Re: st: RE: R squared for constrained regression

[Paul Millar <paul.millar@shaw.ca>]

Another approach is to use the PRE (Proportional Reduction of Error) 
measure.  This is R-squared for -regress- but is different for each 
type of model.  It is available from ssc:
. ssc install pre, replace

Run your model (logit, mlogit, nbreg, etc.) then type:
. pre

PRE is a measure of the predictive power of the model, that is, how 
much better the model is at predicting values of the dependent 
variable than a measure of central tendency is at predicting values 
of the dependent variable.

- Paul Millar


At 02:29 PM 08/03/2006, you wrote:

> This is an FAQ. Here is some possible reading on this and related
> questions.
>
> FAQ     . . . . . . . . . . . . . . . . . . . . . . . Do-it-yourself R-squared
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 
> .   M. Mouse
>         9/03    How can I get an R-squared value when a Stata command
>                 does not supply one?
>                 http://www.stata.com/support/faqs/stat/rsquared.html
>
> FAQ     . . . . . . . . . . . . . . . . . . . . . . . . . R-square after xtgls
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . 
> .  A. McDowell
>         4/03    Why does xtgls not report an R-square statistic?
>                 http://www.stata.com/support/faqs/stat/xtgls2.html
>
> FAQ     . . . . . . . . . . . . . . . . . . . .  Missing R-squared for 2SLS/IV
>         . . . . . . . . . . . . . . . .  W. Sribney, V. Wiggins and 
> D. Drukker
>         1/03    For two-stage least-squares (2SLS/IV/ivreg) estimates, why
>                 is the R-squared statistic not printed in some cases?
>                 For two-stage least-squares (2SLS/IV/ivreg) estimates, why
>                 is the Model Sum of Squares sometimes negative?
>                 For two-stage least-squares (3SLS/IV/ivreg) estimates, why
>                 are the R-squared and Model Sum of Squares sometimes
>                 negative?
>                 http://www.stata.com/support/faqs/stat/2sls.html
>
> FAQ     . . . . . . . . . . . . . . . . . . . .  Pseudo R-squared for xtprobit
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 
> . W. Gould
>         10/01   How can I calculate the pseudo R-squared for xtprobit?
>                 http://www.stata.com/support/faqs/stat/xtprobit.html
>
> FAQ     . . . . . . . . . . . . . . . . . . . . . . . . . Pseudo-R^2 for tobit
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 
> W. Sribney
>         6/97    Why is the pseudo-R^2 for tobit negative or greater
>                 than 1?
>                 http://www.stata.com/support/faqs/stat/pseudor2.html
>
> FAQ     . . . . . . . . . . . . . . . . . .  R-squared:  areg versus xtreg, fe
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 
> . W. Gould
>         9/96    Why isn't the calculation of R2 the same for areg
>                 and xtreg, fe?
>                 http://www.stata.com/support/faqs/stat/xtr2.html
>
> Nick
> n.j.cox@durham.ac.uk
>
> Vadim Grinevich
>
> > As you know when you run a constrained regression, the output
> > statistics
> > does not include R squared. However, I do need at least some
> > indication of
> > it in order to compare my results with those from other studies using
> > similar sort of constraints.
> >
> > To sum up, is there any way to get indication of R squared
> > for constrained
> > regression (cnsreg command)
>
> *
> *   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/
*
*   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/