1) Suppose you want to test a hypothesis that two treatments, A and B, are equivalent against the alternative that the response for A tend to be larger than those of B. You plan to use a paired difference experiment and to analyze the resulting data, which is reproduce below. Given that, the observations are not normally distributed:
i) Specify the null and alternative hypothesis you would test
ii) Conduct the test using the 0.05 significance level
|
Pair
|
1
|
2
|
3
|
4
|
6
|
7
|
8
|
9
|
10
|
|
A
|
54
|
60
|
98
|
43
|
82
|
77
|
74
|
29
|
80
|
|
B
|
45
|
45
|
87
|
31
|
71
|
75
|
63
|
30
|
82
|
2) In a survey to find out the relationship between religious affiliation and attitudes abortion, the data below was obtained:
|
|
Catholics
|
Protestants
|
Moslems
|
Total
|
|
Approve
|
25
|
|
|
100
|
|
Disapprove
|
|
80
|
|
200
|
|
Total
|
80
|
120
|
100
|
300
|
(i) Copy and complete the table above
(ii) Test the hypothesis that there are no significances among the religious groups in terms of attitude towards abortion. (α=0.05)