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: Missing data question. |
Date | Sat, 9 Feb 2013 09:09:09 -0500 |
On Sat, Feb 9, 2013 at 8:12 AM, Benjamin Hong <benjamin1459@gmail.com> wrote: > I heard that there are some techinic called "imputation". > Could you let me know how to employ this function in STATA? You can consider the multiple imputation suite but I'll just throw out the disclosure that learning MI is not a simple undertaking. I've done probably a half dozen substantial missing data analyses and none of them have ever gone smoothly. You need to know quite a bit of theory and still make many judgment calls. I would start by looking at the MI manual, which has some nice discussion, and working the examples. Also download the -midiagplots- diagnostic suite. There are some other "how to do" MI papers around, too. Jay * * 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/