Johansen Cointegration test on strend stationary series
Posted: Tue Jun 12, 2012 6:44 am
Hi all,
my question in concerning the Johansen cointegration test.
If I test 2 series for stationarity and they turn out to be trend-stationary, does it make sense to test them for cointegration?
I think if they have a time(deterministic)-trend, they are not cointegrated but just have a common trend which has nothing to do with cointegration.
And if so, what does option number 4 in the Johansen-test mean (EViews Users Guide II, pp. 686-688).
I think I just did not really understand which option to chose for what kind of series. I found no hint on that in this forum...
Thanks for a short answer!
my question in concerning the Johansen cointegration test.
If I test 2 series for stationarity and they turn out to be trend-stationary, does it make sense to test them for cointegration?
I think if they have a time(deterministic)-trend, they are not cointegrated but just have a common trend which has nothing to do with cointegration.
And if so, what does option number 4 in the Johansen-test mean (EViews Users Guide II, pp. 686-688).
I think I just did not really understand which option to chose for what kind of series. I found no hint on that in this forum...
Thanks for a short answer!