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

Re: st: test for trend with svy commands?


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: test for trend with svy commands?
Date   Thu, 21 Oct 2004 17:33:36 -0400

> > Also, wouldn't I do svylogit instead of svyreg since my
> > outcome is binary (0,1)?

Besides, if the proportion of males varies between say 48% and 53%,
you won't see any difference between probit and linear regression
results, except for scaling of the coefficients (which is related to
the standard deviation of the regression error that is fixed at 1 for
probit, and is approximately 1/2 for the above proportions). True,
your variable is 0/1, but when you want a propotion of males, you do
something like a sum, right? (-svymean- or -svyprop-). Sum is a linear
operation, and thus it corresponds to -svyreg- rather than
-svyprobit-.

-- 
Stas Kolenikov
http://stas.kolenikov.name
*
*   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