INTRODUCTION TO ESTIMATION

TRUE/FALSE
1. An unbiased estimator is said to be consistent if the difference between the estimator and the
parameter grows smaller as the sample size grows larger.
ANS: T

2. An unbiased estimator is a sample statistic whose expected value equals the population parameter.
ANS: T

3. An unbiased estimator is said to be consistent if the difference between the estimator and the
parameter grows larger as the sample size grows larger.
ANS: F

4. If there are two unbiased estimators of a parameter, the one whose variance is smaller is said to be
relatively efficient.
ANS: T

5. An interval estimate is a range of values within which the actual value of the population parameter,
such as , may fall.
ANS: T

6. An interval estimate is an estimate of the range for a sample statistic.

ANS: F

7. The sample variance (where you divide by n  1) is an unbiased estimator of the population variance.
ANS: T

8. Knowing that an estimator is unbiased only assures us that its expected value equals the parameter, but
it does not tell us how close the estimator is to the parameter.
ANS: T

9. The sample mean is a consistent estimator of the population mean .

ANS: T

10. The sample proportion is a consistent estimator of the population proportion p because it is unbiased
and the variance of is p(1  p) / n, which grows smaller as n grows larger.
ANS: T

11. The sample variance s2 is an unbiased estimator of the population variance 2 when the denominator of
s2 is n.
ANS: F

12. An unbiased estimator has an average value (across all samples) equal to the population parameter.
ANS: T

13. The sample variance is a point estimate of the population variance.

ANS: T

14. The confidence interval estimate of the population mean is constructed around the sample mean.
ANS: T
 15. A point estimate consists of a single sample statistic that is used to estimate the true population
parameter.
ANS: T

16. A specific confidence interval obtained from data will always correctly estimate the population
parameter.
ANS: F

MULTIPLE CHOICE
1. An estimator is said to be consistent if:
a. the difference between the estimator and the population parameter grows smaller as the
sample size grows larger.
b. it is an unbiased estimator.
c. the variance of the estimator is zero.
d. the difference between the estimator and the population parameter stays the same as the
sample size grows larger.
ANS: A

2. A point estimator is defined as:

a. a range of values that estimates an unknown population parameter.
b. a single value that estimates an unknown population parameter.
c. a range of values that estimates an unknown sample statistic.
d. a single value that estimates an unknown sample statistic.
ANS: B

3. Which of the following is a characteristic for a good estimator?

a. Being unbiased c. Having relative efficiency
b. Being consistent d. All of these choices are true.
ANS: D

4. An unbiased estimator of a population parameter is defined as:

a. an estimator whose expected value is equal to the parameter.
b. an estimator whose variance is equal to one.
c. an estimator whose expected value is equal to zero.
d. an estimator whose variance goes to zero as the sample size goes to infinity.
ANS: A

5. Which of the following statements is true?

a. The sample mean is relatively more efficient than the sample median.
b. The version of the sample variance where you divide by n is biased.
c. The sample mean is consistent.
d. All of these choices are true.
ANS: D

6. Which of the following statements is correct?

a. The sample mean is an unbiased estimator of the population mean.
b. The sample proportion is an unbiased estimator of the population proportion.
c. The difference between two sample means is an unbiased estimator of the difference
between two population means.
d. All of these choices are true.
ANS: D
 7. If there are two unbiased estimators of a population parameter available, the one that has the smallest
variance is said to be:
a. a biased estimator. c. consistent.
b. relatively efficient. d. relatively unbiased.
ANS: B

8. The problem with relying on a point estimate of a population parameter is that:

a. it is virtually certain to be wrong.
b. it doesn't have the capacity to reflect the effects of larger sample sizes.
c. it doesn't tell us how close or far the point estimate might be from the parameter.
d. All of these choices are true.
ANS: D

9. The sample variance s2 is an unbiased estimator of the population variance 2 when the denominator of
s2 is
a. n + 1 c. n  1
b. n d.
ANS: C

10. The librarian at the New York City Public Library has asked her assistant for an interval estimate of
the mean number of books checked out each day. The assistant took a sample and found the mean to
be 880 books. She provides the librarian with an interval estimate of between 790 and 970 books
checked out per day. An efficient, unbiased point estimate of the number of books checked out each
day at the New York City Public Library is:
a. 790 c. 90
b. 880 d. None of these choices.
ANS: B

