ADF test SIC

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

epeter
Posts: 16
Joined: Wed May 28, 2014 1:59 am

ADF test SIC

Postby epeter » Mon May 11, 2015 8:53 am

Hi everyone and thank you all for your help. I' sorry for my poor english.

I have a quite basic question for you.
I have a series with 40 obs and I'm running an ADF test on levels (with intercept) using SIC for the selection of the lags. The output of the test says that the time series is non stationary and it includes 1 lag, but this lag is clearly non significant (prob: 0.225). Since i was confused by the fact that it included a non significant lag, I remove it manually and i got a totally different result: stationarity. Now, if i see the values of the Schwarz of the two different tests, the best choice is including the first lag, since the schwarz value is the lowest.
But is it correct to include 1 lag that is not significant only because the schwarz value is the lowest?
Shouldn't they be related in some way?

Thank you all guys!!

Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 30 guests