Page 1 of 1
How to analyze panel data?
Posted: Mon Oct 25, 2010 12:25 pm
by miki1zg
After I enter data into a panel workfile, I don't know how to analyze them. Can someone help me?
I have data divided by countries and by years, two variables. In the simple regression model I would like to do the model Y=c(1)+c(2)X, but I don't know how to do this with panel data.
How to analyze panel data?
Posted: Mon Oct 25, 2010 12:48 pm
by EViews Gareth
Same way you do it in a non-panel workfile
Re: How to analyze panel data?
Posted: Mon Oct 25, 2010 12:56 pm
by startz
Also, there is an introductory chapter on panel data in EViews Illustrated.
Re: How to analyze panel data?
Posted: Mon Oct 25, 2010 1:02 pm
by miki1zg
In the non panel data I just write the the equation in "estimate equation" box, and I get the model analysis. And I don't see this option here...
Re: How to analyze panel data?
Posted: Mon Oct 25, 2010 1:03 pm
by miki1zg
Also, there is an introductory chapter on panel data in EViews Illustrated.
I think I have seen this, but I couldn't find the part about the procedure (or steps) for making the analysis.
Re: How to analyze panel data?
Posted: Mon Oct 25, 2010 1:09 pm
by EViews Gareth
You write it in the estimate equation box too. Everything is the same.
Re: How to analyze panel data?
Posted: Thu Oct 28, 2010 2:33 am
by miki1zg
Thanks, I did it so. But now I have the problem with Durbin Watson. The value is always somewhere near 0. I tried to take different data, and I get the same. Should I use some other indicator for detecting autocorrelation? Because with DW it seems that all panel data are positively autocorrelated.