COMPLETION
1. It is intuitively reasonable to expect that a larger sample will produce more ____________________
results.
ANS:
accurate
precise

2. ____________________ estimators do not have the capacity to reflect the effects of larger sample
sizes.
ANS: Point

3. ____________________ estimators reflect the effects of larger sample sizes, but

____________________ estimators do not.
ANS: Interval; point

4. An interval estimator estimates the value of an unknown ____________________.

ANS: parameter

5. A(n) ____________________ estimator of a population parameter is an estimator whose expected

value is equal to that parameter.
ANS: unbiased
 6. The sample ____________________ is an unbiased estimator for the population mean.
ANS:
mean
average

7. The version of the sample variance where you divide by ____________________ gives you an
unbiased estimator of the population variance.
ANS:
n1
n1

8. An unbiased estimator is ____________________ if its variance gets smaller as n gets larger.

ANS: consistent

9. If there are two unbiased estimators of the same parameter, the one whose variance is smaller is said to
be relatively more ____________________.
ANS: efficient

10. The sample ____________________ is relatively more efficient than the sample
____________________ when estimating the population mean.
ANS:
mean; median
average; median

SHORT ANSWER
1. Define unbiasedness.
ANS:
An unbiased estimator of a parameter is an estimator whose expected value equals the parameter.

2. Define consistency.
ANS:
An unbiased estimator is said to be consistent if the difference between the estimator and the
parameter grows smaller as the sample size grows larger.

3. Is the sample mean a consistent estimator of the population mean? Explain

ANS:
Yes, the mean is consistent because it is unbiased and the standard error grows smaller as the sample
size n increases.

4. Draw a sampling distribution of an unbiased estimator for .

ANS:

5. Draw a sampling distribution of a biased estimator for .

ANS:
 6. Draw sampling distributions of a consistent estimator for  where one sample mean is larger than the
other.
ANS:

7. Define relative efficiency.

ANS:
If there are two unbiased estimators of a parameter, the one whose variance is smaller is relatively
efficient.

8. Draw the sampling distribution of two unbiased estimators for , one of which is relatively efficient.
ANS:

9. Explain briefly why interval estimators are preferred to point estimators.

ANS:
An interval estimator incorporates the effects of sample size, but point estimators don't have the
capacity to do this.

10. A random sample of 10 university students was surveyed to help estimate the average amount of time
students spent per week on their computers. The student hours spent using a personal computer over a
randomly selected week were 13, 14, 5, 6, 8, 10, 7, 12, 15, 3.
a. Find an unbiased estimator of the average time per week for all university students.
b. Find an unbiased estimator of the variance.
c. Find a consistent estimator of the average time per week for all university students.
ANS:
a. An unbiased estimator of the population mean is the sample mean, 9.30 hours.
b. An unbiased estimator of the population variance is the sample variance, 16.9 hours.
c. A consistent estimator of the population mean is the sample mean, 9.30 hours.

11. In order to construct a confidence interval estimate of the population mean, the value of the population
mean is needed.
ANS:
F
12. A confidence interval is an interval estimate for which there is a specified degree of certainty that the
actual value of the population parameter will fall within the interval.
ANS:
T

13. The larger the confidence level used in constructing a confidence interval estimate of the population
mean, the narrower the confidence interval.
ANS:
F

14. One can reduce the width of a confidence interval by taking a smaller sample size.
ANS:
F

15. The width of a 95% confidence interval is 0.95.

ANS:
F

16. The term 1   refers to the probability that a confidence interval does not contain the population
parameter.
ANS:
F

17. The difference between the sample statistic and actual value of the population parameter is the
confidence level of the estimate.
ANS:
F

18. In the formula , the subscript  / 2 refers to the area in the lower tail or upper tail of the
sampling distribution of the sample mean.
ANS:
T

19. In developing an interval estimate for a population mean, the population standard deviation  was
assumed to be 8. The interval estimate was 50.0  2.50. Had  equaled 16, the interval estimate would
be 100  5.0.
ANS:
F

