Johansen cointegration test

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

khor1984
Posts: 10
Joined: Mon Jul 02, 2012 10:59 pm

Johansen cointegration test

Postby khor1984 » Mon Jul 09, 2012 8:51 pm

Hi, if my series do not have unit root (stationary), can i do Johansen cointegration test?

Khagani
Posts: 2
Joined: Fri Jun 22, 2012 6:08 am

Re: Johansen cointegration test

Postby Khagani » Wed Jul 11, 2012 5:45 am

Cointegration tests checks the long run relationship between variables. If your variables are stationary, then you do not need to apply cointegration test (in this case Johansen)

redpen
Posts: 1
Joined: Fri Jan 04, 2013 10:05 am

Re: Johansen cointegration test

Postby redpen » Fri Jan 04, 2013 10:10 am

Some papers run Johansen cointegration even if the variables have been found to be I(0). If two variables are I(0) is it wrong to run a cointegration test?

womatar
Posts: 2
Joined: Wed Jan 02, 2013 4:59 am

Re: Johansen cointegration test

Postby womatar » Sun Jan 06, 2013 12:54 am

The purpose of testing for cointegration is to see if a group of non-stationary variables share a relationship that is stationary. So there I don't see a reason to do this for stationary variables. Straight OLS can give you residuals that are not serially correlated.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests