Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: question about survey commands


From   DEEPANKAR BASU <basu.15@osu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: question about survey commands
Date   Wed, 21 Nov 2007 21:34:11 -0500

Hi All,

I am working with Stata version 8.2 in Windows Vista. I am working with a survey dataset (the Demographic and Health Surveys for India). 

After generating some variables, I do a t-test to test for the equality of means (of the relevant variables) and store some results of the test as follows:

ttest nsibg==nsibb, unpaired unequal
local nsibeff = r(mu_1) - r(mu_2)
local g3 = r(t)

ttest nwfsb==nwfsg, unpaired unequal
local nboeff = r(mu_1) - r(mu_2)
local g4 = r(t)

(later I use these local variables).

Since the data does not come from a simple random sample, the standard errors and test statistics are not correct. How do I go about doing the above computations taking account of the fact that I am working with a complex survey dataset?

I can use the *svyset* command to tell Stata the details of the survey design (pweights, psu and strata). But I do not know how proceed after that. Any help will be greatly appreciated.

Deepankar

*
*   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