 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Validity of R Square with -nl- Regressions
At 08:24 AM 6/20/2008, Nick Cox wrote:
Funny. Maarten sees this definition as "obvious", and I do understand
why.
I was brought up an old-fashioned way with lots of correlation before
regression and still tend to see the definition of R-square as the
square of the correlation between observed and fitted as the "obvious"
one.
No doubt there are now people who see a definition in terms of
likelihood results as the "obvious" one.
Continuing this sidelight - I give several formulas for OLS and their
logical Pseudo R^2 analogs at
http://www.nd.edu/~rwilliam/xsoc73994/L04.pdf
For OLS, the formulas all give the same results, but the Pseudo R^2
stats all give different numbers. Counter to the claims of some, I
don't think logic alone clearly favors one Pseudo R^2 measure over another.
One thing I do find kind of remarkable is that the Maximum Likelihood
R^2 (aka Cox-Snell) isn't just a logical analog - it is the exact
same formula for OLS R^2 and Pseudo R^2. That might be why, as Nick
says, some may think this is the "obvious" measure.
I'm not quite sure why McFadden's Pseudo R^2 came to be blessed by
Stata, but I suppose it is as good as any.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/