In: Statistics and Probability
Test to determine if the average cell phone bill differs when compared to the same programs and same areas. A random sample of cell phone bills (in dollars) from four companies is reported below a = .01
Verizon 100 125 105 100 110
Sprint 100 130 90 120 90
At and T 90 90 90 100 120
T Mobile 100 100 110 90 80
Null hypothesis ( H0 ) : All means are equal
i.e .,
Alternative hypothesis ( Ha ) : Atleast one of the is different
For the given data using Anova single factor in Excel we get output as
Anova: Single Factor | ||||||
SUMMARY | ||||||
Groups | Count | Sum | Average | Variance | ||
verizon | 5 | 540 | 108 | 107.5 | ||
sprint | 5 | 530 | 106 | 330 | ||
At and T | 5 | 490 | 98 | 170 | ||
T mobile | 5 | 480 | 96 | 130 | ||
ANOVA | ||||||
Source of Variation | SS | df | MS | F | P-value | F crit |
Between Groups | 520 | 3 | 173.3333 | 0.940113 | 0.444386 | 5.292214 |
Within Groups | 2950 | 16 | 184.375 | |||
Total | 3470 | 19 |
Decision :
p value > 0.01
i .e ., 0.444386 > 0.01
So fail to reject H0
Conclusion : At alpha = 0.01 l.o.s there is no evidence to conclude that the average cell phone bill differs when compared to the same programs and same areas.