Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: R2 with xtreg, re


From   "P. Grant" <ssrnmail@gmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: R2 with xtreg, re
Date   Tue, 3 Nov 2009 09:14:54 -0000

Hi everyone, 

Yesterday I tried sending an email to the list, for some reason it didn't
get through. Here it goes again.

I'm running a random effect model using - xtreg , re - but I'm having some
difficulties interpreting the R-squared results. According to the manual,
"xtreg, re obtains its estimates by performing OLS on (4); none of the R2s
corresponding to (1'''), (2'''), or (3'''') correspond directly to this
estimator (the "relevant" R2 is the one corresponding to (4)). All three
reported R2s are correlations squared, or, if you prefer, from second-round
regressions." 

Given this, how can I retrieve the R2 for my estimated model? After an
online search, it seems that SAS and LIMDEP report R2 for random effects
panel data models
(http://www.indiana.edu/~statmath/stat/all/panel/panel7.html). I don't have
access to these, so how can I report an R2 using Stata? 

Thanks in advance, 

Peter

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index