UPM

Business Statistics 2
Houda Boubaker/Amira Bouziri
Fall 2022

Estimation: One Population

MCQs

1. The term 1-α 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.

2. All other things being equal, the larger the sample size, the narrower the interval estimates
that reflect the uncertainty about a mean's true value.
a. True
b. False
3. The width of a confidence interval is equal to twice the margin of error.
a. True
b. False
4. It is desired to estimate the average total compensation of CEOs in the service 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 service 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.

5. 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 population standard deviation.

b. increase the sample size.

c. increase the level of confidence.

d. increase the sample mean.

6. A 90% confidence interval for the mean percentage of airline reservations being canceled on
the day of the flight is (1.1%, 3.2%). What is the point estimator of the mean percentage of
reservations that are canceled on the day of the flight?
a. 1.05%
b. 2.15%
c. 2.1%
d. 1.60%

7. Which of the following statements is true?

a. If a sample has 16 observations and a 90% confidence estimate for μ is needed, the
appropriate t-score is 1.753.
b. If a sample has 16 observations and a 99% confidence estimate for μ is needed, the
appropriate t-score is 2.602.
c. If a sample has 20 observations and a 95% confidence estimate for μ is needed, the
appropriate t-score is 1.729.
d. If a sample has 20 observations and a 98% confidence estimate for μ is needed, the
appropriate t-score is 2.093.

8. Sales of a new line of athletic footwear are crucial to the success of a company. The company
wishes to estimate the average weekly sales of the new footwear to within $300 with 90%
confidence. The initial sales indicate that the standard deviation of the weekly sales figures is
approximately $1100. How many weeks of data must be sampled for the company to get the
information it desires?
a. 7 weeks
b. 37 weeks
c. 23 weeks
d. 10,915 weeks

9. What is the confidence level of the following confidence interval for µ? x̄±2 .33 σ / √ n
a. 233%
b. 67%
 c. 98%
d. 78%
10. 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 population size.

b. The population standard deviation.

c. The level of confidence desired in the estimate.

d. The allowable or tolerable sampling error.

Problem 1 (Interval estimate of the population mean: σ known)

The number of cars sold annually by used cars salesperson is normally distributed with a standard
deviation of 15. A random sample of 15 salespeople was taken and the number of cars each sold is
listed here.

79 43 58 66 101 63 79 33 58 71 60 101
74 55 88

x=68.6 (computed from sample data)

1. Find the 95% confidence interval estimate of the population mean.
x=68.6
σ=15
n=15
1-α=.95 so Z α / 2=Z 0.025 =1.96
We can use the formula as the population is normally distributed

σ
LCL= x−Z α =¿61
2 √n
σ
UCL= x +Z α =¿ 76.19
2 √n
2. Interpret the interval estimate.
We are 95% confident that the range (61,76.19) contains the true population mean number
of cars sold by salespeople. If we repeat selecting samples of size 15, 95% of them will
provide a confidence interval that contains the true mean and 5% won’t.

Problem 2 (Interval estimate of the population mean: σ un known)

A simple random sample of 100 concert tickets was drawn from a normal population. The mean and
standard deviation of the sample were $120 and $25, respectively. Estimate the population mean
with 90% confidence.
 x=120
s=25
n=100
1-α=.90 so t n−1 ,α / 2=t 99 ,0.05 ≈ 1.66

Check condition: The population is normally distributed (also n>30)

s
LCL= x−t α =115.85
2 √n
s
UCL= x +t α =¿124.15
2 √n
We are 90% confident that the range (115.85,124.15) contains the true population mean. If
we repeat selecting samples of size 100, 90% of them will provide a confidence interval that
contains the true mean and 10% won’t.

Problem 3 (Interval estimate of the population proportion)

A random sample of 200 physicians shows that there are 36 of them who make at least $400,000 a
year. Construct a 99% confidence interval estimate of the population proportion of physicians who
make at least $400,000 a year.

36
^p= =0.18
200

n=200

1−α=0.99 so Z .005=2.58

We chech that n ^p>5 and n(1− ^p )>5

^p ± Z α / 2
√ ^p (1− ^p )
n

0.18 ± 2.58
√ 0.18(0.82)
200

LCL=0.11

UCL=0.25
 Problem 4 (Interval estimate of the population variance)

The weights of a random sample of cereal boxes that are supposed to weigh 1 pound are listed here.
Estimate the variance of the entire population of cereal box weights with 90% confidence. Assume
that the weights of cereal boxes are normally distributed.

