Statalist


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

Re: st: Stata 11 mi vs SAS procmi


From   ymarchenko@stata.com (Yulia Marchenko, StataCorp LP)
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Stata 11 mi vs SAS procmi
Date   Sun, 09 Aug 2009 16:31:04 -0500

JIBONAYAN RAYCHAUDHURI <jibonayanrc@yahoo.com> asks:

> Does mi in stata 11 use conditional densities to impute variables? If so it
> is as theoretically sound as SAS's proc mi? 

To impute multivariate data, -mi- offers -mi impute monotone- and -mi impute
mvn-.  -mi impute monotone- is similar to the MONOTONE statement in SAS's PROC
MI.  -mi impute mvn- implements the NORM method which is also implemented in
SAS's PROC MI.

> Is mi based on the user written ice ? 
> Also, what is the difference between mi and the user written mim commands.
> Is the Stata version of multiple imputation a packaged compilation of these
> user written commands?

-mi- is not a packaged compilation of the user-written commands -ice- and
-mim-.  See

	http://www.stata.com/statalist/archive/2009-07/msg01107.html
	http://www.stata.com/statalist/archive/2009-08/msg00385.html

for a brief comparison of -mi- and these user-written routines.


--Yulia
ymarchenko@stata.com
*
*   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