Exam scores from two semesters for a given class (not this one!) are given on th
ID: 3182877 • Letter: E
Question
Exam scores from two semesters for a given class (not this one!) are given on the following page. The professor hypothesizes that if the exams were equivalent in terms of the material covered, number of questions, types of questions asked, etc. average score and variability of the scores should be the same from one semester to the next. To help the professor determine whether his hypotheses are correct, complete the following:
a. State the null hypotheses in terms of the mean and variation.
b. Manually carry out a formal test of these hypotheses (for both the mean and variance) assuming an alpha value of 0.05.
c. Which tests did you choose for b? Why did you choose them?
d. State your conclusion both formally, and in plain English
e. What assumption(s) have you made in order to carry out the test?
ExamFall
ExamSpring
84
54
68
88
57
54
69
76
76
88
87
86
74
69
61
85
82
74
62
55
91
75
89
88
72
63
88
80
87
89
77
79
88
78
74
68
86
84
90
71
82
69
80
91
73
74
54
68
65
88
82
69
70
85
84
63
91
77
83
ExamFall
ExamSpring
84
54
68
88
57
54
69
76
76
88
87
86
74
69
61
85
82
74
62
55
91
75
89
88
72
63
88
80
87
89
77
79
88
78
74
68
86
84
90
71
82
69
80
91
73
74
54
68
65
88
82
69
70
85
84
63
91
77
83
Explanation / Answer
a) H0: 1 - 2 = 0 i.e. (1 = 2)
H1: 1 - 2 0 i.e. (1 2)
Assuming population variances are equal, we would have to calculate pooled-variance t-Test
Sp^2= (n1-1)S1^2+(n2-1)S2^2/(n1-1)+(n2-1)
= (31-1)*10.40^2+(28-1)*11.17^2/30+27
= 3244.8+3368.76/57
=116.03
tSTAT=(X1-X2)-(µ1-µ2)/Sp^2(1/n1+1/n2)
=(77.52-75.39)-0/116.03(1/31+1/28)
=2.13/0.3656
=5.83
tCRIT is 2.0025 and hence reject the null hypothesis
For Variance:-
H0: 21 = 22
H1: 21 22
FSTAT=S1^2/S2^2=10.40^2/11.17^2=108.16/124.77=0.87
FCRIT=2.13
Hence, we cannot reject null hypothesis
ExamFall ExamSpring 84 54 68 88 57 54 69 76 76 88 87 86 74 69 61 85 82 74 62 55 91 75 89 88 72 63 88 80 87 89 77 79 88 78 74 68 86 84 90 71 82 69 80 91 73 74 54 68 65 88 82 69 70 85 84 63 91 77 83 77.51613 75.3928571 Mean 10.40151 11.1731798 SDa) H0: 1 - 2 = 0 i.e. (1 = 2)
H1: 1 - 2 0 i.e. (1 2)
Assuming population variances are equal, we would have to calculate pooled-variance t-Test
Sp^2= (n1-1)S1^2+(n2-1)S2^2/(n1-1)+(n2-1)
= (31-1)*10.40^2+(28-1)*11.17^2/30+27
= 3244.8+3368.76/57
=116.03
tSTAT=(X1-X2)-(µ1-µ2)/Sp^2(1/n1+1/n2)
=(77.52-75.39)-0/116.03(1/31+1/28)
=2.13/0.3656
=5.83
tCRIT is 2.0025 and hence reject the null hypothesis
For Variance:-
H0: 21 = 22
H1: 21 22
FSTAT=S1^2/S2^2=10.40^2/11.17^2=108.16/124.77=0.87
FCRIT=2.13
Hence, we cannot reject null hypothesis
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.