Chapter 11
Two Samples Tests of Hypothesis
True/False
1. If the null hypothesis states that there is no difference between the mean income of males and the mean income of females, then the test is one-tailed.
Answer: False
2. If the null hypothesis states that there is no difference between the mean net income retail stores in Chicago and New York City, then the test is two-tailed.
Answer: True
3. If we are testing for the difference between two population means, it is assumed that the sample observations from one population are independent of the sample observations from the other population.
Answer: True
4. If we are testing for the difference between two population proportions, it is assumed that the two populations are approximately normal and have equal variances.
Answer: False
5. If we are testing for the difference between two population proportions, it is assumed that the two samples are large enough that the binomial distribution can be approximated by the normal distribution.
Answer: True
6. When sample sizes are less than 30, a test for the differences between two population means has n–1 degrees of freedom.
Answer: False
7. If we are testing for the difference between two population means and assume that the two populations have equal but unknown standard deviations, then the test has (n1 + n2 – 2) degrees of freedom.
Answer: True
8. If we are testing for the difference between two population means and assume that the two populations have equal but unknown standard deviations, the variances are pooled to compute the best estimated variance.
Answer: True
9. If we are testing for the difference between two population means and assume that the two populations have unequal and unknown standard deviations, the degrees of freedom for the test statistic must be computed or calculated.
Answer: True
10. If we are testing for the difference between two population means and assume that the two populations have unequal and unknown standard deviations, the variances are pooled to compute the best estimated variance.
Answer: False AACSB: REF
11. If samples taken from two populations are not independent, then a test of paired differences is applied.
Answer: True
12. The paired difference test has (n1 + n2 – 2) degrees of freedom.
Answer: False
13. When testing for the difference between two dependent samples, n1 = n2.
Answer: True
14. We use the pooled estimate of the proportion in testing the difference between two population proportions.
Answer: True
15. The pooled estimate of the proportion is found by dividing the total number of samples by the total number of successes.
Answer: False
16. The paired t test is especially appropriate when the sample sizes of two groups are the same.
Answer: False
17. A committee studying employer-employee relations proposed that each employee would rate his or her immediate supervisor and in turn the supervisor would rate each employee. To find reactions regarding the proposal, 120 office personnel and 160 plant personnel were selected at random. Seventy-eight of the office personnel and 90 of the plant personnel were in favor of the proposal. Computed z = 1.48. At the 0.05 level, it was concluded that there is sufficient evidence to support the belief that the proportion of office personnel in favor of the proposal is greater than that of the plant personnel.
Answer: False
18. A statistics professor wants to compare grades of two different groups of students taking the same course in two different sections. This is an example of a paired sample.
Answer: False
19. In one class, a statistics professor wants to compare grades on the first and second exams. This is an example of paired or dependent observations.
Answer: True
Multiple Choice
20. If the decision is to reject the null hypothesis of no difference between two population parameters, at the 5% level of significance, what are examples of the alternate hypothesis and rejection region?
A)
B)
C)
D)
Answer: B
21. A poll of 400 people from Dobbs Ferry showed 250 preferred chocolate raspberry coffee while 170 out of 350 in Irvington preferred the same flavor. To test the hypothesis that there is no difference in preferences in the two villages, what is the alternate hypothesis?
A)
B)
C)
D)
Answer: D
22. If the null hypothesis that two means are equal is true, where will 97% of the computed z-values lie between?
A) 2.58
B) 2.33
C) 2.17
D) 2.07
Answer: C
23. How is a pooled estimate of the population proportion represented?
A) pc
B) z
C)
D) n
Answer: A
24. Suppose we are testing the difference between two proportions at the 0.05 level of significance. If the computed z is –1.07, what is our decision?
A) Reject the null hypothesis
B) Do not reject the null hypothesis
C) Take a larger sample
D) Reserve judgment
Answer: B
25. The net weights of a sample of bottles filled by a machine manufactured by Edne, and the net weights of a sample filled by a similar machine manufactured by Orno, Inc., are (in grams):
Edne: 5, 8, 7, 6, 9 and 7
Orno: 8, 10, 7, 11, 9, 12, 14 and 9
Testing the claim at the 0.05 level that the mean weight of the bottles filled by the Orno machine is greater than the mean weight of the bottles filled by the Edne machine, what is the critical value? Assume equal standard deviations for both samples.
A) 2.179
B) 2.145
C) 1.782
D) 1.761
Answer: C
26. A hypothesis will test that two population means are equal. A sample of 10 with a standard deviation of 3 is selected from the first population and a sample of 15 with a standard deviation of 8 from the second population. The standard deviations are not equal. Testing the claim at the 0.01 level, what is the critical value? Assume unequal standard deviations.
A) 2.845
B) 2.787
C) 2.807
D) 2.977
Answer: A
27. Which of the following conditions must be met to conduct a test for the difference in two sample means?
A) Data must be at least of interval scale
B) Populations must be normal
C) Variances in the two populations must be equal
D) A and B correct
E) A, B, and C are correct
Answer: D
28. When is it appropriate to use the paired difference t-test?
A) Four samples are compared at once
B) Any two samples are compared
C) Two independent samples are compared
D) Two dependent samples are compared
Answer: D
29. Using two independent samples, two population means are compared to determine if a difference exists. The population standard deviations are equal. The number in the first sample is fifteen and the number in the second sample is twelve. How many degrees of freedom are associated with the critical value?
