Re: st: RE: xtreg, fe and weights

["David W. Harless" <dwharles@vcu.edu>]

Daniel Simon wrote:
> > Hi - I'm estimating a weighted fixed-effects model. I'm using 
> > -areg- to do so. However, I want to obtain the within 
> > r-squared. When I try and run -xtreg, fe- with any of the 
> > weights options, I get an error message that weights are not 
> > allowed. So, is there any other way to get the within 
> > r-squared while estimated a weighted fe model? 
And Mark Schaffer answered:
> -xtivreg2- supports weights, and straight LSDV as well as IV, so it
> should do want you want.
Can anyone suggest texts or journal articles that explain or justify the use of weights 
that vary within panels in a fixed effects regression model (within-transformation or 
first-difference transformation)?
Dave Harless
*
*   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/