In: Statistics and Probability
A | B | C |
13 | 7 | 9 |
29 | 19 | 54 |
25 | 54 | 5 |
17 | 15 | 11 |
21 | 22 | 20 |
a) Construct ANOVA table and test the null hypothesis: μA = μB = μC
b) Assume that you have statistically enough evidence to reject the null hypothesis; suggest an approach to find out whether all three means are different than each other or only one of them is different than others (while the other two means are equal) and if the second is the case which one is different (NO calculation, explain verbally).
b)
If the decision is to reject the null, then at least one of the
means is different. But, ANOVA does not tell us where the
difference lies. For this, we need another test, either the
Scheffe' or Tukey test. Both tests are set up to test if pairs of
means are different. Using p-value, we can infer for which pair of
means is significantly different.