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]
st: MI Number of datasets issue
From
Afshin <[email protected]>
To
<[email protected]>
Subject
st: MI Number of datasets issue
Date
Mon, 29 Apr 2013 12:32:44 +0100
Dear All,
I am using the MI suite to impute individual data across 3 waves of data
collection. My sample size is about 18,000. Ideally I am hoping to
impute 25 datasets, but STATA will produce an error or not reach
concavity somewhere in the 3rd dataset. So I am imputing 2 datasets at a
time. Although, sometimes it will only impute 1 dataset and then produce
an error in the 2nd. I assumed that each imputation is unaffected by the
previous dataset imputed and the subsequent dataset imputed, so I was
going to use 'mi add' to put all the mini datasets together to reach 25.
Is there something horribly wrong with my imputation, or something I'm
missing I should be doing? Any advice would be most helpful!
afshin
--
Afshin Zilanawala, PhD
Research Department of Epidemiology and Public Health
University College London
1-19 Torrington Place, London WC1E 7HB
+44 (0)20 7679 1795
*
* 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/