1.05 1.03 .98 1.00 .99 .97 1.01 .96

2
s =0.00092679 (computed from sample data)

n=8

2 2 2 2
1−α=0.90 so χ n−1 , α = χ 7 ,0.05 =14.067 and χ n−1 , 1− α = χ 7 ,0.95=2.167
2 2

We can use the formula as the population is normally distributed

2
(n−1)s (7)(0.00092679)
LCL= = =0.00046
χ2 α 14.067
n−1 ,
2

2
(n−1)s (7)(0.00092679)
UCL= 2 = =0.003
χ α 2.167
n−1 ,1−
2

Problem 5 (Determining the sample size to estimate the population mean)

1. Determine the sample size necessary to estimate a population mean to within 1 unit with 90%
confidence given that the population standard deviation is 10.
2 2
(1.645)2(10)2
Z α/ 2 σ
n= 2
= 2
=271
ME 1

2. Suppose that the sample mean was calculated as 150. Estimate the population mean with 90%
confidence.
x±1
LCL=149 and UCL=151

Problem 6 (Determining the sample size to estimate the population proportion)

As a manufacturer of guitars, a major corporation wants to estimate the proportion of guitar players
who are right-handed. How many guitar players must be surveyed if they want the margin of error to
be within ±0.02, with a 95% confidence?

2
Z α/ 2 0.25 (1.96)2 0.25
n= 2
= 2
=2401
ME (0.02)
Problem 7 (Interval estimate for a population mean, a population proportion)

The personnel director of a large corporation wishes to study absenteeism among clerical workers at
the corporation’s central office during the year. A random sample of 25 clerical workers reveals the
following:

 Absenteeism: X̄ =9 .7 days, s=4 . 0 days.

 12 clerical workers were absent more than 10 days.

1. Construct a 95% confidence interval estimate for the mean number of absences for clerical
workers during the year. Interpret. (Assume that the population is normally distributed)
s
As the population is normal, x ± t 0.025 ,24
√n

4
9.7 ± 2.604
√ 25
9.7 ± 1.6512
LCL=8.0488
UCL=11.3512
We are 95% confident, that the range [8.0488, 11.3512] contains the true population mean
number of absences of clerical workers per years.

2. Construct a 95% confidence interval estimate for the population proportion of clerical
workers absent more than 10 days during the year. Interpret.

n ^p=25∗ ( 2512 )=12>5∧n ( 1− ^p) =25(1− 1225 )=13>5

^p ± z α /2
√^p (1− ^p )
n

^p ± z 0.025
√ ^p (1− ^p )
n
12
^p= =0.48
25

0.48 ± 1.96
√ 0.48(0.52)
25
LCL=0.2841
UCL=0.6758
 We are 95% confident that the range [0.2841, 0.6758] contains the population proportion of
workers who were absent for more than 10 days.

3. Suppose that the personnel director also wishes to take a survey in a branch office. What
sample size is needed to have 95% confidence in estimating the population mean
absenteeism to within ±1.5 days if the population standard deviation is estimated to be 4.5
days? (Assume that the population is normally distributed)
2 2
z 0.025 σ 1.96 ( 4.5 )
n=( ) =( ) =34.57 (round up¿35)
E 1.5

Problem 8 (interval estimate for a population mean)

The Human Relations Department of Electronics, Inc., would like to include a dental plan as part of
the benefits package. The question is: How much does a typical employee and his or her family spend
per year on dental expenses? A sample of 45 employees reveals the mean amount spent last year
was $1,820, with a standard deviation of $660.

1. What are the population, the variable of interest and the parameter(s)?
Population: Employees of Electronics, Inc
Variable of interest: dental expenses of employees and their family
Parameter: Mean dental expenses per family

2. Construct a 95 percent confidence interval for the population mean.

As n>30,we may use the below formula
s
x ± t 44 ,0.025
√n
660
1820 ± 2.021
√ 45

LCL=1621.16
UCL=2018.84
We are 95% confident, that the range [1621.16, 2018.84] contains the true population mean
dental expenses per family.
 3. The information from part (2) was given to the president of Electronics, Inc. He indicated he
could afford $1,700 of dental expenses per employee. Is it possible that the population mean
could be $1,700? Justify your answer.
Yes, as the confidence interval built in question 2 contains the value $1700.

