multiple imputation in GLM Multivariate

[Sam Batchelor]

Hi,  I'm running GLM Multvaraite analysis in SPSS 17.0 with multiple
imputation.  The results appear for each separate imputation but SPSS
doesn't provide any pooled results.  Can the multivariate test results
(e.g. Wilks lambda) be pooled? If so, how?  What about the univariate
(between subjects) results?  Thanks in advance to anyone who responds to
this (and please phrase your response as if talking to a 3 yr old as
statistics are really not my thing!)

=====================
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

[Joost van Ginkel]

Dear Sam,

The reason why SPSS doesn't provide pooled estimates of the multivariate
tests is that no combination rules for MANOVA are available. The
univariate F-tests, however, can be combined (Schafer, 1997, pp.
112-116), only this is not implemented in SPSS (yet). However, you can
use an SPSS macro available from my personal page
http://www.socialsciences.leiden.edu/educationandchildstudies/childandfa
milystudies/organisation/staffcfs/van-ginkel.html which allows you to
combine the results of univariate F-tests. The file is called
MI-mul.sps. I recently finished an improved version of this macro
(MI-mul2.sps) but this version won't be online until next week. I may be
worthwile waiting for this macro because it is much more user friendly.
Good luck!

Best regards,

Joost van Ginkel


Joost R. Van Ginkel, PhD
Leiden University
Faculty of Social and Behavioural Sciences
Data Theory Group
PO Box 9555
2300 RB Leiden
The Netherlands
Tel: [phone]
Fax: [phone]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Sam Batchelor
Sent: 09 April 2010 04:11
To: [hidden email]
Subject: multiple imputation in GLM Multivariate

Hi,  I'm running GLM Multvaraite analysis in SPSS 17.0 with multiple
imputation.  The results appear for each separate imputation but SPSS
doesn't provide any pooled results.  Can the multivariate test results
(e.g. Wilks lambda) be pooled? If so, how?  What about the univariate
(between subjects) results?  Thanks in advance to anyone who responds to
this (and please phrase your response as if talking to a 3 yr old as
statistics are really not my thing!)

=====================
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

**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************

=====================
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