Multiple Imputation problem(Which data that need to be use)

[sabrik2]

Hi guys,im new here.I just finished doing multiple imputation to my data(500++).I run 5 imputation and the result show 5 different output in every imputation.The question is,which of the imputation is the final and the correct imputed data..is it the 5th imputation(the last data imputation)?

[Joost van Ginkel]

The results that say "Pooled" below the results of the 5 imputed data sets are the results you should interpret. However, these pooled results are not displayed every analysis. For example, for PCA and ANOVA no pooled results are displayed. For ANOVA there are solutions but they are currently not implemented in SPSS.

Best regards,

Joost van Ginkel

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of sabrik2
Sent: vrijdag 18 april 2014 22:58
To: [hidden email]
Subject: Multiple Imputation problem(Which data that need to be use)

Hi guys,im new here.I just finished doing multiple imputation to my data(500++).I run 5 imputation and the result show 5 different output in every imputation.The question is,which of the imputation is the final and the correct imputed data..is it the 5 imputation(the last data imputation)?



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Multiple-Imputation-problem-Which-data-that-need-to-be-use-tp5725542.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[haliltokay]

Hi,

Is there any way you can export the pooled variables to another file so that you are only operating with the pooled variables?

I might have misunderstood the whole concept of multiple imputation, but I would like to have one data set with only the pooled variables - if possible?