Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | roland andersson <rolandersson@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Multiple imputation of repeated examinations data |
Date | Thu, 25 Apr 2013 20:21:33 +0200 |
I have clinical data of patients examined one to three times with some hours interval. The data looks like this in the wide format age, sex, diagnosis, time1, var1_1, var2_1, var3_1, time2, var1_2, var2_2, var3_2, time3, var1_3, var2_3 etc Some patients have only one examination, others up to three. I have previously identified and used the latest examination and imputed missing values for only that examination, but would like to take advantage of all the data from all examinations and especially the dynamic effect of the time. The problem is how MI or ICE can recognise and associate the time of the examination with the results of the examinations at that time and see the dynamic change? I have seen this thread which is a bit similar but did not answer my question as they dd not use the dynamic change between the observations http://www.stata.com/statalist/archive/2013-03/msg00217.html Regards Roland E Andersson * * 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/