Information Technology Reference
In-Depth Information
Estimates
Measure: MEASURE_1
95% Confidence Interval
age group
teen
gender
female
attract
1
2
1
2
1
2
1
2
Mean
Std. Error
Lower Bound
Upper Bound
2.800
.346
2.066
3.534
4.200
.387
3.379
5.021
male
.600
.346
-.134
1.334
1.600
.387
.779
2.421
mid 20s
female
5.800
.346
5.066
6.534
5.600
.387
4.779
6.421
male
1.800
.346
1.066
2.534
4.800
.387
3.979
5.621
These are the
probabilities of the
differences occurring
by chance alone for the
pairwise comparisons
with age asfirst order.
Pairwise Comparisons
Measure: MEASURE_1
95% Confidence Interval for
Difference
a
Mean
Difference
(I-J)
Sig.
a
age group
teen
attract
1
(I)gender
female
male
female
male
female
male
female
male
(J)gender
male
female
male
female
male
female
male
female
Std. Error
Lower Bound
Upper Bound
2.200*
.490
.000
1.161
3.239
-2.200*
.490
.000
-3.239
-1.161
2
2.600*
.548
.000
1.439
3.761
-2.600*
.548
.000
-3.761
-1.439
mid 20s
1
4.000*
.490
.000
2.961
5.039
-4.000*
.490
.000
-5.039
-2.961
2
.800
.548
.163
-.361
1.961
-.800
.548
.163
-1.961
.361
Based on estimated marginal means
*.
The mean difference is significant at the .05 level.
a. Adjustment for multiple comparisons: Bonferroni.
Figure 14.20
Comparing the two levels of
gender.
or stacked mode as explained in Section 10.15.2, and is similar to those
we have seen for the examples in Chapters 10-13. The
age, gender
,and
attract
independent variables show the codes for the levels corresponding
to the
jealousy
dependent variable for each case. Note that by examining
the data file we can determine that
age
and
gender
are between-subjects
variables because each subject is associated with only one level of each of
those variables. By the same reasoning, we can determine that
attract
is a
within-subjects variable because each subject has values on the dependent
variable for both levels of
attract
. To illustrate how to read the data file, the
individual identified as
subid 1
whose record is shown in Row 2 (the first
row of data) is coded as
age 1
(teen) and
gender 1
(female). That person
provided a jealousy rating of 3 for
attract 1
(emotional) and a jealousy
rating of 5 for
attract 2
(physical).
14.9.2 STRUCTURING THE DATA ANALYSIS
Import the data file from Excel into a new SAS project. Then from the
main menu select
Analyze
➜
ANOVA
➜
Mixed Models
.Thewindow