Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: impute or not


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: impute or not
Date   Sun, 22 Aug 2010 08:36:27 +0000 (GMT)

--- On Sat, 21/8/10, Steve Pitts wrote:
> I'm a timorous non-statistician using the public files from
> a national multistage survey of emergency department visits.
> Length of stay (LOS) is missing in about 8% of 254,000
> observations (lots more in some subgroups).

Given that sample size and proportions of missing values, I 
would start with no imputation at all. The idea behind multiple
imputation is simple, but getting a good imputation model is in
practice very hard and diagnosing it even harder, so if 
imputation leads to different results it is hard to determine 
whether that is due to you correcting the bias from missing data 
or because you made an error in the imputation model... So I 
would only do imputation when I think it is so important that I 
want and can spent a lot of time getting the imputation model 
right (think weeks or months full time).

Hope this helps,
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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index