User Guide

202
Chapter 8
Youwanttodoapaired-samplest test. Your data structure is case groups, but
you don’t have the repeated measures for the paired variables that the procedure
requires. S
elect
Restructure selected cases into variables in the Restructure Data
Wizard, use id to identify the row groups in the current data, and use time to create the
variable group in the new file.
Figure 8-19
New, restructured data for cases to variables
When you ru
n the paired-samples t test, you can now use bef and aft as the variable
pair.
Restruct
ure Data Wizard (Variables to Cases): Number of Va riable Groups
Note:The
wizard presents this step if you choose to restructure variable groups
into rows.
In this step, decide how many variable groups in the current file that you want
to restructure in the new file.
How many v
ariable groups are in the current file?
Think about how many variable
groups exist in the current data. A group of related columns, called a variable group,
records repeated measures of the same variable in separate columns. For example, if
you have
three columns in the current data—w1, w2,andw3—that record width,
you have one variable group. If you have an additional three columns—h1, h2,and
h3—that record height, you have two variable groups.
How man
y variable groups should be in the new file?
Consider how many variable
groups you want to have represented in the new data file. You do not have to
restructure all variable groups into the new file.