Graphing an Interaction in SPSS version 15: BAR GRAPH
There is a good chance that sometime during your career you will be asked to graph an interaction.
Briefly defined, an interaction is when the effect of one independent variable on the dependent variable
depends on the different levels of one or more other independent variables. We will practice graphing an
interaction from a 2 x 2 between-subjects factorial design.
Step 1. Click on
Graphs
, then
Legacy Dialogs
and select
Bar
.
Step 2. In the
Bar Charts
menu, click on
Clustered
and then make sure
Summaries for groups of
cases
is selected (this is the default option). Then click “
Define
.”
Step 3. In the
Define Cluster Bar
menu, first select
Other statistic (e.g., mean)
that enables you to
plot the means of your groups, and then select your dependent variable measure (e.g., “guilty”)
and move it into the
Variable
field. The default will be to compute the mean for that variable.
Step 4. Now move the one of the independent variables (e.g., "
sex
") into the
Category Axis
field. Then,
move the other independent variable (e.g., “
cond
”) into the
Define Clusters by
field. The
category axis variable will be the variable that appears along the horizontal axis. The define
clusters by variable will represent the other IV that has a legend.
Note:
This figure is constructed as a bar graph because the variable in the categorical axis
is a discrete variable; this is how I was trained. If that variable was continuous, then
creating a line graph would be more appropriate. Others may feel that a line graph
is always more desirable, while others have no preference, so check with your
professor or colleagues.

This
** preview**
has intentionally

**sections.**

*blurred***to view the full version.**

*Sign up*