20. A 95% confidence interval estimate for a population mean  is determined to be 75 to 85. If the
confidence level is reduced to 80%, the confidence interval for  becomes wider.
ANS:
F

21. When constructing confidence interval for a parameter, we generally set the confidence level 1  
close to 1 (usually between 0.90 and 0.99) because it is the probability that the interval includes the
actual value of the population parameter.
ANS:
T
22. Suppose that a 90% confidence interval for  is given by . This notation means that we are
90% confident that  falls between and .
ANS:
F

23. We cannot interpret the confidence interval estimate of  as a probability statement about  because
the population mean is a fixed quantity.
ANS:
T

24. The width of the confidence interval estimate of the population mean  is a function of only two
quantities: the population standard deviation  and the sample size n.
ANS:
F

25. Doubling the population standard deviation  has the effect of doubling the width of the confidence
interval estimate of .
ANS:
T

26. Increasing the value of 1   narrows a confidence interval.

ANS:
F

27. Suppose that a 95% confidence interval for  is given by . This notation means that, if we
repeatedly draw samples of the same size from the same population, 95% of the values of will be
such that  would lie somewhere between and .
ANS:
T

28. When constructing confidence interval estimate of , doubling the sample size n decreases the width
of the interval by half.
ANS:
F

29. In this chapter you need four values to construct the confidence interval estimate of . They are the
sample mean, the sample size, the population standard deviation, and the confidence level.
ANS:
T

30. Given a mean of 2.1 and a standard deviation of 0.7, a 90% confidence interval will be 2.1  0.7.
ANS:
F

31. Suppose a sample size of 5 has mean 9.60. If the population variance is 5 and the population is
normally distributed, the lower limit for a 92% confidence interval is 7.85.
ANS:
T

32. Other things being equal, as the confidence level increases, the width of the confidence interval
increases.
ANS:
 T

33. Other things being equal, the confidence interval for the mean will be wider for 99% confidence than
for 95% confidence.
ANS:
T

34. The lower limit of the 90% confidence interval for , where n = 64, = 70, and  = 20, is 65.89.
ANS:
T

35. The letter  in the formula for constructing a confidence interval estimate of the population mean is:
a. the level of confidence.
b. the probability that a particular confidence interval will contain the population mean.
c. the area in the lower tail of the sampling distribution of the sample mean.
d. None of these choices.
ANS:
D

36. Which of the following is an incorrect statement about a 90% confidence interval?
a. If we repeatedly draw samples of the same size from the same population, 90% of the
resulting confidence intervals will include .
b. There is a 90% probability that the population mean  will lie between the lower
confidence limit (LCL) and the upper confidence limit (UCL).
c. We are 90% confident that our sample mean equals the population mean .
d. 90% of the population values will lie within the confidence interval.
ANS:
A

37. The term 1   refers to:

a. the probability that a confidence interval does not contain the population parameter.
b. the confidence level.
c. the level of unbiasedness.
d. the level of consistency.
ANS:
B

38. Suppose an interval estimate for the population mean was 62.84 to 69.46. The population standard
deviation was assumed to be 6.50, and a sample of 100 observations was used. The mean of the sample
was:
a. 6.62
b. 56.34
c. 62.96
d. 66.15
ANS:
D

39. The width of a confidence interval estimate of the population mean increases when the:
a. level of confidence increases
b. sample size decreases
c. value of the population standard deviation increases
d. All of these choices are true.
 ANS:
D

40. In developing an interval estimate for a population mean, the population standard deviation  was
assumed to be 10. The interval estimate was 50.92  2.14. Had  equaled 20, the interval estimate
would be
a. 60.92  2.14
b. 50.92  12.14
c. 101.84  4.28
d. 50.92  4.28
ANS:
D

41. If the confidence level is reduced, the confidence interval:

a. widens.
b. remains the same.
c. narrows.
d. disappears.
ANS:
C

42. The value for a 95% confidence interval estimate for a population mean  is
a. 0.95
b. 0.025
c. 1.65
d. 1.96
ANS:
D

43. In developing an interval estimate for a population mean, a sample of 50 observations was used. The
interval estimate was 19.76  1.32. Had the sample size been 200 instead of 50, the interval estimate
would have been:
a. 19.76  .33
b. 19.76  .66
c. 19.76  5.28
d. None of these choices.
ANS:
B

