The three R-squareds are:
1) within: The R-squared from the mean-deviated regression, i.e. the
ordinary r-squared from running OLS on the transformed data.
2)between: first, this computes the fitted values using the
fixed-effects parameter vector and the within-individual means of the
indepdenent variables. Then calculates the r-squared as the squared
correlation between those predicted values and the within-individual
means of the original y variable.
3) overall: first, this computes the fitted values using the
fixed-effects parameter vector and the original, untransformed
independent variables. Then calculates the r-squared as the squared
correlation between those predicted values and the original,
untransformed y variable.
Seems to me like you would want the within R-squared, since you are
using the within estimator.
Justin Smith
On Wed, 16 Aug 2006 01:54:44 +0200
"Steffen H. Gr�ning" <[email protected]> wrote:
JS>Hi,
JS>
JS>I have been looking on FAQ and quite every other resource that
JS>google
JS>pointed me to. I have gotten so far as to know that when using a
JS>fixed
JS>effects model to only interpret the within r squared.
JS>But why is stata giving the other r squares as well and how can i
JS>interpret them?
JS>I haven�t found a clear cut answer to the differences and
JS>interpretations of within between and overall r squared. Maybe
JS>someone
JS>could help me out here?
JS>
JS>Thank You.
JS>Steffen.
JS>
JS>
JS>*
JS>* For searches and help try:
JS>* http://www.stata.com/support/faqs/res/findit.html
JS>* http://www.stata.com/support/statalist/faq
JS>* http://www.ats.ucla.edu/stat/stata/
Justin Smith
PhD Candidate
Department of Economics
McMaster University
Phone: (905) 962-0353
E-mail: [email protected]
*
* 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/
