Page 1 of 1

Differences-in-difference estimation

Posted: Sun Jan 23, 2011 6:57 am
by antionio
I've searched both Eviews manuls for the panel data method, differences-in-difference estimation but i cannot find anything.
Does anyone know if it's possible to do this in Eviews at all?

Re: Differences-in-difference estimation

Posted: Mon Jan 24, 2011 10:33 am
by EViews Glenn
Difference-in-differences estimates can generally be obtained using some form of dummy variables specification. You'll have to make a decision on how you want to specify the model.

A useful reference is the lectures notes by Imbens and Wooldridge...

http://www.nber.org/WNE/lect_10_diffindiffs.pdf

Re: Differences-in-difference estimation

Posted: Fri May 23, 2014 2:17 pm
by MarcusD1984
Dear Glenn,

thanks for posting the Wooldridge paper. However, I am still not sure how to implement the difference-indifference estimator in eViews.
Any advice how to do it practically? I have a binary (0,1) variable that is 1 in one year throughout a panel of 5 years with n=50 firms. Then I want to look at the firms development over time.

Thanks so much for your help,

Marcus