In: Statistics and Probability
Listed below are times(in minutes and seconds) while an athlete rode his bicycle through each mile of a 3 mile loop. Use a 0.05 significance level to test the claim that it takes the same time to ride each of the miles.
Mile 1 | 3:14 | 3:24 | 3:23 | 3:22 | 3:21 |
Mile 2 | 3:19 | 3:22 | 3:21 | 3:17 | 3:19 |
Mile 3 | 3:34 | 3:31 | 3:29 | 3:31 | 3:29 |
The data converted into decimals is as below
Mile 1 | Mile 2 | Mile 3 |
3.23 | 3.32 | 3.57 |
3.4 | 3.37 | 3.52 |
3.38 | 3.35 | 3.48 |
3.37 | 3.28 | 3.52 |
3.35 | 3.32 | 3.48 |
The summary statistics is as below
Mile 1 | Mile 2 | Mile 3 | |
Total | 16.73 | 16.64 | 17.57 |
n | 5 | 5 | 5 |
Mean | 3.35 | 3.33 | 3.51 |
Sum Of Squares | 0.02 | 0.00 | 0.01 |
Variance | 0.0046 | 0.0012 | 0.0014 |
_______________________________________
The Hypothesis:
H0: There is no difference between the mean time taken for the three miles.
Ha: The mean time of at least one mile is different from the others.
________________________________________________
The ANOVA table is as below.
Source | SS | DF | Mean Square | F | Fcv | p |
Between | 0.105 | 2 | 0.053 | 21.98 | 3.89 | 0.0001 |
Within/Error | 0.03 | 12 | 0.002 | |||
Total | 0.13 | 14 |
The p value is calculated for F = 21.98 for df1 = 2 and df2 = 12
The F critical is calculated at = 0.05 for df1 = 2 and df2 = 12
The Decision Rule:
If F test is > F critical, Then Reject H0.
Also if p-value is < , Then reject H0.
The Decision:
Since F test (21.98) is > F critical (3.89), We Reject H0.
Also since p-value (0.0001) is < (0.05), We Reject H0.
The Conclusion: There is sufficient evidence at the 95% level of significance to conclude that the mean time of at least one mile is different from the others.
__________________________________________________________
Calculations For the ANOVA Table:
Overall Mean = [3.35 +3.33 +3.51) / 3 = 3.40
SS treatment = SUM [n* ( Individual Mean - overall mean)2] = 5 * (3.35 - 3.4)2 + 5 * (3.33 - 3.4)2 + 5 * (3.51 - 3.4)2 = 0.105
df1 = k - 1 = 3 - 1 = 2
MSTR = SS treatment/df1 = 0.105 / 2 = 0.053
SS error = SUM (Sum of Squares) = 0.02 + 0.0 + 0.01 = 0.03
df2 = N - k = 15 - 3 = 12
Therefore MS error = SS error/df2 = 0.03 / 12 = 0.002
F = MSTR / MSE = 0.053 / 0.002 = 21.98
______________________________________________