A) 24
B) 25
C) 26
D) 27
Answer: B
30. Administering the same test to a group of 15 students and a second group of 15 students to see which group scores higher is an example of
A) a one sample test of means.
B) a two sample test of means.
C) a paired t-test.
D) a test of proportions.
Answer: B
31. What is the critical value for a one-tailed hypothesis test in which a null hypothesis is tested at the 5% level of significance based on two samples, both sample sizes are 13? Assume the population standard deviations are equal.
A) 1.708
B) 1.711
C) 2.060
D) 2.064
Answer: B
32. What is the critical value for a one-tailed hypothesis test in which a null hypothesis is tested at the 5% level of significance based on two samples, both sample sizes are 13? The standard deviations for the samples are 5 and 7. Assume the population standard deviations are unequal.
A) 2.064
B) 1.711
C) 2.074
D) 1.717
Answer: D
33. If two samples are used in a hypothesis test for which the combined degrees of freedom is 24, which one of the following is NOT true about the two sample sizes? Assume the population standard deviations are equal.
A) Sample A = 11; sample B = 13
B) Sample A = 12; sample B = 14
C) Sample A = 13; sample B = 13
D) Sample A = 10; sample B = 16
E) Cannot determine from the above information
Answer: A
34. If two samples, one of size 14 and the second of size 13, are used to test the difference between population means, how many degrees of freedom are used to find the critical value? Assume the population standard deviations are equal.
A) 27
B) 26
C) 25
D) 14
E) 13
Answer: C
35. 20 randomly selected statistics students were given 15 multiple-choice questions and 15 open-ended questions – all on the same material. The professor was interested in determining which type of questions the students scored higher. This experiment is an example of
A) a one sample test of means.
B) a two sample test of means.
C) a paired t-test.
D) a test of proportions.
Answer: C
Use the following to answer questions 35-36:
Of 250 adults who tried a new multi-grain cereal, “Wow!”, 187 rated it excellent; of 100 children sampled, 66 rated it excellent.
36. Using the 0.1 significance level and the alternate hypothesis p1 not equal to p2, what is the null hypothesis?
A)
B)
C)
D) None of the above
Answer: C
37. What test statistic should we use?
A) z-statistic
B) Right one-tailed test
C) Left one-tailed test
D) Two-tailed test
Answer: A
Use the following to answer questions 38-45:
A national manufacturer of ball bearings is experimenting with two different processes for producing precision ball bearings. It is important that the diameters be as close as possible to an industry standard. The output from each process is sampled and the average error from the industry standard is calculated. The results are presented below.
The researcher is interested in determining whether there is evidence that the two processes yield different average errors. Assume that the population standard deviations are equal.
38. What is the null hypothesis?
A) .
B) .
C) .
D) .
Answer: A
39. What is the alternate hypothesis?
A) .
B) .
C) .
D) .
Answer: B
40. What is the degrees of freedom?
A) 10
B) 13
C) 26
D) 24
Answer: D
41. What is the critical t value at the 1% level of significance?
A) +2.779
B) –2.492
C) 1.711
D) 2.797
Answer: D
42. What is the computed value of t?
A) +2.797
B) –2.797
C) –13.70
D) +13.70
Answer: C
43. What is the decision at the 1% level of significance?
A) Reject the null hypothesis and conclude the means are different.
B) Reject the null hypothesis and conclude the means are the same.
C) Fail to reject the null hypothesis and conclude the means are the same.
D) Fail to reject the null hypothesis and conclude the means are different.
Answer: A
44. Assume calculated t to be +2.70, at the 0.01 level of significance what would be the decision?
A) Reject the null hypothesis and conclude the means are different.
B) Reject the null hypothesis and conclude the means are the same.
C) Fail to reject the null hypothesis and conclude the means are the same.
D) Fail to reject the null hypothesis and conclude the means are different.
Answer: C
45. This example is what type of test?
A) One sample test of means.
B) Two sample test of means.
C) Paired t-test.
D) Test of proportions.
Answer: B
Use the following to answer questions 46-48:
The results of a mathematics placement exam at Mercy College for two campuses is as follows:
46. What is the null hypothesis if we want to test the hypothesis that the mean score on Campus 1 is higher than on Campus 2?
A) .
B) .
C) .
D) .
E) None of the above
Answer: E
47. What is the computed value of the test statistic?
A) 9.3
B) 2.6
C) 3.4
D) 1.9
Answer: C
48. Given that the two population standard deviations are known, what is the p-value if the computed test statistic is 4.1?
A) 1.0
B) 0.0
C) 0.05
D) 0.95
Answer: B
Fill-in-the-Blank
49. What is the purpose of pooling the sample variances when testing the difference between two population means? ______
Answer: To compute a single estimate of the population variance.
50. What is the critical value of t for a two-tail test of the difference of two means, a level of significance of 0.10 and sample sizes of seven and fifteen? Assume equal population standard deviations. ______
Answer: 1.734
51. What is the critical value of t for the claim that the difference of two means is less than zero with a = 0.025 and sample sizes of nine and seven? Assume equal population standard deviations. ______
Answer: -2.179
Use the following to answer questions 52-55:
A study by a bank compared the average savings of customers who were depositors for three years or less, with those who had been depositors for more than three years. The results of a sample are:
52. Assuming that the financial officer wants to show that there is a difference in the average savings balance between the two classes of depositors, what is the null hypothesis? ______