Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Catharine Morgan <Catharine.Morgan@manchester.ac.uk> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | st: Descriptives of imputed data |
| Date | Tue, 9 Aug 2011 09:31:24 +0000 |
Dear Statalist, I am ultimately wanting to create tables of descriptive data showing complete case data and then the imputed data using the usual proportions and means/medians and testing between two groups of individuals. I use both STATA 10 and STATA 11 and I have the data in the format to use both -mi- and -mim-. For the imputed data I know how to report combined estimates using Rubin's rules for means and proportions (using mim:mean X1 and mim: proportion X2) but is there a way to achieve the median and the test between these two medians (Mann-Whitney) and also the test between two means (ttest)? Is there a way to achieve the equivalent chi^2 for proportions in imputed data? Many thanks, Cathy * * 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/