You are on page 1of 2

DATA DRUGS;

INPUT DRUG AGE NDRUG LOAD @@;


CARDS;
1 1 1 30 1 1 1 32 1 1 2 39 1 1 2 36 1 2 1 37 1 2 1 39 1 2 2 35 1 2 2 37 1 3 1 31 1 3 1 33 1 3 2 36 1
3 2 34
2 1 1 43 2 1 1 42 2 1 2 40 2 1 2 41 2 2 1 44 2 2 1 43 2 2 2 48 2 2 2 46 2 3 1 43 2 3 1 42 2 3 2 42 2
3 2 41
3 1 1 37 3 1 1 39 3 1 2 43 3 1 2 41 3 2 1 38 3 2 1 39 3 2 2 42 3 2 2 44 3 3 1 41 3 3 1 39 3 3 2 39 3
3 2 37
4 1 1 29 4 1 1 27 4 1 2 28 4 1 2 29 4 2 1 33 4 2 1 37 4 2 2 35 4 2 2 33 4 3 1 31 4 3 1 29 4 3 2 30 4
3 2 32
;
PROC GLM;
CLASS DRUG AGE NDRUG;
MODEL LOAD=DRUG|AGE|NDRUG(AGE);
TEST H=DRUG DRUG*AGE E=DRUG*NDRUG(AGE);
TEST H=AGE E=NDRUG(AGE);
MEAN DRUG/TUKEY;
RUN;
General Linear Models Procedure
Class Level Information

Class Levels Values

DRUG 4 1234

AGE 3 123

NDRUG 2 12

Number of observations in data set = 48

General Linear Models Procedure

Dependent Variable: LOAD

Source DF Sum of Squares Mean Square F Value Pr > F

Model 23 1253.91666667 54.51811594 28.44 0.0001

Error 24 46.00000000 1.91666667

Corrected Total 47 1299.91666667

R-Square C.V. Root MSE LOAD Mean

0.964613 3.720772 1.38443731 37.20833333

Source DF Type I SS Mean Square F Value Pr > F

DRUG 3 992.25000000 330.75000000 172.57 0.0001


AGE 2 113.16666667 56.58333333 29.52 0.0001
DRUG*AGE 6 33.50000000 5.58333333 2.91 0.0280
NDRUG(AGE) 3 26.75000000 8.91666667 4.65 0.0106
DRUG*NDRUG(AGE) 9 88.25000000 9.80555556 5.12 0.0006
Source DF Type III SS Mean Square F Value Pr > F

DRUG 3 992.25000000 330.75000000 172.57 0.0001


AGE 2 113.16666667 56.58333333 29.52 0.0001
DRUG*AGE 6 33.50000000 5.58333333 2.91 0.0280
NDRUG(AGE) 3 26.75000000 8.91666667 4.65 0.0106
DRUG*NDRUG(AGE) 9 88.25000000 9.80555556 5.12 0.0006

Tests of Hypotheses using the Type III MS for DRUG*NDRUG(AGE) as an error term

Source DF Type III SS Mean Square F Value Pr > F

DRUG 3 992.25000000 330.75000000 33.73 0.0001


DRUG*AGE 6 33.50000000 5.58333333 0.57 0.7462

Tests of Hypotheses using the Type III MS for NDRUG(AGE) as an error term

Source DF Type III SS Mean Square F Value Pr > F

AGE 2 113.16666667 56.58333333 6.35 0.0836

General Linear Models Procedure

Tukey's Studentized Range (HSD) Test for variable: LOAD

NOTE: This test controls the type I experimentwise error rate, but generally
has a higher type II error rate than REGWQ.

Alpha= 0.05 df= 24 MSE= 1.916667


Critical Value of Studentized Range= 3.901
Minimum Significant Difference= 1.5592

Means with the same letter are not significantly different.

Tukey Grouping Mean N DRUG

A 42.9167 12 2

B 39.9167 12 3

C 34.9167 12 1

D 31.0833 12 4

You might also like