You can use -test- after the -svymean- procedure. Assuming that x2 is
coded 0/1:
. svymean x1, by(x2)
. test [x1]0=[x1]1
(If you are using stata 7, then you need to use -svytest- rather than
-test-).
--Nick
-----------------------------------------------------------
Nicholas Winter, Ph.D. P 202.939.5343
Policy Studies Associates F 202.939.5732
1718 Connecticut Avenue, NW [email protected]
Washington, DC 20009-1148 www.policystudies.com
-----------------------------------------------------------
> -----Original Message-----
> From: Robert Bozick [mailto:[email protected]]
> Sent: Saturday, May 03, 2003 3:51 PM
> To: [email protected]
> Subject: st: t tests with complex survey data
>
>
> Hello Everyone --
>
> I was wondering if anyone knew how to do a difference of
> means tests when using complex survey data (clustered, stratified).
>
> I tried the survey mean procedure:
> svymean (x1) by x2
>
> However, this just gives me the estimates of x1 for each
> category of x2. Is there a way to perform a difference of
> means that adjusts the standard errors for the clustered,
> stratified nature of my sample AND gives me the t statistics
> and p values?
>
> Thanks in advance!
>
> *
> * 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/
