6
$\begingroup$

I'm performing a random effects analysis on panel Data, and I haven't been able to find an answer to the question, which R-square should I look at: within, between or random?

I know that for fixed effects I have to use within, but what about for random effects?

I am using Stata.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

Random effect estimator (GLS estimator) is a weighted average of between and within estimators. In Stata, the default is random effect and you need to use R-squared: overall. As specified here, R-sq: within is not correct for fixed effect and there are alternatives to correct that in Stata. For example you need to use R-square from the one provided by either regressor areg. Also, see here for details. 

use http://www.stata-press.com/data/imeus/traffic, clear

xtreg fatal beertax spircons unrate perinc

or 

xtreg fatal beertax spircons unrate perinc, re
Improve this answer
$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.