Information Technology Reference
In-Depth Information
Levene's Test of Equality of Error Variances
a
Dependent Variable: MATH_DV
df1
The equal variances assumption is not
violated, probabilities (Sigs.) are > .05
F
.105
df2
Sig.
33
Tests the null hypothesis that the error variance
of the dependent variable is equal across groups.
a. Design: Intercept+VERB_COV+GROUP
Figure 16.15
2
.901
Levene's test results.
Bonferroni adjusted
t
-test procedure to compare the adjusted group
means. This is why this option is located in the
EstimatedMarginalMeans
area.
In the lower portion of the
Options
dialog window, select
Descrip-
tive statistics
and
Homogeneity tests
as shown in Figure 16.14. Click
Continue
to reach the main dialog window and click
OK
to run the
analysis.
16.9.2 THE OUTPUT OF THE COVARIANCE ANALYSIS
Figure 16.15 shows the results of Levene's test of the equality of error
variances. The outcome is not significant, and so we cannot reject the
hypothesis that the error variances are equal.
Figure 16.16 presents the observed group means and standard devia-
tions. These are the means prior to adjustment and are not the means that
are compared in the ANCOVA. We show them here so that they may be
contrasted with the adjusted means we will show in a moment.
Figure 16.17 contains the summary table for the ANCOVA. Both the
covariate of verbal ability and the effect of the independent variable (train-
ing program) are statistically significant. The full eta squared value for the
effects are computed by dividing the sum of squares for the effect of the
independent variable by the
Corrected Total
sum of squares presented in
the summary table, yielding a value of .735 (as shown in the footnote to
the summary table). SPSS also provides an adjusted
R
squared value to
take into account error variance contributing toward successful prediction
of the values of the dependent variable.
Descriptive Statistics
Dependent Variable: MATH_DV
Std.
Deviation
Figure 16.16
Observed means and stan-
dard deviations for the groups.
GROUP
Mean
N
1
2
3
Total
10.83
10.92
11.33
11.03
2.725
2.234
1.723
2.210
12
12
12
36
