Information Technology Reference
In-Depth Information
ANOVA
SS
A
satscore
Sum of
Squares
df
Mean Square
F
Sig.
Between Groups
Within Groups
Total
4
57624.286
43.467
.000
230497.1
39771.429
270268.6
30
1325.714
34
SS
S/A
Figure 6.7
The ANOVA results from
One-Way ANOVA
.
appears that the assumption of homogeneity of variance has not been
violated.
6.7.3 SUMMARY TABLE
The summary table for the omnibus analysis is presented in Figure 6.7
and is identical to what we showed earlier. The
One-Way ANOVA
proce-
dure does not generate a value for eta square (
2
), but it is easy enough
to do on a hand calculator. All we need to do is divide the
between-
groups sum of squares
by the
total sum of squares;
this gives us a value of
.853 (230497
η
.
143
÷
270268
.
571
=
.
853).
6.8 PERFORMING THE OMNIBUS ONE-WAY BETWEEN-
SUBJECTS ANOVA IN SAS
6.8.1 THE DATA FILE
The data file that we are using for the SAS analysis has the same structure
as the file we used in the previous SPSS analysis. Figure 6.8 displays the
Excel spreadsheet containing our data. In the first column we find
subid
representing the identification code for the participants in the study. In
the following columns, we see the group variable with value labels of 0,
2, 4, 6, and 8 representing our
groups
(the codes inform us directly of
the number of months of study the students put in), and the dependent
variable
satscore
.
6.8.2 IMPORTING THE DATA FILE
To perform the data analysis, you must launch
SAS Enterprise Guide
and import the data file from Excel. Thus, from the main menu select
File
➜
Import Data
and follow the directions provided in Appendix B.
Oncethedatahavebeenimportedintothecurrentproject,thesteps
taken will be displayed in icons on the project grid background as shown
in Figure 6.9.
6.8.3 PERFORMING THE OMNIBUS ANALYSIS
As was true for SPSS, there are several procedures in
SAS Enterprise Guide
through which we can perform various kinds of ANOVAs. Our choice for
a one-way between-subjects design is the
Linear Models
because it is the
