Re: R: st: MCKelvey and Zavoina

[Richard Williams <richardwilliams.ndu@gmail.com>]

At 10:24 AM 6/2/2012, enrico wrote:

> Thank you very much!!

You are welcome. For more on the different Pseudo R^2 measures, 
including formulas and rationales, see the appendix of

http://www.nd.edu/~rwilliam/stats3/L04.pdf

Also, while you appear to be ok, people often have an old version of 
-fitstat- installed. The most current version is on Scott Long's site 
and is part of his spost9 package. Type

findit spost9

to get and install it.

> -----Messaggio originale-----
> Da: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di Richard Williams
> Inviato: sabato 2 giugno 2012 18.06
> A: statalist@hsphsun2.harvard.edu; statalist@hsphsun2.harvard.edu
> Oggetto: Re: st: MCKelvey and Zavoina
>
> At 07:19 AM 6/2/2012, enrico wrote:
> >Dear Statalist,
> >
> >my name is Enrico and I am an italian student. I'm working with Stata but I
> >have a problem. I know that the formula to calculate the Pseudo R-square
> >MCkelvey and Zavoina is R^2=Var(y*)/(Var(y*)+Var(error)), where Var(error)
> >in the Logit is equal to 3.14^2/3 while in the Probit is equal to 1.
> >
> >Why if I use this formula in this case I don't obtein the exact value? In
> >fact  6.84/(6.84+3.29)=0.675 and not 0.519. Which formula do you use
> >instead?
>
> Wrong formula. V(y*) already includes V(e). You need to SUBTRACT V(e)
> from the numerator rather than add it to the denominator. Then it
> becomes the logical analog of Explained variance/ Total variance. So,
>
> (6.84 - 3.29)/6.84 = .519
>
>
> >logit honcomp female read science
> >fitstat, sav(r2_1)
> >
> >Measures of Fit for logit of honcomp
> >
> >Log-Lik Intercept Only:       -115.644   Log-Lik Full Model:
> >-80.118
> >D(196):                        160.236   LR(3):
> >71.052
> >                                          Prob > LR:
> >0.000
> >McFadden's R2:                   0.307   McFadden's Adj R2:
> >0.273
> >ML (Cox-Snell) R2:               0.299   Cragg-Uhler(Nagelkerke) R2:
> >0.436
> >McKelvey & Zavoina's R2:         0.519   Efron's R2:
> >0.330
> >Variance of y*:                  6.840   Variance of error:
> >  3.290
> >Count R2:                        0.810   Adj Count R2:
> >0.283
> >AIC:                             0.841   AIC*n:
> >168.236
> >BIC:                          -878.234   BIC':
> >-55.158
> >BIC used by Stata:             181.430   AIC used by Stata:
> >168.236
> >
> >Thank you,
> >Enrico
> >

-------------------------------------------
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/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/