44. After constructing a confidence interval estimate for a population mean, you believe that the interval is
useless because it is too wide. In order to correct this problem, you need to:
a. increase the sample size.
b. increase the population standard deviation.
c. increase the level of confidence.
d. increase the sample mean.
ANS:
A

45. A confidence interval is defined as:

a. a point estimate plus or minus a specific confidence level.
 b. a lower and upper confidence limit associated with a specific level of confidence.
c. an interval that has a 95% probability of containing the population parameter.
d. a lower and upper confidence limit that has a 95% probability of containing the population
parameter.
ANS:
B

46. Which of the following is not a part of the formula for constructing a confidence interval estimate of
the population mean?
a. A point estimate of the population mean.
b. The standard error of the sampling distribution of the sample mean.
c. The confidence level.
d. The value of the population mean.
ANS:
D

47. Which of the following conditions does not allow you to use the formula to
estimate ?
a. Population is normally distributed and the population variance is known.
b. Population is not normally distributed but n is large; population variance is known.
c. Population has any distribution and n is any size.
d. All of these choices allow you to use the formula.
ANS:
C

48. In the formula , the  / 2 refers to:

a. the probability that the sample mean will not equal the population mean.
b. the probability that the confidence interval will not contain the population mean.
c. the level of confidence.
d. None of these choices.
ANS:
D

49. The larger the confidence level, the:

a. smaller the value of z / 2.
b. wider the confidence interval.
c. smaller the probability that the confidence interval will contain the population mean.
d. None of these choices.
ANS:
B

50. A 99% confidence interval estimate of the population mean  can be interpreted to mean:
a. if all possible sample are taken and confidence intervals created, 99% of them would
include the true population mean somewhere within their interval.
b. we have 99% confidence that we have selected a sample whose interval does include the
population mean.
c. we estimate that the population mean falls between the lower and upper confidence limits,
and this type of estimator is correct 99% of the time.
d. All of these choices are true.
ANS:
D
51. Suppose a 95% confidence interval for  turns out to be (1,000, 2,100). What does it mean to be 95%
confident?
a. In repeated sampling, the population parameter would fall in the resulting interval 95% of
the time.
b. 95% of the observations in the entire population fall in the given interval.
c. 95% of the observations in the sample fall in the given interval.
d. None of these choices.
ANS:
A

52. It is desired to estimate the average total compensation of CEOs in the publishing industry. Data were
randomly collected from 18 CEOs and 95% confidence interval was calculated to be ($2,190,000,
$4,720,000). Based on the interval above, do you believe the actual average total compensation of
CEOs in the publishing industry could be $3,000,000?
a. Yes, and I am sure of that.
b. Yes, and I am 95% confident of that.
c. No, and I am sure of that.
d. No, and I am 95% confident of that.
ANS:
B

53. When estimating the population mean using a confidence interval, the sample mean is in the
____________________ of the interval.
ANS:
middle

54. A confidence interval is a probability statement about the ____________________ mean.

ANS:
sample

55. The confidence ____________________ is the chance that the interval contains the parameter, over
repeated sampling.
ANS:
level

56. In the formula for a confidence interval for , 1   is called the ____________________.
ANS:
confidence level

57. The smallest number in a confidence interval is abbreviated by ____________________.

ANS:
LCL

58. It is ____________________ to say that a 95% confidence interval means there is a 95% chance that
the parameter lies in that confidence interval.
ANS:
wrong
incorrect

59. The population mean is a(n) ____________________ but ____________________ quantity.

ANS:
 fixed; unknown

60. If you increase the confidence level, the confidence interval becomes ____________________.
ANS:
wider
bigger
larger

61. We do not have control over the population standard deviation when forming a confidence interval,
but we can control the ____________________ and the ____________________.
ANS:
confidence level; sample size
sample size; confidence level

62. The confidence level that is considered to be the standard amongst statisticians is
____________________%.
ANS:
95

63. If the population values are very close to each other, the width of the confidence interval is
____________________ than if the population values are very far apart.
ANS:
narrower
smaller

64. Increasing the sample size fourfold decreases the width of the confidence interval by
____________________.
ANS:
half
one-half
50%

65. A survey of 100 businesses revealed that the mean after-tax profit was $80,000. Assume the
population standard deviation is $15,000:
a. Determine the 95% confidence interval estimate of the mean after-tax profit for all
businesses.
b. Explain why you can use the confidence interval formula here, even though the population
is not necessarily normal.
ANS:
a. LCL = $77,060 and UCL = $82,940.
b. By the Central Limit Theorem, as long as n is large (and 100 is considered large), the
sample means have an approximate normal distribution.

