Comparing Coefficients of two samples

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

loukk
Posts: 2
Joined: Mon Dec 09, 2013 3:57 am

Comparing Coefficients of two samples

Postby loukk » Mon Dec 09, 2013 4:05 am

Hi,

I don't how to compare the coefficients of my panel data fixed effect regression, reading other topics I should put the 2 samples into 1 and add a dummy. So that what I did, my regression looks like this:

blev = c tan prf gop siz nts iva Dcrisis

My data contains 10 years, first 5 year Dcrisis=0, other 5 year Dcrisis=1. I should run a wald test to test if tan(dcrisis=0)=tan(dcrisis=1) is this possible? My professor adviced me to use interaction terms but I could't find how.

How should I solve this?

loukk
Posts: 2
Joined: Mon Dec 09, 2013 3:57 am

Re: Comparing Coefficients of two samples

Postby loukk » Mon Dec 09, 2013 6:27 am

I just figured out a possible solution:

smpl @all
equation e.ls blev c (dcrisis=0)*tan (dcrisis=1)*tan (dcrisis=0)*prf (dcrisis=1)*prf (dcrisis=0)*siz (dcrisis=1)*siz (dcrisis=0)*gop (dcrisis=1)*gop (dcrisis=0)*nts (dcrisis=1)*nts (dcrisis=0)*iva (dcrisis=1)*iva

now I only need to add cross section fixed effects then i'm able to run the several wald restriction tests.

Is this the right way to perform the test?


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests