In: Statistics and Probability
7. Coke Cola Inc. approach your professor that they have invented a smart energy drink that they believe it can make the students calm and clear about doing statistics. The professor took this drink to the two sections of BUQU1230. One section took the sugar drinks (fake drinks) and the other section took the real drinks.
Sugar drinks | Smart drinks |
97 | 64 |
95 | 85 |
89 | 72 |
79 | 64 |
78 | 74 |
87 | 93 |
83 | 70 |
94 | 79 |
76 | 79 |
79 | 75 |
83 | 66 |
84 | 83 |
76 | 74 |
82 | 70 |
85 | 82 |
85 | 82 |
91 | 75 |
72 | 78 |
86 | 99 |
70 | 57 |
91 | 91 |
82 | 78 |
73 | 87 |
96 | 93 |
64 | 89 |
74 | 81 |
88 | 84 |
88 | 63 |
60 | 78 |
73 | 66 |
84 | |
85 | |
85 |
The result of the tests were listed in excel file. At 5% significance level, can we conclude that the average mark is higher in the section with smart drinks than the section with the sugar drink?
For Sugar drinks :
∑x = 2460
∑x² = 204186
n1 = 30
Mean , x̅1 = Ʃx/n = 2460/30 = 82
Standard deviation, s2 = √[(Ʃx² - (Ʃx)²/n)/(n-1)] = √[(204186-(2460)²/30)/(30-1)] = 9.2214
For Smart drinks :
∑x = 2585
∑x² = 205597
n2 = 33
Mean , x̅2 = Ʃx/n = 2585/33 = 78.3333
Standard deviation, s2 = √[(Ʃx² - (Ʃx)²/n)/(n-1)] = √[(205597-(2585)²/33)/(33-1)] = 9.8510
----
Null and Alternative hypothesis:
Ho : µ1 ≥ µ2
H1 : µ1 < µ2
Pooled variance :
S²p = ((n1-1)*s1² + (n2-1)*s2² )/(n1+n2-2) = ((30-1)*9.2214² + (33-1)*9.851²) / (30+33-2) = 91.3333
Test statistic:
t = (x̅1 - x̅2) / √(s²p(1/n1 + 1/n2 ) = (82 - 78.3333) / √(91.3333*(1/30 + 1/33)) = 1.5209
df = n1+n2-2 = 61
p-value = T.DIST(1.5209, 61, 1) = 0.9333
Decision:
p-value > α, Do not reject the null hypothesis
Conclusion:
There is not enough evidence to conclude that the average mark is higher in the section with smart drinks than the section with the sugar drink at 0.05 significance level.