66. The temperature readings for 20 fall days (degrees Fahrenheit) in Wheeling, West Virginia, are
normally distributed with a mean of 5.5 degrees and a standard deviation of 1.5 degrees. Determine the
90% confidence interval estimate for the fall mean temperature.
ANS:
LCL = 4.9 degrees and UCL = 6.05 degrees.

67. A sample of 49 measurements of tensile strength for roof hangers are calculated to have a mean of
2.45 and a standard deviation of 0.25. (Units are Newton's per square meter.)
a. Determine the 95% confidence interval for mean tensile strength for all hangers.
b. Interpret this confidence interval.
 ANS:
a. LCL = 2.38 and UCL = 2.52 (Newton's per square meter).
b. I estimate the mean tensile strength for all roof hangars to be between 2.38 and 2.52
Newton's per square meter, based on my sample. We know that 95% of the time the true
population mean would fall in the resulting interval.

68. A random sample of 10 waiters in Weston, West Virginia, revealed the following hourly earnings,
including tips: 19, 18, 15, 16, 18, 17, 16, 18, 20, and 14. (Units are dollars.)
a. If the hourly earnings are normally distributed with a standard deviation of $4.50, estimate
with 95% confidence the mean hourly earnings for all waitresses in Iowa City.
b. Interpret your confidence interval.
ANS:
a. LCL = $14.31 and UCL = $19.89.
b. Based on my sample, I estimate that the mean hourly earnings is between $14.31 and
$19.89. I am 95% confident that in repeated sampling, the population parameter would fall
in the resulting interval.

Time Spent Playing Computer Games

Suppose that the amount of time teenagers spend playing computer games per week is normally
distributed with a standard deviation of 1.5 hours. A sample of 100 teenagers is selected at random,
and the sample mean computed as 6.5 hours.
69. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean.
ANS:
LCL = 6.21 and UCL = 6.79 (hours per week)
70. {Time Spent Playing Computer Games Narrative} Interpret the 95% confidence interval for this
situation.
ANS:
Based on our sample, we estimate the average time teenagers spend playing computer games is
between 6.21 hours and 6.79 hours per week. We know that 95% of the time the true population mean
would fall in the resulting interval.
71. {Time Spent Playing Computer Games Narrative} Determine and interpret the 99% confidence
interval estimate of the population mean.
ANS:
Based on our sample we estimate the average time teenagers spent playing computer games LCL =
6.11 and UCL = 6.89 (hours per week). Repeated samples correctly estimate this average 99% of the
time.
72. {Time Spent Playing Computer Games Narrative} Determine and interpret the 90% confidence
interval estimate of the population mean.
ANS:
LCL = 6.25 and UCL = 6.75 (hours per week). Repeated samples correctly estimate this average 90%
of the time.
73. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the sample size is changed to 300.
ANS:
LCL = 6.33 and UCL = 6.67 (hours per week)
74. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the sample size is changed to 36.
ANS:
LCL = 6.01 and UCL = 6.99 (hours per week)
75. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the population standard deviation is changed to 2.
ANS:
 LCL = 6.11 and UCL = 6.89 (hours per week)
76. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the population standard deviation is changed to 1.2.
ANS:
LCL = 6.26 and UCL = 6.74 (hours per week)
77. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the sample mean is changed to 5.0 hours.
ANS:
LCL = 4.71 and UCL = 5.29 (hours per week)
78. {Time Spent Playing Computer Games Narrative} Determine the 95% confidence interval estimate of
the population mean if the sample mean is changed to 8.5 hours.
ANS:
LCL = 8.21 and UCL = 8.79 (hours per week)
79. {Time Spent Playing Computer Games Narrative} What happens to the width of a confidence interval
in each of the following situations?
a. Confidence level increases
b. Confidence level decreases
c. Sample size increases
d. Sample size decreases
e. Population standard deviation increases
f. Population standard deviation decreases
g. Sample mean increases
h. Sample mean decreases
ANS:
a. Widens
b. Narrows
c. Narrows
d. Widens
e. Widens
f. Narrows
g. No change
h. No change

