INTRODUCTION TO HYPOTHESIS TESTING

TRUE/FALSE
1. A null hypothesis is a statement about the value of a population parameter.
ANS: T

2. An alternative or research hypothesis is an assertion that holds if the null hypothesis is false.
ANS: T

3. A Type I error is represented by ; it is the probability of rejecting a true null hypothesis.

ANS: T

4. A Type I error is represented by .

ANS: F

5. Reducing the probability of a Type I error also reduces the probability of a Type II error.
ANS: F

6. Increasing the probability of a Type I error will increase the probability of a Type II error.
ANS: F

7. It is possible to commit a Type I error and a Type II error at the same time.
ANS: F

8. A Type II error is represented by ; it is the probability of rejecting a true null hypothesis.

ANS: F

9. In a criminal trial, a Type I error is made when an innocent person is convicted.

ANS: T

10. The probability of making a Type I error and the level of significance are the same.
ANS: T

11. In a criminal trial, a Type II error is made when an innocent person is acquitted.
ANS: F

12. A Type II error is represented by ; it is the probability of failing to reject a false null hypothesis.
ANS: T

13. In testing a hypothesis, statements for the null and alternative hypotheses as well as the selection of the
level of significance should precede the collection and examination of the data.
ANS: T

14. The statement of the null hypothesis always includes an equals sign (=).
ANS: T

15. There is an inverse relationship between the probabilities of Type I and Type II errors; as one
increases, the other decreases, and vice versa.
ANS: T

MULTIPLE CHOICE
1. A professor of linguistics refutes the claim that the average student spends 3 hours studying for the
midterm exam. She thinks they spend more time than that. Which hypotheses are used to test the
claim?
a. H0:   3 vs. H1:   3 c. H0:   3 vs. H1:   3
b. H0:   3 vs. H1:   3 d. H0:   3 vs. H1:   3
ANS: A

2. The probability of a Type I error is denoted by:

a.  c. 
b. 1   d. 1  
ANS: C

3. A Type I error is committed if we make:

a. a correct decision when the null hypothesis is false.
b. a correct decision when the null hypothesis is true.
c. an incorrect decision when the null hypothesis is false.
d. an incorrect decision when the null hypothesis is true.
ANS: D

4. A Type II error is committed if we make:

a. a correct decision when the null hypothesis is false.
b. a correct decision when the null hypothesis is true.
c. an incorrect decision when the null hypothesis is false.
d. an incorrect decision when the null hypothesis is true.
ANS: C

5. The hypothesis of most interest to the researcher is:

a. the alternative hypothesis. c. both hypotheses are of equal interest.
b. the null hypothesis. d. Neither hypothesis is of interest.
ANS: A

6. A spouse suspects that the average amount of money spent on Christmas gifts for immediate family
members is above $1,200. The correct set of hypotheses is:
a. H0:   1200 vs. H1:   1200 c. H0:   1200 vs. H1:   1200
b. H0:   1200 vs. H1:   1200 d. H0:   1200 vs. H1:   1200
ANS: C

7. Which of the following conclusions is not an appropriate conclusion from a hypothesis test?
a. Reject H0. Sufficient evidence to support H1.
b. Fail to reject H0. Insufficient evidence to support H1.
c. Accept H0. Sufficient evidence to support H0.
d. All of these choices are true.
ANS: C

8. A Type I error occurs when we:

a. reject a false null hypothesis. c. don't reject a false null hypothesis.
b. reject a true null hypothesis. d. don't reject a true null hypothesis.
ANS: B

9. A Type II error is defined as:

a. rejecting a true null hypothesis. c. not rejecting a true null hypothesis.
 b. rejecting a false null hypothesis. d. not rejecting a false null hypothesis.
ANS: D

10. The probability of a Type II error is denoted by:

a.  c. 1  
b.  d. 1  
ANS: B

11. In a criminal trial, a Type I error is made when:

a. a guilty defendant is acquitted. c. a guilty defendant is convicted.
b. an innocent person is convicted. d. an innocent person is acquitted.
ANS: B

12. In a criminal trial, a Type II error is made when:

a. a guilty defendant is acquitted. c. a guilty defendant is convicted.
b. an innocent person is convicted. d. an innocent person is acquitted.
ANS: A

13. We cannot commit a Type I error when the:

a. null hypothesis is true. c. null hypothesis is false.
b. level of significance is 0.10. d. test is a two-tail test.
ANS: C

14. The level of significance can be:

a. any number between 1.0 and 1.0.
b. any number greater than zero.
c. any number greater than 1.96 or less than 1.96.
d. None of these choices.
ANS: D

15. Which of the following is an appropriate null hypothesis?

a. The mean of a population is equal to 60.
b. The mean of a sample is equal to 60.
c. The mean of a population is not equal to 60.
d. All of these choices are true.
ANS: A

16. Which of the following statements is not true?

a. The probability of making a Type II error increases as the probability of making a Type I
error decreases.
b. The probability of making a Type II error and the level of significance are the same.
c. The power of the test decreases as the level of significance decreases.
d. All of these choices are true.
ANS: B

