st: Re: How to test for the country and time effect in the fixed effect model?

[Kit Baum <baum@bc.edu>]

See the [XT] xtreg manual entry (or any good econometrics text: pp.  
226-227 in my book, URL below) re the between estimator. Essentially  
it is a regression on N observations which are the averages of their  
respective time series.

The -xtreg- command does not include time effects. If you want them,  
create dummies for each time period and include all but one in the  
regression. A standard -test- for their joint significance will  
indicate whether you should include them. The F-test at the foot of - 
xtreg- is the test for the existence of country effects.


Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


On Jun 15, 2007, at 2:33 AM, Carine wrote:


> At the moment I am writing my thesis and I have to work with panel  
> data and STATA. I am a beginner with respect to both and therefore  
> I was wondering whether somebody could help me with the following  
> two questions:
> 1. what does the between estimator actually calculate? I am only  
> familiar with the fixed and random effects model in panel data.
> 2. For the estimation of the fixed effects model, I use xtreg  
> depvar variablelist, fe. Does this command automatically take care  
> of both the country and time effect that are present in the fixed  
> effect model? And how can I test whether there is a country effect  
> but no time effect, or the other way around?
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/