Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: svyset: weight and missing


From   Mohamad Mahmoud <[email protected]>
To   statalist <[email protected]>
Subject   st: svyset: weight and missing
Date   Fri, 28 Feb 2014 15:16:17 -0500

Dear Statalist,
I am very familiar with Stata but new to survey analysis. I am
analyzing a cross country cross time survey and have the following two
questions on setting up using -svyset-:

1) Weights: Which weighting variable should I use: the weight of each
respondent within sample r the weight within country/year. The survey
contains two weight variables
-wt_sample: equals the sampling weight within each survey for each
country/yr. It has a mean of 1 and its total equals to the sample size
for that country/year.
-wt_proj: The projection weight is the weight of each respondent
within the country. Its total equals the population of the country.

2) Some country/year combinations are missing PSU, strata, and
weights. What effect does missing each of psu/strata/weight have on
the analysis? That is, will they be excluded from the calculation of
the coefficients and standard errors. In this case, what is the best
action, leave it as is or assign them equal weights?

Thanks!
Mohamad Mahmoud
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index