17. Which of the following would be an appropriate alternative hypothesis?

a. The mean of a population is equal to 70.
b. The mean of a sample is equal to 70.
c. The mean of a population is greater than 70.
d. The mean of a sample is greater than 70.
ANS: C
 18. If a test of hypothesis has a Type I error probability of .05, this means that:
a. if the null hypothesis is true, we don't reject if 5% of the time.
b. if the null hypothesis is true, we reject it 5% of the time.
c. if the null hypothesis is false, we don't reject it 5% of the time.
d. if the null hypothesis is false, we reject it 5% of the time.
ANS: B

19. Suppose we wish to test H0:    vs. H1:   45. What will result if we conclude that the mean is
greater than 45 when the actual mean is 50?
a. We have made a Type I error.
b. We have made a Type II error.
c. We have made both a Type I error and a Type II error.
d. We have made the correct decision.
ANS: D

20. Which of the following probabilities is equal to the significance level ?

a. Probability of making a Type I error.
b. Probability of making a Type II error.
c. Probability of rejecting H0 when you are supposed to.
d. Probability of not rejecting H0 when you shouldn't.
ANS: A

21. If we reject the null hypothesis when it is false, then we have committed:
a. a Type II error. c. both a Type I error and a Type II error.
b. a Type I error. d. neither a Type I error nor a Type II error.
ANS: D

22. Researchers claim that 40 tissues is the average number of tissues a person uses during the course of a
cold. The company who makes Puffs brand tissues thinks that fewer of their tissues are needed. What
are their null and alternative hypotheses?
a. H0:   40 vs. H1:   40 c. H0:  40 vs. H1:  40
b. H0:   40 vs. H1:   40 d. H0:   40 vs. H1:   40
ANS: B

23. The owner of a local Jazz Club has recently surveyed a random sample of n = 200 customers of the
club. She would now like to determine whether or not the mean age of her customers is over 30. If so,
she plans to alter the entertainment to appeal to an older crowd. If not, no entertainment changes will
be made. The appropriate hypotheses to test are:
a. H0:   30 vs. H1:   30. c. H0:  30 vs. H1:  30.
b. H0:   30 vs. H1:   30. d. H0:  30 vs. H1:  30.
ANS: B

COMPLETION
1. If a researcher rejects a true null hypothesis, she has made a(n) ____________________ error.
ANS: Type I

2. If a researcher fails to reject a false null hypothesis he has made a(n) ____________________ error.
ANS: Type II

3. If a researcher rejects a false null hypothesis, she has made a(n) ____________________ decision.
ANS:
 correct
good

4. If a researcher fails to reject a true null hypothesis, he has made a(n) ____________________
decision.
ANS:
correct
good

5. The probability of a Type I error is denoted by ____________________.

ANS: 

6. The probability of a Type II error is denoted by ____________________.

ANS: 

7. You cannot commit a(n) ____________________ error when the null hypothesis is true.
ANS: Type II

8. You cannot commit a(n) ____________________ error when the null hypothesis is false.
ANS: Type I

9. The hypothesis testing procedure begins with the assumption that the null hypothesis is
____________________.
ANS: true

10. After you set up the hypotheses and collect your data, you calculate the statistic that serves as the
criterion for making your decision. This number is called the ____________________ statistic.
ANS: test

SHORT ANSWER
1. Formulate the null and alternative hypothesis in each case:
a. Ten years ago the average American drank 2.5 cups of coffee per day. You suspect that
amount has changed since then.
b. A researcher at Ohio State University speculates that the average SAT score for entering
freshmen is higher than the national average of 1,650.
c. The manager of the University of Iowa bookstore suspects the average amount of money a
student spends on books is less than the reported $400.
ANS:
a. H0:   2.5, H1:   2.5
b. H0:   1650, H1:   1650
c. H0:   400, H1:   400

2. For each of the following pairs of null and alternative hypotheses, determine whether or not they are
statistically correct to conduct a hypothesis test.
a. H0:   25, H1:   25
b. H0:   30, H1:   30
c. H0:  35, H1:  35
d. H0:  40, H1:  40
e. H0:   60, H1:   60
ANS:
a. appropriate
b. appropriate
 c. inappropriate
d. inappropriate
e. inappropriate

3. Suppose an auto manufacturer states that their car goes from 0 to 60 miles per hour in 10 seconds on
average, and you suspect that time is longer.
a. Set up the null and alternative hypotheses to test this claim.
b. Explain how you know which is the null hypothesis and which is the alternative
hypothesis.
ANS:
a. H0:  = 10 seconds vs. H1:  > 10 seconds
b. The null hypothesis represents the 'status quo.' In other words, it's what you would believe
unless there is sufficient evidence against it. It represents the original claim. The
alternative hypothesis is what you suspect is true, and what you want to show is true by
providing sufficient evidence against H0.

