In: Economics
Supplier A |
Supplier B |
Supplier C |
28 37 34 29 31 33 |
22 27 29 20 18 30 |
33 29 39 33 37 38 |
i. The degree of freedom for the groups would be m-1 or 2, for m is number of groups. The degree of freedom for the error would be n-m or 15, for n is the total number of observations.
The sum of square total would be or or . The sum of square of error would be or or or . The sum of square between would be or or .
The anova table would be as below.
DF | SS | MS | F | P-val | |
Group | 2 | 354.1111 | 354.1111/2=177.0556 | 0.0014 | |
Error | 15 | 254.1667 | 254.1667/15=16.9445 | ||
Total | 17 | 608.2778 |
ii. The null hypothesis is that the mean of the groups is the same for all, while the alternate would be that the mean of the groups is not same for all.
The F-statistic obtained is . The critical F would be , and since , we may reject the null that the mean is the same for all. This means that the variation between groups is quite high. This can also be confirmed by the p-value, which is less than 0.05 alpha level.