80. A random sample of 10 university students was surveyed to determine the amount of time spent
weekly at the library. The times are: 13, 14, 5, 6, 8, 10, 7, 12, 15, and 3. If the times are normally
distributed with a standard deviation of 5.2 hours, estimate with 90% confidence the mean weekly time
at the library by all university students.
ANS:
LCL = 6.59 and UCL = 12.01 hours.

81. A financial consultant wanted to determine the mean annual return on Bond funds. A random sample
of 60 returns shows a mean of 12%. If the population standard deviation is assumed to be 4%, estimate
with 95% confidence the mean annual return on all Bond funds.
ANS:
LCL = 11% and UCL = 13%

82. A market researcher is interested in studying the incomes of consumers in a particular region. The
population standard deviation is known to be $1,000. A random sample of 50 individuals resulted in an
average income of $15,000. What is the upper end point in a 99% confidence interval for the average
income?
ANS:
UCL = $15,364.87
83. An economist is interested in studying the spending habits of consumers in a particular region. The
population standard deviation is known to be $1,000. A random sample of 50 individuals resulted in an
average expense of $15,000. What is the width of the 99% confidence interval?
ANS:
Width = $729.74

84. A precision control engineer is interested in the mean length of tubing being cut automatically by
machine. It is known that the standard deviation in the cutting length is 0.15 feet. A sample of 60 cut
tubes yields a mean length of 12.15 feet. This sample will be used to obtain a 99% confidence interval
for the mean length cut by machine.
a. What is the z / 2 value to use in obtaining the confidence interval?
b. Develop the 99% confidence interval for .
ANS:
a. z / 2 = 2.58
b. LCL = 12.10 and UCL = 12.20 (feet)

Conference Rooms Rented

A hotel chain wants to estimate the average number of conference rooms rented daily in each month.
The population of conference rooms rented daily is assumed to be normally distributed for each with a
standard deviation of 24 rooms.
85. {Conference Rooms Rented Narrative} During January, a sample of 16 days has a sample mean of 48
rooms. This information is used to calculate an interval estimate for the population mean to be from 40
to 56 rooms. What is the level of confidence of this interval?
ANS:
81.64%
86. {Conference Rooms Rented Narrative} During February, a sample of 25 days has a sample mean of 37
rooms. Use this information to calculate a 92% confidence interval for the population mean.
ANS:
LCL = 28.6 and UCL = 45.4 (rooms)

87. To estimate with 95% confidence the mean of a normal population whose standard deviation is
assumed to be 4 and the maximum allowable sampling error is assumed to be 1, requires a random
sample of size 62.
ANS:
T

88. The sample size needed to estimate the population mean was found to be 865. If the value of the
population standard deviation was 75, and the maximum allowable error was 5, then the confidence
level used was 95%.
ANS:
T

89. The sample size needed to estimate a population mean to within 1 unit with 90% confidence given that
the population standard deviation is 10 is 17.
ANS:
F

90. In determining the size n needed to estimate the population mean, n increases as the confidence level
decreases.
ANS:
F
91. In determining the sample size n needed to estimate the population mean, n decreases as the desired
width of the confidence interval decreases.
ANS:
F

92. In determining the sample size n needed to estimate the population mean, n is higher if the population
standard deviation  is higher.
ANS:
T

93. When determining the sample size necessary for estimating the true population mean, which factor is
not of our concern when sampling with replacement?
a. The allowable or tolerable sampling error.
b. The level of confidence desired in the estimate.
c. The population standard deviation.
d. The population size.
ANS:
D

94. Which of the following statements is false regarding the sample size needed to estimate a population
mean?
a. It is directly proportional to the population variance.
b. It is directly proportional to the square of z / 2.
c. It is directly proportional to the square of the maximum allowable error B.
d. None of these choices.
ANS:
C