4. Suppose a pickup and delivery company states that their packages arrive within two days or less on
average. You want to find out whether the actual average delivery time is longer than this. You
conduct a hypothesis test.
a. Set up the null and alternative hypotheses.
b. Suppose you conclude wrongly that the company's statement about average delivery time
is within two days. What type of error is being committed and what is the impact of that
error?
c. Suppose you conclude wrongly that the delivery company's average time to delivery is in
fact longer than two days. What type of error did you commit and what is the impact of
this error?
d. Which error is worse from the company's standpoint, a Type I or a Type II error? Why?
e. Which error is worse from a consumer standpoint, a Type I or a Type II error? Why?
ANS:
a. H0:  = 2 days vs. H1:  > 2 days
b. You did not reject the company's claim but you should have. This is a Type II error. It is a
missed opportunity to say the company's claim is wrong. The impact is that people will
not get their packages delivered within 2 days on average, and could eventually become
dissatisfied.
c. You rejected the company's claim but you should not have. This is a Type I error. You
caused a false alarm. The impact is that the company loses its credibility needlessly. This
could cause some real problems for the person who made the false alarm.
d. The company does not want to lose its reputation unfairly, so they want to minimize the
chance for a Type I error. However, this increases the chance that customers will get their
packages delivered later than promised, on average.
e. The consumer wants to know their packages are being delivered as promised (on average),
so they want to decrease the chance of a Type II error. However, this increases the chance
of a false alarm.

5. Explain the difference between accepting H0 and failing to reject H0.

ANS:
The basis of making a decision in a hypothesis test is looking at the test statistic, and whether there is
enough evidence to reject H0 in favor of the alternative. That is not the same as saying you accept H0 if
you don't have enough evidence against it. Like in a jury trial you cannot conclude that someone is
innocent; you can only conclude that they are not guilty because there is not enough evidence to say
they are guilty. Whether or not H0 is actually true is a fact, and cannot be proven with sample data. The
best you can do is to gather evidence and determine whether you have enough evidence to reject H0
and accept the alternative. That is the real question anyway.
 6. Explain why a Type I error and a Type II error have an inverse relationship.
ANS:
In order to reduce the chance of a false alarm, you have to let some opportunities for detection slip by.
In order to reduce the chance for a missed opportunity to detect something, you are going to increase
the chance of a false alarm.

7. Think about a situation where you have a test for a virus. First, you are tested positive or negative.
Second, you either really do have the virus or you don't.
a. If you actually have the virus but the test did not catch it, which error has been made and
what is the impact of that error?
b. If you actually don't have the virus but the test says you did, which error is being made
and what is the impact of this error?
c. Which error is the worst one to commit in this situation and why?
ANS:
a. A Type II error has been committed, which is a very costly error. You are being told you
are OK when you really have the virus, and you are going untreated.
b. This is a false alarm, and a Type I error. A Type I error causes undue worry on behalf of
the person taking the test, and could cause some treatments to occur that shouldn't.
c. With a Type II error you are letting people with the virus go unnoticed, and hence
untreated. With a Type I error you falsely tell them they have the virus. This can cause
undue worry but it is certainly not as bad of a problem as letting someone go on not
knowing they have the virus. A Type II error is the worst in this situation.

8. The p-value of a test is the probability of observing a test statistic at least as extreme as the one
computed given that the null hypothesis is true.
ANS:
T

9. A p-value is usually set at 0.05.

ANS:
F

10. The p-value of a test is the smallest  at which the null hypothesis can be rejected.
ANS:
T

11. The p-value is the probability that the null hypothesis is true.
ANS:
F

12. In order to determine the p-value, it is necessary to know the level of significance.
ANS:
F

13. A one-tail p-value is two times the size of a two-tail test.

ANS:
F

14. In a one-tail test, the p-value is found to be equal to 0.054. If the test had been two-tail, then the
p-value would have been 0.027.
ANS:
 F

15. For a given level of significance, if the sample size is increased, the probability of committing a Type
II error will decrease.
ANS:
T

16. The critical values will bound the rejection and non-rejection regions for the null hypothesis.
ANS:
T

17. If we do not reject the null hypothesis, we conclude that there is enough statistical evidence to infer
that the null hypothesis is true.
ANS:
F

18. If a null hypothesis is rejected at the 0.05 level of significance, it must be rejected at the 0.025 level.
ANS:
F

19. A sample is used to obtain a 95% confidence interval for the mean of a population. The confidence
interval goes from 78.21 to 87.64. If the same sample had been used to test the null hypothesis that the
mean of the population differs from 90, the null hypothesis could be rejected at a level of significance
of 0.05.
ANS:
T

20. If we reject a null hypothesis at the 0.05 level of significance, then we must also reject it at the 0.10
level.
ANS:
T

21. If your p-value is greater than 0.900 you should reject H0 at the 0.10 level.
ANS:
F

22. A p-value is a probability, and must be between 0 and 1.

ANS:
T

23. A one-tail test for the population mean  produces a test-statistic z = 0.75. The p-value associated
with the test is 0.7734.
ANS:
F

24. Using the confidence interval when conducting a two-tail test for the population mean , we do not
reject the null hypothesis if the hypothesized value for  falls between the lower and upper confidence
limits.
ANS:
T
25. A two-tail test for the population mean  produces a test-statistic z = 1.89. The p-value associated with
the test is 0.0588.
ANS:
T

26. For a given level of significance, if the sample size is increased, the probability of committing a Type I
error will decrease.
ANS:
F

27. A sample is used to obtain a 95% confidence interval for the mean of a population. The confidence
interval goes from 10.89 to 13.21. If the same sample had been used to test H0:  = 12 vs. H1:   12,
H0 could not be rejected at the 0.05 level.
ANS:
T

28. If we reject the null hypothesis, we conclude that there is enough statistical evidence to infer that the
alternative hypothesis is true.
ANS:
T

