Design and Analysis, Fourth Edition, by Keppel and WickensChapter 3: Variance Estimates and the F-Ratio | SAS Textbook Examples

Data from Chapter 2 from Table 2.2, page 22

data table2_2;
input a score;
datalines;
1 16 
1 18
1 10 
1 12
1 19
2 4
2 7
2 8
2 10
2 1
3 2
3 10
3 9
3 13 
3 11
;
run;

Table 3.2, page 37. One way Analysis of Variance
For the between subject design, SAS’s syntax for proc glm and proc mixed are essentially the same. The inclusion of a within-subject factor the differences in procedures become more pronounced, and until then, we are going to stay exclusively with proc glm.

proc glm data = table2_2;
class a;
model score = a/ ss3; 
run; quit;

The GLM Procedure

   Class Level Information
Class         Levels    Values
a                  3    1 2 3

Number of observations    15

Dependent Variable: score
                                        Sum of
Source                      DF         Squares     Mean Square    F Value    Pr > F
Model                        2     210.0000000     105.0000000       7.00    0.0097
Error                       12     180.0000000      15.0000000
Corrected Total             14     390.0000000

R-Square     Coeff Var      Root MSE    score Mean
0.538462      38.72983      3.872983      10.00000

Source                      DF     Type III SS     Mean Square    F Value    Pr > F
a                            2     210.0000000     105.0000000       7.00    0.0097

Data from Table 3.5, page 51

data table3_5;
input a errors;
datalines;
1 37
1 22
1 22
1 25
2 36
2 45
2 47
2 23
3 43
3 75
3 66
3 46
4 76
4 66
4 43
4 62
;
run;

Table 3.6, page 53. One-way Analysis of Variance

proc glm data = table3_5;
class a;
model errors = a/ ss3;
run; quit;

The GLM Procedure

    Class Level Information
Class         Levels    Values
a                  4    1 2 3 4

Number of observations    16

Dependent Variable: errors
                                        Sum of
Source                      DF         Squares     Mean Square    F Value    Pr > F
Model                        3     3314.250000     1104.750000       7.34    0.0047
Error                       12     1805.500000      150.458333
Corrected Total             15     5119.750000

R-Square     Coeff Var      Root MSE    errors Mean
0.647346      26.73819      12.26615       45.87500

Source                      DF     Type III SS     Mean Square    F Value    Pr > F
a                            3     3314.250000     1104.750000       7.34    0.0047

Data from Table 3.6, page 57

data table3_6;
input a score;
datalines;
1 5
1 9
1 7
2 12
2 10
2 10
2 8
2 11
2 9
3 3
3 6
3 5
3 6
;
run;

Table 3.7, page 57. One-way Analysis of Variance with unequal sample size

proc glm data = table3_6;
class a;
model score = a/ ss3;
run; quit;

The GLM Procedure

   Class Level Information
Class         Levels    Values
a                  3    1 2 3

Number of observations    13

Dependent Variable: score
                                        Sum of
Source                      DF         Squares     Mean Square    F Value    Pr > F
Model                        2     62.30769231     31.15384615      12.98    0.0017
Error                       10     24.00000000      2.40000000
Corrected Total             12     86.30769231

R-Square     Coeff Var      Root MSE    score Mean
0.721925      19.94011      1.549193      7.769231

Source                      DF     Type III SS     Mean Square    F Value    Pr > F
a                            2     62.30769231     31.15384615      12.98    0.0017