Date: Tue, 19 Jul 2011 15:23:22 -0400
Reply-To: Gene Maguin <emaguin@buffalo.edu>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Gene Maguin <emaguin@buffalo.edu>
Subject: Re: repeated measures anova
In-Reply-To: <1311098806460-4613114.post@n5.nabble.com>
Content-Type: text/plain; charset="us-ascii"
This message was on another listserver and I replied as follows to it.
Peter,
First off, I don't understand what you are trying to do. That said, your
syntax indicates that you have a multivariate repeated measures with two
measures at each of five time points. You have only one factor: time. There
is no interaction.
>>The problem is that I am unable to obtain an F-test for the time variable.
You get something, i'll bet, so what do you get?
>>And I also cannot generate the interaction.
If you want an interaction, you have to set up your data differently. I
think this is the correct setup. There may be some other things you want to
change downstream of the Wsfactor subcommand.
GLM wave1 wave2 wave3 wave4 wave5 W1Char W2Char W3Char W4Char W5Char
/WSFACTOR=char 2 time 5 Polynomial
/METHOD=SSTYPE(3)
/PLOT=PROFILE(time)
/EMMEANS=TABLES(time) COMPARE ADJ(BONFERRONI)
/PRINT=DESCRIPTIVE ETASQ
/CRITERIA=ALPHA(.05)
/WSDESIGN=time.
Peter, since you reposted to this listserv, I'm concluding that my
suggestions were not helpful. What did I not understand?
Gene Maguin
-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
pjiman1
Sent: Tuesday, July 19, 2011 2:07 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: repeated measures anova
I'm trying to conduct a Repeated Measures ANOVA in SPSS. My syntax is pasted
below.
I am trying to obtain results where both time and scale are
repeated/within-subject factors and then test for time, scale, and
time*scale effects---where all scales at all times listed as variables.
My data are in wide form. The wave variables are coded two ways: one set has
variables wave1 to wave 5 each coded as 0,1, indicating which subject has
data for each wave, the other set has variables w1 to W5 coded as 1,2,3,4,5
depending on which subject has data for each wave.
The problem is that I am unable to obtain an F-test for the time variable.
And I also cannot generate the interaction.
GLM wave1 wave2 wave3 wave4 wave5 W1Char W2Char W3Char W4Char W5Char
/WSFACTOR=time 5 Polynomial
/MEASURE=wave char
/METHOD=SSTYPE(3)
/PLOT=PROFILE(time)
/EMMEANS=TABLES(time) COMPARE ADJ(BONFERRONI)
/PRINT=DESCRIPTIVE ETASQ
/CRITERIA=ALPHA(.05)
/WSDESIGN=time.
I suspect that a) I have a fundamental error in my setup, b) I am
overlooking a minor problem with my syntax, or c) I suspect that my wave
variables (i.e. time) are coded incorrectly. Or is there some other problem
with my setup?
I am not interested in recasting the analysis in SAS, HLM, or Structural
Equation Modeling. My boss is looking for a quick and simple solution to
this in SPSS.
Thanks in advance.
--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/repeated-measures-anova-tp4613
114p4613114.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.
=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (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
LISTSERV@LISTSERV.UGA.EDU (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