29. The larger the p-value, the more likely one is to reject the null hypothesis.
ANS:
F

30. In order to determine the p-value, which of the following is not needed?
a. The level of significance.
b. Whether the test is one-tail or two-tail.
c. The value of the test statistic.
d. All of these choices are true.
ANS:
A

31. Which of the following p-values will lead us to reject the null hypothesis if the level of significance
equals 0.05?
a. 0.150
b. 0.100
c. 0.051
d. 0.025
ANS:
D

32. In testing the hypotheses H0:   50 vs. H1:   50, the following information is known: n = 64, =
53.5, and  = 10. The standardized test statistic z equals:
a. 1.96
b. 2.80
c. 2.80
d. 1.96
ANS:
C

33. If a hypothesis is not rejected at the 0.10 level of significance, it:

 a. must be rejected at the 0.05 level.
b. may be rejected at the 0.05 level.
c. will not be rejected at the 0.05 level.
d. must be rejected at the 0.025 level.
ANS:
C

34. In testing the hypotheses H0:   75 vs. H1:  < 75, if the value of the test statistic z equals 2.42, then
the p-value is:
a. 0.5078
b. 2.4200
c. 0.9922
d. 0.0078
ANS:
D

35. For a two-tail test, the null hypothesis will be rejected at the 0.05 level of significance if the value of
the standardized test statistic z is:
a. smaller than 1.96 or greater than 1.96
b. greater than 1.96 or smaller than 1.96
c. smaller than 1.96 or greater than 1.96
d. greater than 1.645 or less than 1.645
ANS:
C

36. In testing the hypotheses H0:   800 vs. H1:   800, if the value of the test statistic equals 1.75, then
the p-value is:
a. 0.0401
b. 0.0802
c. 0.4599
d. 0.9599
ANS:
B

37. If a hypothesis is rejected at the 0.025 level of significance, it:

a. must be rejected at any level.
b. must be rejected at the 0.01 level.
c. must not be rejected at the 0.01 level.
d. may or may not be rejected at the 0.01 level.
ANS:
B

38. Suppose that we reject a null hypothesis at the 0.05 level of significance. Then for which of the
following -values do we also reject the null hypothesis?
a. 0.06
b. 0.04
c. 0.03
d. 0.02
ANS:
A

39. The critical values z or z / 2 are the boundary values for:
 a. the rejection region(s).
b. the level of significance.
c. Type I error.
d. Type II error.
ANS:
A

40. In a two-tail test for the population mean, if the null hypothesis is rejected when the alternative
hypothesis is true:
a. a Type I error is committed.
b. a Type II error is committed.
c. a correct decision is made.
d. a one-tail test should be used instead of a two-tail test.
ANS:
C

41. Using a confidence interval when conducting a two-tail test for , we do not reject H0 if the
hypothesized value for :
a. is to the left of the lower confidence limit (LCL).
b. is to the right of the upper confidence limit (UCL).
c. falls between the LCL and UCL.
d. falls in the rejection region.
ANS:
C

42. In a two-tail test for the population mean, the null hypothesis will be rejected at  level of significance
if the value of the standardized test statistic z is such that:
a. z > z
b. z < z
c. z < z < z
d. | z | > z / 2
ANS:
D

43. In testing the hypothesis H0:   100 vs. H1:  > 100, the p-value is found to be 0.074, and the sample
mean is 105. Which of the following statements is true?
a. The probability of observing a sample mean at least as large as 105 from a population
whose mean is 100 is 0.074.
b. The probability of observing a sample mean smaller than 105 from a population whose
mean is 100 is 0.074.
c. The probability that the population mean is larger than 100 is 0.074.
d. None of these choices.
ANS:
A

44. If we reject the null hypothesis, we conclude that:

a. there is enough statistical evidence to infer that the alternative hypothesis is true.
b. there is not enough statistical evidence to infer that the alternative hypothesis is true.
c. there is enough statistical evidence to infer that the null hypothesis is true.
d. there is not enough statistical evidence to infer that the null hypothesis is true.
ANS:
A
45. Suppose that in a certain hypothesis test the null hypothesis is rejected at the .10 level; it is also
rejected at the .05 level; however it cannot be rejected at the .01 level. The most accurate statement
that can be made about the p-value for this test is that:
a. p-value = 0.01.
b. p-value = 0.10.
c. 0.01 < p-value < 0.05.
d. 0.05 < p-value < 0.10.
ANS:
C

46. Statisticians can translate p-values into several descriptive terms. Suppose you typically reject H0 at
level 0.05. Which of the following statements is correct?
a. If the p-value < 0.001, there is overwhelming evidence to infer that the alternative
hypothesis is true.
b. If 0.01 < p-value < 0.05, there is evidence to infer that the alternative hypothesis is true.
c. If p-value > 0.10, there is no evidence to infer that the alternative hypothesis is true.
d. All of these choices are true.
ANS:
D

47. If we do not reject the null hypothesis, we conclude that:

a. there is enough statistical evidence to infer that the alternative hypothesis is true.
b. there is not enough statistical evidence to infer that the alternative hypothesis is true.
c. there is enough statistical evidence to infer that the null hypothesis is true.
d. there is not enough statistical evidence to infer that the null hypothesis is true.
ANS:
B

