Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: ICE and two conditions
From
Richard Williams <[email protected]>
To
[email protected]
Subject
Re: st: ICE and two conditions
Date
Thu, 01 Dec 2011 10:34:51 -0500
At 09:40 AM 11/29/2011, daniel klein wrote:
Morten,
I do not have access to Stata at the moment, so I cannot replicate
your problem. However, I would like to point out two things.
If you are using Stata 12, there is no need to use -ice- since Stata's
-mi- supports imputationa via chained-equations in the current
version. (It is based on the work of Royston). Further, if you use
Stata's -mi-, you do not need to specify conditions, as Stata will
only impute "hard missings" (i.e. sysmiss). Create soft missing values
(i.e. one of .a, .b, ..., .z) in your original dataset according to
your conditions, as these values will not be imputed.
Do others agree that there is no need to ever use -ice- anymore if
you have Stata 12? I'm quite happy to stick with one program if that
is possible. But are there situations when you would still prefer -ice-?
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/