Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Comparing proportions using survey data


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Comparing proportions using survey data
Date   Tue, 13 Apr 2010 13:52:53 -0400

Omar <O.S.Mcdoom@lse.ac.uk> :

webuse nhanes2, clear
g north=region==1
svy:tab north highbp, row se
test _b[p12]=_b[p22]

insufficient imprecision?

On Tue, Apr 13, 2010 at 1:38 PM,  <O.S.Mcdoom@lse.ac.uk> wrote:
> Folks,
>
> I have individual-level survey data (n=294).  I would like to compare
> the proportions of responses to one question (a binary variable) across
> two regions: north (n=154) and south (n=140).
>
> I believe I should treat the two regions as independent samples. The
> survey sample design is a cluster sample stratified by region so that no
> individuals in the sample from the north region appear in the sample
> from the south region.
>
> Stata's prtest command does not support the survey (svy) command.  How
> may I measure the significance of the difference between the proportion
> of responses of northerners against the proportion of responses of
> southerners - whilst taking into account the survey design effects?
>
> I posted a similar query earlier but with insufficient imprecision.
> Practical advice much appreciated.
>
> Cheerio, Omar

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index