Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "JVerkuilen (Gmail)" <jvverkuilen@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: mi impute chained |
| Date | Wed, 31 Oct 2012 08:56:01 -0400 |
A larger point: I've found a good deal of the MI literature to be misleading about just how difficult MI is in practice. Just to name two points: Loading up the imputation model is all well and good but it's so collinear that it can't run, you're out of luck. Also the impact of outliers gets spread around the entire dataset if you leave them in, just as in any other full information method. * * 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/