Pooled Results after ANOVA

[Rita_Lev]

Hi all,

I am trying to conduct a one-way ANOVA as a means of characterizing group
differences before treatment. I had some missing data and used the multiple
imputation technique to fill in the gaps. I am able to see the swirl symbol
next to the analyses, indicating the MI was successful and I split the file
by the imputation variable as other forums indicated. However, when I run
the ANOVA, my output shows the 5 iterations separately, but not the pooled
result.

Can anyone help me figure out what may be the issue?

Thank you!!



--
Sent from: http://spssx-discussion.1045642.n5.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

[Zdaniuk, Bozena-3]

hi Rita, to my knowledge, SPSS still does not provide pooled results for ANOVA. You can try to run your analysis in MIXED as that analysis does provide the pooled results in SPSS.
cheers,
bozena
________________________________________
From: SPSSX(r) Discussion [[hidden email]] on behalf of Rita_Lev [[hidden email]]
Sent: Wednesday, September 05, 2018 6:53 AM
To: [hidden email]
Subject: Pooled Results after ANOVA

Hi all,

I am trying to conduct a one-way ANOVA as a means of characterizing group
differences before treatment. I had some missing data and used the multiple
imputation technique to fill in the gaps. I am able to see the swirl symbol
next to the analyses, indicating the MI was successful and I split the file
by the imputation variable as other forums indicated. However, when I run
the ANOVA, my output shows the 5 iterations separately, but not the pooled
result.

Can anyone help me figure out what may be the issue?

Thank you!!



--
Sent from: http://spssx-discussion.1045642.n5.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

[Joost van Ginkel]

You can pool the results using an SPSS macro available from my personal page:

https://www.universiteitleiden.nl/en/staffmembers/joost-van-ginkel#tab-1

It is included in a zip file called MI-MUL2.zip, and it comes with a manual with data examples. Also, see my 2014 paper that discusses the combination rules for ANOVA that are carried out by this macro:

Van Ginkel, J.R. & Kroonenberg, P.M. (2014). Analysis of variance of multiply imputed data.  Multivariate Behavioral Research, 49, 78-91.

By the way, Mixed Models does pool the results for separate regression coefficients in your ANOVA model, but not the F-tests. My macro however, does. If you have any questions regarding the macro or if you need some help, please feel free to contact me.

Best regards,

Joost van Ginkel
________________________________________
From: SPSSX(r) Discussion [[hidden email]] on behalf of Rita_Lev [[hidden email]]
Sent: Wednesday, September 05, 2018 3:53 PM
To: [hidden email]
Subject: Pooled Results after ANOVA

Hi all,

I am trying to conduct a one-way ANOVA as a means of characterizing group
differences before treatment. I had some missing data and used the multiple
imputation technique to fill in the gaps. I am able to see the swirl symbol
next to the analyses, indicating the MI was successful and I split the file
by the imputation variable as other forums indicated. However, when I run
the ANOVA, my output shows the 5 iterations separately, but not the pooled
result.

Can anyone help me figure out what may be the issue?

Thank you!!



--
Sent from: http://spssx-discussion.1045642.n5.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