Hey Jon,
I believe I know what he wants, but have intentionally avoided using the words to describe what he wants in that way, as I don’t want to give
people the tools to do this, and allow such a bad practice to happen. I guess it’s their work, and up to them if they want to follow such a bad practice.
As Jon is eluding to here, the actual data set created is not really 5 separate files, but rather, one stacked file with each of the 5 “data
sets” numbered sequentially 1-5. In the analysis, you tell the program to analyze it as a split file across that variable, and then pool the estimates from each of the outputs (which as Jon has noted, can be output separately as well). While many programs
now allow you to incorporate all these steps into a simple set of sequential analysis steps, technically there is no reason why you can’t first run the MLM on each of the 5 data sets (for instance, if R has no ability to split a file on the analysis, just
select cases within each of the 5 sets sequentially and run the analysis, outputting the estimates into their own 5 data sets. You can then remerge the files together, and run a program to pool the estimates across all 5. This is just much more cumbersome
than the available tools in programs like SPSS, SAS, or HLM.
Matthew J Poes
Research Data Specialist
Center for Prevention Research and Development
University of Illinois
510 Devonshire Dr.
Champaign, IL 61820
Phone: 217-265-4576
email:
[hidden email]
From: SPSSX(r) Discussion [mailto:[hidden email]]
On Behalf Of Jon K Peck
Sent: Friday, April 27, 2012 10:42 AM
To: [hidden email]
Subject: Re: Export pooled Multiple Imputation data
The multiply imputed dataset is just a dataset. You can import it - all the sets - like any other dataset.
If you mean the results, OMS or OUTPUT EXPORT can export any or all tables in various formats.
Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621
From: torvon <[hidden email]>
To: [hidden email]
Date: 04/27/2012 09:04 AM
Subject: [SPSSX-L] Export pooled Multiple Imputation data
Sent by: "SPSSX(r) Discussion" <[hidden email]>
I am using Multiple Imputation in SPSS 20 to impute missing values. However,
since I am running multivariate multilevel analysis with the MCMCglmm
package in R, I need to export the data.
I have found no option to export the pooled imputed values. What would you
recommend?
Thank you
T
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Export-pooled-Multiple-Imputation-data-tp5669830p5669830.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
| Free forum by Nabble | Edit this page |