In: Math
The computer operations department had a business objective of reducing the amount of time to fully update each subscriber's set of messages in a special secured email system. An experiment was conducted in which 23 subscribers were selected and three different messaging systems were used. Eight subscribers were assigned to each system, and the update times were measured as follows:
System A | System B | System C |
38.8 | 41.8 | 36.9 |
42.1 | 36.4 | 36.1 |
45.2 | 39.1 | 39.2 |
34.8 | 28.7 | 35.6 |
48.3 | 36.4 | 41.9 |
37.8 | 36.1 | 31.7 |
41.1 | 35.8 | 35.2 |
43.6 | - | 38.1 |
Given Sample Means: x̅a = 41.46, x̅b = 36.33, x̅c = 35.84, Grand Mean = 38.29
Given Sample Standard Deviations: sa = 4.32, sb = 4.00, sc = 3.02, S = 4.34
A) At the 0.05 level of significance, is there evidence of a difference in the variance of the update times between Systems B and C? (Show your work: hypotheses, test statistic, critical value, and decision).
B) Fill out the following summary table for One-Way ANOVA:
Source of Variation | SS | df | MS | F |
Among Groups | ||||
Within Groups | 14.54 | - | ||
Total | 22 | - | - |
C) Using the Tukey-Kramer method, determine which pair of the designs have the difference in mean distances at the 0.05 level of significance by filling out the following table (the upper-tail critical value from the studentized range distribution with 3 and 20 degrees of freedom as Qα = 3.578)
Pair (i,j) | |Xbari -Xbarj | | Comparison (> or <) | Critical Range | Difference (Yes or No) |
(A,B) | ||||
(A,C) | ||||
(B,C) |
A)
The hypotheses are :
Test is two tailed.
Here we have
Test statistics will be
Degree of freedom of numerator is df1=7-1=6 and degree of freedom of denominator is df2=8-1=7.
So critical value for 0.05 level of significance using excel function "=FINV(0.025,6,7)" is 5.119.
Since F < 5.119 so we fail to reject the null hypothesis.
That is we cannot conclude that there is evidence of a difference in the variance of the update times between Systems B and C.
(b)
The SS among groups is:
There are 3 groups so degree of freedom among groups is df=n-12
Source of Variation | SS | df | MS | F |
Among Groups | 124.326 | 2 | 62.163 | 4.275 |
Within Groups | 14.54*20=290.8 | 23-3=20 | 14.54 | - |
Total | 415.126 | 22 | - | - |
C)
Here we have 3 groups. The degree of freedom is
df= 20
So Tukey's HSD will be
Following is the completed table:
groups (i-j) | xbari | xbarj | ni | nj | HSD | xbari-xbarj | Lower limit | Upper limit | Significant(Yes/No) |
mu1-mu2 | 41.46 | 36.33 | 8 | 7 | 4.993 | 5.13 | 0.137 | 10.123 | Yes |
mu1-mu3 | 41.46 | 35.84 | 8 | 8 | 4.8237 | 5.62 | 0.7963 | 10.4437 | yes |
mu2-mu3 | 36.33 | 35.81 | 7 | 8 | 4.993 | 0.52 | -4.473 | 5.513 | No |