In: Statistics and Probability
Please solve the hypothesis testing problems (#1, and 2) using Minitab as the tool. For each problem, (1) specify the business and statistical hypotheses, (2) specify what the Type I and Type II errors are in this business context, and, the implications of making those errors, (3) include the results from Minitab, (4) draw appropriate conclusions to your statistical hypotheses based on the results, and, finally, (5) present the business conclusions in a short non-statistical summary.
Suppose Smith and Wilson is a relatively small West Coast advertising agency. Assume that they have hired you to help in their newly established advertising research department. Your first task is to evaluate the results of a copy test for a new consumer product. Three different versions of the advertisement were prepared. A random sample of 10 viewers watched the three versions. After each commercial was shown, each consumer’s attitude toward the product was measured on a scale of 1 to 100 (the higher the score, the more favorable the attitude). The scores of the 10 viewers are below:
Viewer |
Version |
||
A |
B |
C |
|
1 |
66 |
61 |
85 |
2 |
79 |
51 |
90 |
3 |
58 |
44 |
79 |
4 |
77 |
50 |
88 |
5 |
65 |
35 |
78 |
6 |
59 |
28 |
69 |
7 |
71 |
41 |
89 |
8 |
80 |
38 |
95 |
9 |
77 |
45 |
85 |
10 |
68 |
50 |
80 |
The ANOVA output is:
The hypothesis being tested is:
H0: µ1 = µ2 = µ3
Ha: Not all means are equal
The p-value is 0.000.
Since the p-value (0.000) is less than the significance level (0.05), we can reject the null hypothesis.
Therefore, we can conclude that not all means are equal.
Thus, we can say that there is a difference in the consumer’s attitude toward the product.