48. In a one-tail test, the p-value is found to be equal to 0.068. If the test had been two-tail, the p-value
would have been:
a. 0.932
b. 0.466
c. 0.034
d. 0.136
ANS:
D

49. If the value of the sample mean is close enough to the hypothesized value 0 of the population mean
, then:
a. the value of 0 is definitely correct.
b. the value of 0 is definitely wrong.
c. we reject the null hypothesis.
d. we cannot reject the null hypothesis.
ANS:
D

50. The p-value of a test is the:

a. smallest  at which the null hypothesis can be rejected.
b. largest  at which the null hypothesis can be rejected.
c. smallest  at which the null hypothesis cannot be rejected.
d. largest  at which the null hypothesis cannot be rejected.
 ANS:
A

51. We have created a 95% confidence interval for  with the result (8, 13). What conclusion will we
make if we test H0:   15 vs. H1:   15 at  = 0.05?
a. Reject H0 in favor of H1
b. Accept H0 in favor of H1
c. Fail to reject H0 in favor of H1
d. We cannot tell what our decision will be from the information given
ANS:
A

52. The p-value criterion for hypothesis testing is to reject the null hypothesis if:
a. p-value = 
b. p-value < 
c. p-value > 
d.  < p-value < 
ANS:
B

53. If the p value is less than  in a two-tail test:

a. the null hypothesis should not be rejected.
b. the null hypothesis should be rejected.
c. a one-tail test should be used.
d. No conclusion should be reached.
ANS:
B

54. If a marketer wishes to determine whether there is evidence that average family income in a
community exceeds $32,000:
a. either a one-tail or two-tail test could be used with equivalent results.
b. a one-tail test should be utilized.
c. a two-tail test should be utilized.
d. None of these choices.
ANS:
B

55. We have created a 95% confidence interval for  with the results (10, 25). What conclusion will we
make if we test H0:   26 vs. H1:   26 at  = 0.025?
a. Reject H0 in favor of H1
b. Accept H0 in favor of H1
c. Fail to reject H0 in favor of H1
d. We cannot tell from the information given.
ANS:
D

56. The rejection region for testing H0:   100 vs. H1:   100, at the 0.05 level of significance is:
a. | z | < 0.95
b. | z | > 1.96
c. z > 1.65
d. z < 2.33
ANS:
 B

57. The owner of a local nightclub has recently surveyed a random sample of n = 300 customers of the
club. She would now like to determine whether or not the mean age of her customers is over 35. If so,
she plans to alter the entertainment to appeal to an older crowd. If not, no entertainment changes will
be made. Suppose she found that the sample mean was 35.5 years and the population standard
deviation was 5 years. What is the p-value associated with the test statistic?
a. 0.9582
b. 1.7300
c. 0.0418
d. 0.0836
ANS:
C

58. It is possible to directly compare the results of a confidence interval estimate to the results obtained by
testing a null hypothesis if:
a. a two-tail test for  is used.
b. a one-tail test for  is used.
c. a two-tail test for is used.
d. a one-tail test for is used.
ANS:
A

59. The rejection region for testing H0:   80 vs. H1:   80, at the 0.10 level of significance is:
a. z > 1.96
b. z < 0.90
c. z > 1.28
d. z < 1.28
ANS:
D

60. We have created a 90% confidence interval for  with the result (25, 32). What conclusion will we
make if we test H0:   28 vs. H1:   28 at  = 0.10?
a. Reject H0 in favor of H1.
b. Accept H0 in favor of H1.
c. Fail to reject H0 in favor of H1.
d. We cannot tell from the information given.
ANS:
C

61. The numerical quantity computed from the data that is used in deciding whether to reject H0 is the:
a. significance level.
b. critical value.
c. test statistic.
d. parameter.
ANS:
C
62. The owner of a local Karaoke Bar has recently surveyed a random sample of n = 300 customers of the
bar. She would now like to determine whether or not the mean age of her customers is over 35. If so,
she plans to alter the entertainment to appeal to an older crowd. If not, no entertainment changes will
be made. If she wants to be 99% confident in her decision, what rejection region she use if the
population standard deviation  is known?
a. Reject H0 if z < 2.33
b. Reject H0 if z < 2.58
c. Reject H0 if z > 2.33
d. Reject H0 if z > 2.58
ANS:
C

63. There are two approaches to making a decision in a hypothesis test once the test statistic has been
calculated. One approach is the ____________________ method. The other approach is the p-value
method.
ANS:
rejection region

64. There are two approaches to making a decision in a hypothesis test once the test statistic has been
calculated. One approach is the rejection region method. The other approach is the
____________________ method.
ANS:
p-value
p value

65. The ____________________ is a range of values such that if the test statistic falls into that range we
reject the null hypothesis in favor of the alternative
hypothesis.
ANS:
rejection region

66. The probability of a test statistic falling in the rejection region is equal to the value of
____________________.
ANS:

the significance level
a Type I error

67. When a null hypothesis is rejected, the test is said to be statistically ____________________ at level
.
ANS:
significant

68. If the conclusion of a hypothesis test is that a statistically significant result was found, then the null
hypothesis ____________________ (was/was not) rejected.
ANS:
was

