Statalist


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

Re: st: table & chi-square from multiply imputed survey data (-ice-, -mim-) [repost]


From   "Michael I. Lichter" <mlichter@buffalo.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: table & chi-square from multiply imputed survey data (-ice-, -mim-) [repost]
Date   Thu, 05 Feb 2009 14:05:37 -0500

Thank you Stas and Maarten for the thoughtful and useful responses. Thanks in particular to Stas for the pointer to his library, and Maarten for the pointer to Rose Medeiros' presentation (though I can't say I know what to do with it). I also appreciate the endorsement of -mlogit- (in some form). (I would try Stas' suggested bootstrap, mlogit, & repeat method if I knew how to implement it.)

I find it interesting that multiple imputation as it exists now does not deal with seemingly-simple problems like producing tables and chi-square statistics, but works well for apparently-complex problems like producing coefficients and standard errors for multivariate models. Perhaps there's something here for an ambitious grad student ... :)

FWIW, when I try mlogit (or svy mlogit) with mim -- e.g., "xi: mim: mlogit B i.A" I get a "conformability error". I assume that the error is coming from mim rather than mlogit because I can run mlogit without mim on the whole dataset and on each replicate individually without problems. This could easily be a result of the particular variables I'm looking at, but it would be nice to know how to avoid "conformability error" in mim.

Thanks again.

Michael
*
*   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   |   What's new   |   Site index