Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: MCKelvey and Zavoina


From   "enrico" <[email protected]>
To   <[email protected]>
Subject   st: MCKelvey and Zavoina
Date   Sat, 2 Jun 2012 14:19:35 +0200

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?

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



*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index