Statalist


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

st: Odds ratios with micombine


From   "Duhita Mahatmya" <dmaha@iastate.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Odds ratios with micombine
Date   Wed, 29 Oct 2008 14:59:41 -0500 (CDT)

Hi all,

We are currently having issues with the micombine command. Specifically, we 
have performed ICE on our dataset to impute missing values, and are using 
micombine to obtain parameter estimates. We are running logistic regressions 
and would like to report the odds ratios. The odds ratios are reported when we 
include the [detail] option in micombine, but the final (combined) results 
still only output the unstandardized beta coefficients. Is there a way to 
report the average of the odds ratios? or does Rubin's rules only apply to 
unstandardized betas?

Thanks,
Duhita

-----
Duhita Mahatmya
Research Assistant
Institute for Social and Behavioral Research
Human Development and Family Studies
Iowa State University
dmaha@iastate.edu



*
*   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