Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: k-sample tests for differences in proportions


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: k-sample tests for differences in proportions
Date   Wed, 5 Nov 2003 14:49:03 -0000

The mean of a binary variable is totally interpretable; 
in this case the interpretation is not that an individual 
has half a degree, but that on average half the individuals 
have degrees. 

Logit, probit and much else would not make sense otherwise. 

Nick 
n.j.cox@durham.ac.uk 

Jingky P. Lozano
 
> I was thinking that you can probably use Kruskall-Wallis 
> which is the nonpar 
> equivalent of ANOVA but since you only have two possible 
> answer (with Univ and 
> without univ degree) per religion, I agree that you can 
> just simply use chi-
> square.  There will really be not much use in comparing the 
> means.  A 0.5 mean 
> in education variable cannot be interpreted as incomplete 
> Univ degree since 
> your coding system is categorical.  I think it is more 
> appropriate to use chi-
> square. 

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index