95. To estimate the mean of a normal population whose standard deviation is 6, with a bound on the error
of estimation equal to 1.2 and confidence level 99% requires a sample size of at least:
a. 166
b. 167
c. 13
d. None of these choices.
ANS:
B

96. The sample size needed to estimate a population mean within 2 units with a 95% confidence when the
population standard deviation equals 8 is
a. 62
b. 61
c. 8
d. None of these choices.
ANS:
A

97. The sample size needed to estimate a population mean to within 10 units was found to be 68. If the
population standard deviation was 50, then the confidence level used was:
a. 99%
b. 95%
c. 90%
d. None of these choices.
ANS:
 C

98. The sample size needed to estimate a population mean to within 50 units was found to be 97. If the
population standard deviation was 250, then the confidence level used was
a. 90%
b. 95%
c. 99%
d. None of these choices.
ANS:
B

99. The sampling error for a confidence interval is also defined as the ____________________ of
____________________.
ANS:
error; estimation

100. The error of estimation is the ____________________ between an estimator and the parameter.
ANS:
difference

101. When determining the required sample size for a confidence interval, you need to know the population
____________________, the confidence ____________________, and the ____________________
on the error of estimation.
ANS:
standard deviation; level; bound

102. Because n is an integer and we want the bound on the error of estimation to be no more than a given
amount, any non-integer value found for n must always be rounded ____________________.
ANS:
up

103. If the bound on the error of estimation decreases, the sample size ____________________.
ANS:
increases

104. If the population standard deviation is guesstimated, and it turned out to be smaller than you assumed,
then the sample size you calculated is ____________________ than it needs to be.
ANS:
larger
bigger
greater
more

105. If the population standard deviation is guesstimated, and it turned out to be larger than you assumed,
then the sample size you calculated is ____________________ than it needs to be.
ANS:
smaller
less
106. Statisticians can control the ____________________ of a confidence interval by determining the
sample size necessary to produce the desired results.
ANS:
width

107. The bound on the error of estimation is the ____________________ amount of sampling error that we
are willing to tolerate.
ANS:
maximum
greatest
largest

108. As the bound on the error of estimation decreases, the sample size ____________________.
ANS:
increases

109. Determine the sample size that is required to estimate a population mean to within 0.4 units with a
99% confidence when the population standard deviation is 1.75.
ANS:
128 (using z = 2.58)

College Dean
A college dean would like to estimate a population mean to within 40 units with 99% confidence given
that the population standard deviation is 200.
110. {College Dean Narrative} What sample size should be used?
ANS:
n = 167 (using z = 2.58)
111. {College Dean Narrative} What sample size should be used if the standard deviation is changed to 50?
ANS:
n = 11 (using z = 2.58)
112. {College Dean Narrative} What sample size should be used if using a 95% confidence level?
ANS:
n = 97
113. {College Dean Narrative} What sample size should be used if we wish to estimate the population
mean to within 10 units?
ANS:
n = 2,663 (using z = 2.58)

114. A research firm has been contracted to estimate the mean weekly family expenditure on clothes. He
believes that the standard deviation of the weekly expenditure is $125. Determine with 99%
confidence the number of families that must be sampled to estimate the mean weekly family
expenditure on clothes to within $15.
ANS:
n = 463 (using z = 2.58)

115. How large a sample of federal employees in Nevada should be taken if we want to estimate with 98%
confidence the mean salary to within $2,000. The population standard deviation is assumed to be
$10,500.
ANS:
n = 150
116. An electronics retailer is interested in studying the incomes of consumers in a particular area. The
population standard deviation is known to be $1,000. What sample size would the researcher need to
use for a 95% confidence interval if the difference between UCL and LCL should not be more than
$100?
ANS:
n = 1, 537 (Note that B equals $50 here, which is half of $100.)

117. An engineer for an electric fencing company is interested in the mean length of wires being cut
automatically by machine. The desired length of the wires is 12 feet. It is known that the standard
deviation in the cutting length is 0.15 feet. Suppose the engineer decided to estimate the mean length
to within 0.025 with 99% confidence. What sample size would be needed?
ANS:
n = 240 (using z = 2.58)