Re: st: RE: KcKelvey & Zavoina's R2 in -fitstat- after -gologit2-

[Ted Anagnoson <anag999@silcom.com>]

Well, McKelvey and Zavoina's R2 keeps popping up, so permit me a short 
story, which is that in 1972 I was taking the poli sci version of 
econometrics that Dick McKelvey taught and we got to logits and probits, 
etc., and McKelvey started talking about his R2 that he and Bill Zavoina 
had developed.

I distinctly remember Dick saying it was better than nothing, but not by 
very much, and that the whole notion of R2 wasn't appropriate for 
logistic/probit analysis....which has already come up in the discussion.

At any rate, it stuck in my mind from my first year in graduate school way 
too many years ago.

Ted Anagnoson
California State University, Los Angeles





At 06:21 PM 3/5/2008 -0500, Richard Williams wrote:

> > There was a similar question posed last year, but the solution suggested
> >
> > to that post (see below) gives me an estimate of "." I'm not sure what
> > that means.
> >
> > sysuse auto
> > logit foreign price
> > fitstat
> > estadd scalar r2_mz = r(r2_mz)
> >
> > and then tabulate using:
> >
> > estout ., eform cells(n se(par)) stats(r2_mz) style(fixed)
> >
> > or:
> >
> > esttab ., eform se scalars(r2_mz)
> I just tried it, and the above code works fine for me:
>
> . estout ., eform cells(n se(par)) stats(r2_mz) style(fixed)
>
>                      n/se
> price
>                (.0000844)
> _cons
>                (.1996672)
> r2_mz            .0032806
>
> . esttab ., eform se scalars(r2_mz)
>
> ----------------------------
>                       (1)
>                   foreign
> ----------------------------
> price               1.000
>               (0.0000844)
> ----------------------------
> N                      74
> r2_mz             0.00328
> ----------------------------
> Exponentiated coefficients; Standard errors in parentheses
> * p<0.05, ** p<0.01, *** p<0.001
>
> Are you sure you have the latest and greatest version of -fitstat-?  The 
> version on SSC is NOT the most current.  Rather, J. Scott Long maintains 
> the latest version of his software on his own site.  Try
>
> findit spost9
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME:   (574)289-5227
> EMAIL:  Richard.A.Williams.5@ND.Edu
> 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/
*
*   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/