69. The ____________________ of a test is the probability of observing a test statistic at least as extreme
as the one from your sample, given that H0 is true.
ANS:
p-value
p value
70. You reject H0 if the p-value of your hypothesis is ____________________ than the significance level.
ANS:
less
smaller

71. The ____________________ is a measure of the amount of statistical evidence that supports the
alternative hypothesis.
ANS:
p-value
p value

72. If we do not reject the null hypothesis, we conclude that there ____________________(is/is not)
enough statistical evidence to infer that the alternative hypothesis is true.
ANS:
is not

Production Filling
A production filling operation has a historical standard deviation of 6 ounces. When in proper
adjustment, the mean filling weight for the production process is 50 ounces. A quality control
inspector periodically selects at random 36 containers and uses the sample mean filling weight to see if
the process is in proper adjustment.
73. {Production Filling Narrative} State the null and alternative hypotheses.
ANS:
H0:   50 vs. H1:   50
74. {Production Filling Narrative} Using a standardized test statistic, test the hypothesis at the 5% level of
significance if the sample mean filling weight is 48.6 ounces.
ANS:
Test statistic: z = 1.40
Rejection region: | z | > z.025 = 1.96
Conclusion: Don't reject H0. We cannot infer that the process is out of proper adjustment.
75. {Production Filling Narrative} Develop a 95% confidence interval and use it to test the hypothesis.
ANS:
LCL = 46.64, and UCL = 50.56. Since the hypothesized value 50 falls in the 95% confidence interval,
we fail to reject H0 at  = 0.05.

76. A social researcher claims that the average adult listens to the radio less than 26 hours per week. He
collects data on 25 individuals' radio listening habits and finds that the mean number of hours that the
25 people spent listening to the radio was 22.4 hours. If the population standard deviation is known to
be eight hours, can we conclude at the 1% significance level that he is right?
ANS:
H0:   26 vs. H1:  < 26
Test statistic: z = 2.25
Rejection region: z < z.01 = 2.33
Conclusion: Don't reject H0. No, we cannot conclude at  = .01 that the social researcher is right.

77. A random sample of 100 observations from a normal population whose standard deviation is 50
produced a mean of 75. Does this statistic provide sufficient evidence at the 5% level of significance to
infer that the population mean is not 80?
ANS:
H0:   80 vs. H1:   80
 Rejection region: | z | > z.025 = 1.96
Test statistic: z = 1.0
Conclusion: Don't reject H0. Insufficient evidence at the 5% level to say the population mean differs
from 80.

78. In testing the hypotheses H0:   50 vs. H1:  < 50, we found that the standardized test statistic is z =
1.59. Calculate the p-value, and state your conclusion if  = .025.
ANS:
p-value = 0.0559 > . Fail to reject H0. Insufficient evidence to say the population mean is less than
50.

79. Suppose that 10 observations are drawn from a normal population whose variance is 64. The
observations are: 58, 62, 45, 50, 59, 65, 39, 40, 41, and 52. Test at the 10% level of significance to
determine if there is enough evidence to conclude that the population mean is greater than 45.
ANS:
H0:   45, H1:  > 45
Test statistic: z = 2.41
p-value = 0.008
Reject H0. Yes, there is enough statistical evidence at the 10% significance level to conclude that the
population mean is greater than 45.

80. Suppose that 9 observations are drawn from a normal population whose standard deviation is 2. The
observations are: 15, 9, 13, 11, 8, 12, 11, 7, and 10. At 95% confidence, you want to determine
whether the mean of the population from which this sample was taken is significantly different from
10.
a. State the null and alternative hypotheses.
b. Compute the value of the test statistic.
c. Compute the p-value.
d. Interpret the results.
ANS:
a. H0:   10 vs. H1:   10
b. z = 1.0
c. 0.1587  2 = 0.3174.
d. Cannot reject H0. Not enough evidence to say the mean is other than 10.

81. Determine the p-value associated with each of the following values of the standardized test statistic z,
and state your conclusion.
a. two-tail test, with z = 1.50, and  = .10
b. one-tail test, with z = 1.05, and  = .05
c. one-tail test, with z = 2.40, and  = .01
ANS:
a. 0.1336, fail to reject H0
b. 0.1469, fail to reject H0
c. 0.0082, reject H0

Watching the News

A researcher claims viewers spend an average of 40 minutes per day watching the news. You think the
average is higher than that. In testing your hypotheses H0:   40 vs. H1:  > 40, the following
information came from your random sample of viewers: = 42 minutes, n = 25. Assume  = 5.5, and
 = 0.10.
82. {Watching the News Narrative} Calculate the value of the test statistic.
ANS:
 z = 1.82
83. {Watching the News Narrative} Set up the rejection region.
ANS:
z > z.05 = 1.645
84. {Watching the News Narrative} Determine the p-value.
ANS:
0.0344
85. {Watching the News Narrative} Interpret the result.
ANS:
Reject H0 and conclude that the average time watching the News is more than 40 minutes per day for
viewers (at the 0.10 level).

