Bookmark and Share

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: Re: st: remaining missings after multiple imputation


From   "Ploutz-Snyder, Robert (JSC-SK)[USRA]" <[email protected]>
To   "[email protected]" <[email protected]>
Subject   RE: Re: st: remaining missings after multiple imputation
Date   Tue, 20 Apr 2010 08:41:33 -0500

Anne,
I'm getting similar results with some imputations that I'm working on, but I'm using ice instead of mi.  Strictly speaking, I'm working with uvis prior to ice to fine-tune my modeling of the missing values, and  I get missing imputations sometimes that I cannot explain.  

So while I cannot help you with your situation, I provide this to the list in the hopes that it helps others more experienced with mi?

Rob 

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Anne Jurczok
Sent: Tuesday, April 20, 2010 8:14 AM
To: [email protected]
Subject: AW: Re: st: remaining missings after multiple imputation

Hello,
  First of all thank you for the advice with the if function in ice. I  
will certainly try it as well.

Do these observations contain only missing values on
the variables you use for the imputation?...

...I looked at my variables which have missings despite the imputation  
and found no coherent pattern. Do you have any idea?
Best, Anne

--- On Mon, 19/4/10, Anne Jurczok wrote:
I decided against using ice, since I have different types
of missings in my dataset (hard and soft missings) and I
couldn't find any literature about different types of
missings handled by ice.
It is implicit in the sense that -ice- allows you to specify
an -if- statement. So, you could type something like:

gen byte soft = lnvermgen < .a
ice <varlist> if soft, <other options>
Not all cases of my dataset are considered for the
imputation.
Do these observations contain only missing values on
the variables you use for the imputation?


-- Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------




*
*   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/




*
*   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/

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index