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: Mediation Analysis with "mi svyset" data
From
Lauren Beresford <[email protected]>
To
Statalist <[email protected]>
Subject
st: Mediation Analysis with "mi svyset" data
Date
Wed, 14 Mar 2012 12:30:46 +0000
Hello Statalisters,
I want to do a mediation analysis using data with a complex survey design where I have imputed variables with missing data. I have two dependent variables - one is a count and the other is binary. The independent variable of interest is binary and the mediator variables are continuous. I am wondering if any of the mediation programs in Stata support mi estimation with complex survey designs (i.e. mi estimate:svy:)?
Here are some packages that I have come across, but it is unclear to me if I can use mi estimate:svy with these commands:
sgmediation - for continuous variables but has an option for prefix where you can include "mi estimate:svy:"
medeff - supports logit models and pweightshttp://scholar.harvard.edu/dtingley/files/mediationstata_1.pdf
binary_mediation - binary mediation analysishttp://www.ats.ucla.edu/stat/stata/faq/binary_mediation.htm
Any help is much appreciated.
Kind regards,Lauren Beresford
Doctoral CandidateUC Berkeley, Sociology
*
* 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/