LSAT Scores
The Admissions officer for the graduate programs at the University of Pennsylvania believes that the
average score on the LSAT exam at his university is significantly higher than the national average of
1,300. An accepted standard deviation for LSAT scores is 125. A random sample of 25 scores had an
average of 1,375.
86. {LSAT Scores Narrative} State the appropriate null and alternative hypotheses.
ANS:
H0:   1300 vs. H1:  > 1300
87. {LSAT Scores Narrative} Calculate the value of the test statistic and set up the rejection region at the
0.025 level. What is your conclusion?
ANS:
Test statistic: z = 3.0
Rejection region: z > z.025 = 1.96
Conclusion: Reject H0. There is enough statistical evidence to infer that the average LSAT for all
graduate students at the University of Pennsylvania is higher than 1,300.
88. {LSAT Scores Narrative} Calculate the p-value.
ANS:
p-value = 0.0013
89. {LSAT Scores Narrative} Use the p-value to test the hypotheses.
ANS:
Since p-value = 0.0013 <  = 0.025, we reject H0.

90. With the following p-values, would you reject or fail to reject the null hypothesis? Comment on the
statistical significance of each result. (Assume you normally reject H0 at level 0.08.)
a. p-value = 0.0025
b. p-value = 0.0328
c. p-value = 0.0795
d. p-value = 0.1940
ANS:
a. There is overwhelming evidence to reject H0. The test is highly significant.
b. There is strong evidence to reject H0. The test is deemed to be significant.
c. There is weak evidence to reject H0. The test is marginally statistically significant.
d. There is no evidence to reject H0. The test is not statistically significant.

Marathon Runners
A researcher wants to study the average miles run per day for marathon runners. In testing the
hypotheses: H0:   25 miles vs. H1:   25 miles, a random sample of 36 marathon runners drawn
from a normal population whose standard deviation is 10, produced a mean of 22.8 miles weekly.
91. {Marathon Runners Narrative} Compute the value of the test statistic and specify the rejection region
associated with 5% significance level.
 ANS:
Test statistic: z = 1.32
Rejection region: | z | > z.025 = 1.96
92. {Marathon Runners Narrative} Compute the p-value.
ANS:
0.0934  2 = 0.1868
93. {Marathon Runners Narrative} What can we conclude at the 5% significance level regarding the null
hypothesis?
ANS:
Fail to reject H0. Not enough evidence to say the average runner mileage is different from 25.
94. {Marathon Runners Narrative} Develop a 95% confidence interval estimate of the population mean.
ANS:
19.533 to 26.067
95. {Marathon Runners Narrative} Explain briefly how to use the confidence interval to test the
hypothesis.
ANS:
Since the hypothesized value 0 = 25 is included in the 95% confidence interval, we fail to reject H0 at
 = 0.05.

Toaster Oven
An appliance manufacturer claims to have developed a new toaster oven that consumes an average of
no more than 250 W. From previous studies, it is believed that power consumption for toaster ovens is
normally distributed with a standard deviation of 18 W. A consumer group suspects the actual average
is more than 250 W. They take a sample of 20 toaster ovens and calculate the average consumption to
be 260 W.
96. {Toaster Oven Narrative} What is the parameter of interest in this situation?
ANS:
The mean power consumption of all such toaster ovens (in W).
97. {Toaster Oven Narrative} State the appropriate hypotheses for the consumer group to do their test.
ANS:
H0:   250 vs. H1:  > 250
98. {Toaster Oven Narrative} For a test with a level of significance of 0.05, determine the critical value.
ANS:
z.05 = 1.645
99. {Toaster Oven Narrative} What is the value of the test statistic?
ANS:
z = 2.49
100. {Toaster Oven Narrative} Calculate the p-value of the test.
ANS:
0.0064
101. {Toaster Oven Narrative} What is the conclusion from the hypothesis test using  = .05?
ANS:
Since the p-value = 0.0064 < .05, we reject the null hypothesis. We conclude that the manufacturer's
claim is false; that is, the new toaster oven consumes an average of more than 250 W. Due to the small
size of the p-value, this result is highly statistically significant.

102. There is a direct relationship between the power of a test and the probability of a Type II error.
ANS:
F

103. The power of the test refers to the probability of rejecting a false null hypothesis.
 ANS:
T

104. For a given level of significance, if the sample size is increased, the power of the test will increase.
ANS:
T

105. If a sample size is increased at a given  level, the probability of committing a Type II error is
increased.
ANS:
F

106. The power of a test is the probability that a true null hypothesis will be rejected.
ANS:
F

107. For a given level of significance, if the sample size is increased, the probability of committing a Type
II error will increase.
ANS:
F

108. For a given sample size, the probability of committing a Type II error will increase when the
probability of committing a Type I error is reduced.
ANS:
T

109. The operating characteristic curve plots the values of  (the probability of committing a Type II error)
versus the values of the population mean .
ANS:
T

110. One way of expressing how well a test performs is to report its power--the probability of detecting a
false null hypothesis.
ANS:
T

111. As the alternative value of  increases, so does the power of the test.
ANS:
T

112. The power of a test is measured by its capability of:

a. rejecting a null hypothesis that is true.
b. not rejecting a null hypothesis that is true.
c. rejecting a null hypothesis that is false.
d. not rejecting a null hypothesis that is false.
ANS:
C

113. The power of a test is denoted by:

a. 
b. 
c. 1  
 d. 1  
ANS:
D

114. For a given level of significance, if the sample size increases, the probability of a Type II error will:
a. remain the same.
b. increase.
c. decrease.
d. be equal to 1.0 regardless of .
ANS:
C

