How to determine Engle-Granger Cointegration?

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Posts: 28
Joined: Fri Sep 26, 2014 2:24 am

How to determine Engle-Granger Cointegration?

Postby ecofine » Sun Jun 03, 2018 6:05 am


I have to get kind comments and information again.
I ran an E-G cointegration and got these results.

Null hypothesis: Series are not cointegrated
Cointegrating equation deterministics: C @TREND
Automatic lags specification based on Schwarz criterion (maxlag=26)

Dependent tau-statistic Prob.* z-statistic Prob.*
LTP -4.513031 0.0165 -41.77165 0.0100
LCAL -3.766898 0.1172 -23.58500 0.2019
LNK -4.489272 0.0177 -41.12109 0.0113

*MacKinnon (1996) p-values.

Intermediate Results:
Rho - 1 -0.018289 -0.017810 -0.018004
Rho S.E. 0.004052 0.004728 0.004010
Residual variance 1.65E-05 0.000152 1.61E-05
Long-run residual variance 1.65E-05 5.13E-05 1.61E-05
Number of lags 0 5 0
Number of observations 2284 2279 2284
Number of stochastic trends** 3 3 3
Above results, two tau tests are rejecting the null of no-cintegration but one accepts. also, Z tests show the same results.

Do i have to reject or accept the null hypothesis of no cointegration?

In this kind of confusing results, do i have to accept more than reject?

Your kind information is very much appreciated.

Thank you.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: Google [Bot] and 1 guest