One difference between data files for mixed models and others is that we use what is often
called a “long form.” Instead of putting each subject’s data on one line, we have a separate
line for every value of the dependent variance. Thus our data file will be structured like the
one in Table 14.16
Instead of showing you how to use the graphical interface in SPSS, which would take
quite a bit of space, I am simply giving you the syntax for the commands.^8 After you have
entered your data, open a new Syntax window, paste in the following commands, and
select Run from the toolbar. I have left out a number of commands that do fine tuning, but
what I have will run your analysis nicely.
MIXED
dv BY Group Time
/FIXED 5 Group Time Group * Time | SSTYPE(3)
/METHOD 5 REML
/PRINT 5 DESCRIPTIVES SOLUTION
/REPEATED 5 Time | SUBJECT(Subj) COVTYPE(CS)
/EMMEANS 5 TABLES(Group)
/EMMEANS 5 TABLES(Time)
/EMMEANS 5 TABLES(Group * Time).Section 14.12 Mixed Models for Repeated-Measures Designs 501Table 14.15 (continued)
Group Subj Time0 Time1 Time3 Time6
2 13 282 186 225 134
2 14 317 31 85 120
2 15 362 104..
2 16 338 132 91 77
2 17 263 94 141 142
2 18 138 38 16 95
2 19 329.. 6
2 20 292 139 104.
2 21 275 94 135 137
2 22 150 48 20 85
2 23 319 68 67.
2 24 300 138 114 174
Table 14.16 Data restructured into a long form
Subj Time Group dv
1 0 1 296
1 1 1 175
1 3 1 187
1 6 1 242............
24 3 2 114
24 6 2 174
(^8) The following is quick description of using the menu selections. Select analysis/mixed/linear,specify Subj for
the Subjects box and Time for the Repeated box. Click continueand move to the next screen. Specify the
dependent variable (dv) and the factors (Group and Time). Select fixed from the bottom of the box, highlight both
Group and Time and click the addbutton, click continue.Now click on the randombutton and add Subj to the
bottom box. Then click pasteto make sure that you have syntax similar to what I gave above.