'Cases in Use' After Imputation Query

Welcome to the forum for REALCOM users. Feel free to post your question about REALCOM here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Go REALCOM (Developing multilevel models for REAListically COMplex social science data) >> http://www.bristol.ac.uk/cmm/software/realcom/
Post Reply
rjv
Posts: 2
Joined: Mon Jun 27, 2011 2:31 pm

'Cases in Use' After Imputation Query

Post by rjv »

I was wondering if anyone could help to clarify an issue around the number of ‘cases in use’ listed at the bottom of the Equations window after running an analysis using imputed data sets from Realcom.

First, some context. I first ran a growth curve analysis without imputation in MLWIN but listwise deletion led to a large number of missing cases. As a result, using the same model, I then conducted multiple imputation using Realcom (in which all of the variables in my model were used in the imputation). However, after running the analysis with the imputed data sets, at the bottom of the Equations window, it says 6615 of 14340 cases in use. This is a larger number of ‘cases in use’ than I had running the models without imputation but is fewer than I expected (I assumed, perhaps erroneously, that if I imputed in this way that it would say that all 14340 of 14340 cases were in use).

While I followed the instructions from the REALCOM-IMPUTE: multiple imputation using MLwin guide by Harvey Goldstein (August 2010), I am wondering if I have made some error in the imputation or in my analysis because I assumed that it would say that all 14340 of 14340 cases would be in use.

Any comments on whether the incomplete number of 'cases in use' at the bottom of the Equations window is abnormal or not, would be greatly appreciated. If not, any suggestions on how to remedy this would be very helpful.

Many Thanks,

Ryan
Harvey Goldstein
Posts: 49
Joined: Sun Sep 06, 2009 5:30 pm

Re: 'Cases in Use' After Imputation Query

Post by Harvey Goldstein »

Dear Ryan
Seems strange. If you could send the relevant data files (original data records i.e. mlwin worksheet indicating the variables used + some of your imputed datsets we can have a look.
best
Harvey Goldstein (h.goldstein@bristol.ac.uk)
Post Reply