VAR objects for cointegration tests? What exactly do the Group object coefficent estimates show? I'm talking about the second half of the output in the Group object, after the cointegration tests. In the second half, the output lists for 1 cointegrating relationship, a list of "nomralized cointegrating coefficients" and "adjustment coefficients." It does this for each possibility of conintegration. These are not the same coefficients as the coefficients in the output for the VAR object, where you can estimate a VECM. What are they? How do you reconcile the two competing sets of coefficients?

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests