In: Statistics and Probability
Find, or come up with, a data set to test the equality of means of 3 categories. Provide the sample statistics for each category. Using technology (Ti-84 or Excel) find the critical value, test statistic and p-value of the ANOVA test. Then interpret the results in the context of the problem.
Sol:
let A,B,C represents 3 groups
A | B | C |
20 | 47 | 17 |
23 | 49 | 25 |
25 | 67 | 17 |
27 | 64 | 31 |
27 | 49 | 16 |
21 | 67 | 17 |
26 | 51 | 19 |
23 | 70 | 16 |
21 | 54 | 21 |
26 | 60 | 24 |
31 | 49 | 20 |
Ho;All the three group means are equal
Ha:atleast one of the group means are differnt
alpha=0.05
perfom ANOVA one way in excel
data>data analysis>anova single factor we gt
Output:
Anova: Single Factor | ||||||
SUMMARY | ||||||
Groups | Count | Sum | Average | Variance | ||
A | 11 | 270 | 24.54545 | 10.87273 | ||
B | 11 | 627 | 57 | 76.4 | ||
C | 11 | 223 | 20.27273 | 22.21818 | ||
ANOVA | ||||||
Source of Variation | SS | df | MS | F | P-value | F crit |
Between Groups | 8874.97 | 2 | 4437.485 | 121.585 | 4.08E-15 | 3.31583 |
Within Groups | 1094.909 | 30 | 36.49697 | |||
Total | 9969.879 | 32 |
From Output
Test statistic,F=121.585
p vlaue=4.08E-15=0.0000
F critical=3.31583
F statistic>F critical
Reject Null hypothesis
Accept aletrnative Hypothesis
Conclusion:
There is no sufficient statistical evidence at 5 % level of signifcance to conclude that all the 3 group means are equal.