Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Lucy Bilaver" <lbilaver@niu.edu> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: mi estimate & svy --esampvaryok option |
Date | Wed, 10 Jul 2013 14:15:37 -0500 |
I would like to specify a multiply imputed variable in a subpop statement with svy. My estimation sample does vary across imputations. The esampvaryok option allows the procedure to run, but I am concerned that I don't know what statistical issue this is overcoming or the consequence. Could anyone point me to references that would explain the issue or validate that it is okay to fit a regression with multiply imputed complex survey data where the subpop varies across imputations? I am using the Taylor linearization method to get standard errors. Thanks. -Lucy Bilaver * * 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/