Difference in J-stats under TSLS

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

oksanakim
Posts: 56
Joined: Wed Apr 04, 2012 10:38 am

Difference in J-stats under TSLS

Postby oksanakim » Wed Sep 20, 2017 7:02 am

Good morning All

I have run the TSLS because one of the variables may be endogenous. I am not sure how to interpret the results of the Regressor endogeneity test:



Value df Probability
Difference in J-stats 1.737618 2 0.4195

J-statistic summary:
Value
Restricted J-statistic 1.737618
Unrestricted J-statistic 0.000000


Does the above suggest that the instrument I used was not efficient? What exactly in the Null under this test? Thank you in advance!!

oksanakim
Posts: 56
Joined: Wed Apr 04, 2012 10:38 am

Re: Difference in J-stats under TSLS

Postby oksanakim » Wed Sep 20, 2017 7:24 am

I forgot to mention that upob TSLS estimation using and IV variable, the previously significant result on the endogenous variable became insignificant, and the R-sq became negative... Does this all suggest the instrument I chose makes no sense? Thank you.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 23 guests