115. For a given sample size n, if the level of significance  is decreased, the power of the test will:
a. increase.
b. decrease.
c. remain the same.
d. Not enough information to tell.
ANS:
B

116. For a given level of significance , if the sample size n is increased, the probability of a Type II error 
will:
a. decrease.
b. increase.
c. remain the same.
d. Not enough information to tell.
ANS:
A

117. If the probability of committing a Type I error for a given test is decreased, then for a fixed sample
size n, the probability of committing a Type II error will:
a. decrease.
b. increase.
c. stay the same.
d. Not enough information to tell.
ANS:
B

118. If we want to compute the probability of a Type II error, which of the following statements is false?
a. We need to know the significance level .
b. We need to know the sample size n.
c. We need to know the alternative value of the population mean .
d. All of these choices are true.
ANS:
D

119. Which of the following statements is false regarding the operating characteristic (OC) curve?
a. The OC curve plots the values of  versus the values of .
b. The OC curve plots the values of  versus the values of .
c. The OC curve can be useful in selecting a sample size n.
d. None of these choices.
ANS:
 B

120. For a given level of significance, if the sample size is increased, the probability of committing a Type
II error will ____________________.
ANS:
decrease

121. For a given level of significance, if the sample size is increased, the power of the test will
____________________.
ANS:
increase

122. To calculate the probability of a(n) ____________________ error you need to specify a value of 
other than the one given in the null hypothesis.
ANS:
Type II

123. Probabilities for Type I and Type II errors are actually ____________________ probabilities.
ANS:
conditional

124. By ____________________ the significance level, you increase the probability of a Type II error.
ANS:
decreasing
lowering

125. The ____________________ of a test is a measure of its performance.

ANS:
power

126. To increase the power of a test, ____________________ the sample size.

ANS:
increase

127. The power of a test plus the probability of a Type II error equals ____________________.
ANS:
one
1

128. A(n) ____________________ characteristic curve plots the probability of a Type II error for various
alternative values of ____________________.
ANS:
operating; 

129. As the sample size increases, the operating characteristic curves drop down to zero at a(n)
____________________ rate.
ANS:
increased
faster
higher
130. To test the hypotheses: H0:  = 40 vs. H1:   40, we draw a random sample of size 16 from a normal
population whose standard deviation is 5. If we set  = 0.01, find the probability of committing a Type
II error when  = 37.
ANS:
 = P(36.775 < < 43.225 given that  = 37) = P(0.18 < z < 4.98) = 0.5714

131. Calculate the probability of a Type II error for the hypothesis test: H0:  = 50 vs. H1:  > 50, given that
 = 55,  = 0.05,  = 10, and n = 16.
ANS:
 = P( < 54.113 given that  = 55) = P(z < .36) = 0.3594

Rechargeable Batteries
A researcher wants to study the average lifetime of a certain brand of rechargeable batteries (in hours).
In testing the hypotheses, H0:  = 950 hours vs. H1:   950 hours, a random sample of 25
rechargeable batteries is drawn from a normal population whose standard deviation is 200 hours.
132. {Rechargeable Batteries Narrative} Calculate , the probability of a Type II error when  = 1000 and
 = 0.10.
ANS:
 = P(884.2 < < 1015.8 given that  = 1000) = P(2.9 < z < .40) = .6535
133. {Rechargeable Batteries Narrative} Calculate the power of the test when  = 1000 and  = 0.10.
ANS:
Power = 1   = 1  0.6535 = 0.3465
134. {Rechargeable Batteries Narrative} Interpret the meaning of the power of the test.
ANS:
The probability of detecting that the mean lifetime is not 950 hours, when indeed the lifetime is 1,000
hours, is 0.3465, when  = 0.10.
135. {Rechargeable Batteries Narrative} Recalculate  if n is increased from 25 to 40.
ANS:
 = P(897.98 < < 1002.02, given that  = 1000) = P(3.23 < z < .06) = .5233
136. {Rechargeable Batteries Narrative} Review the results of the previous questions. What is the effect of
increasing the sample size on the value of ?
ANS:
 decreases as n increases.
137. {Rechargeable Batteries Narrative} Recalculate  if  is lowered from 0.10 to 0.05.
ANS:
 = P(871.6 < < 1028.4 given that  = 1000) = P(3.21 < z < .71) = 0.7604
138. {Rechargeable Batteries Narrative} Review the results of the previous questions. What is the effect of
decreasing the significance level on the value on ?
ANS:
 increases as  decreases

139. During the last energy crisis, a government official claimed that the average car owner refills the tank
when there is more than 3 gallons left. To check the claim, 10 cars were surveyed as they entered a gas
station. The amount of gas remaining before refill was measured and recorded as follows (in gallons):
3, 5, 3, 2, 3, 3, 2, 6, 4, and 1. Assume that the amount of gas remaining in tanks is normally distributed
with a standard deviation of 1 gallon. Compute the probability of a Type II error and the power of the
test if the true average amount of gas remaining in tanks is 3.5 gallons and= 0.10.
ANS:
 = P( < 3.4 given that  = 3.5) = P(z < 32) = 0.3745
Power = 1   = 0.6255