Problem 9 (interval estimate for a population mean, population proportion)

The branch manager of an outlet of a nationwide chain of pet supply stores wants to study
characteristics of her customers. In particular, she decides to focus on two variables: the amount of
money spent by customers and whether the customers own a cat. The results from a sample of 70
customers are as follows:

 Amount of money spent: X̄ =$ 21. 34 and s=$ 9 .22

 26 customers own a cat.
1. Construct a 95% confidence interval estimate for the population mean amount spent in the pet
supply store.
s
As n>30, we can use the formula: x ± t 69 ,0.025
√n
9.22
21.34 ± 2.000
√70
LCL=19.13
UCL=23.54
We are 95% confident, that the range [19.13 , 23.54] contains the true population mean
amount of money spent in the pet store

2. The manger concluded that 95% of his customers spend an amount of money between the two
limits of the obtained interval in question 1. How would you respond to this statement?
The statement is wrong as the interval built in the previous question provides a range of
possible values for the population mean amount of money spent in the store and not a range
a possible values for the population’s observations.

3. Construct a 90% confidence interval estimate for the population proportion of customers
who own only a cat.
26
^p= =0.37
70

We need to check that n ^p >5∧n ( 1−^p ) >5

 ^p ± z α /2
√ ^p (1− ^p )
n

^p ± z 0.05
√ ^p (1− ^p )
n

0.37 ± 1.645
√ 0.37 (0.63)
70

LCL=0.275
UCL=0.465
We are 90% confident that the range [0.275, 0.465] contains the population proportion of
customers who only own a cat.

4. Why are the interval estimates obtained in the questions 1 and 2 preferred over point estimates

( X̄ and ^p) to estimate the population mean and the population proportion?
With a point estimation, we do not have any knowledge about the accuracy of our
estimation. As an interval estimation gives a range of possible values for the population
parameter, the width of the confidence interval informs about the accuracy of the
estimation.

Problem 10 (interval estimate for a population mean)

One of the major measures of the quality of service provided by any organization is the speed with
which it responds to customer complaints. A large family-held department store selling furniture and
flooring, including carpet, had undergone a major expansion in the past several years. In particular,
the flooring department had expanded from 2 installation crews to an installation supervisor, a
measurer, and 15 installation crews. The store had the business objective of improving its response
to complaints. The variable of interest was defined as the number of days between when the
complaint was made and when it was resolved. Data were collected from a sample of 50 complaints
that were made in the last year. The sample mean and sample standard deviation are respectively
equal to 43.04 and 41.93, see table 1.

Table 1: One-Sample Statistics

Std. Error
N Mean Std. Deviation Mean

Number of days 50 43,0400 41,92606 5,92924

 1. What are the population and the parameter(s) of interest in this case?

Population: Customers who deposited complaints

Parameter: Mean number of days to resolve the complaint.

2. What is (are) the point estimate(s) of the parameter(s) defined in question #1?

Point estimate: 43.04

3. Construct a 99% confidence interval estimate for the population mean number of days
between the receipt of a complaint and the resolution of the complaint.

s
x ± t 49 ,0.005
√n
43.04 ±2.704 (5,92924)
LCL=27.026
UCL=59.054

4. Construct a 95% confidence interval estimate for the population mean number of days
between the receipt of a complaint and the resolution of the complaint.

s
x ± t 49 ,0.025
√n
43.04 ±2.021 (5,92924)
LCL=31.057
UCL=55.023

Problem 11 ( Interval estimate for a population proportion)

A random sample of 40 television viewers was asked if they had watched the current week’s Lost
episode. The following data represent their responses:
 1. Calculate the proportion of viewers in the sample who indicated they watched the current
week’s episode of Lost.
6
^p= =0.15 (this is a point estimate)
40

2. Compute a 95% confidence interval for the proportion of viewers in the population who
watched the current week’s episode of Lost.

^p ± z α /2
√^p (1− ^p )
n

^p ± z 0.025
√ ^p (1− ^p )
n

0.15 ± 1.96
√ 0.15(0.85)
40
LCL=0.039
UCL=0.26

3. State and Check the conditions needed to perform the confidence interval in question 2.

We need to check that n ^p=40 ( 0.15 )=6>5∧n (1−^p )=40 ( 0.85 )=34 >5

4. Interpret the interval you found in question 2.

We are 95% confident that the interval [0.039, 0.26] contains the true proportion of TV viewers who
watched the last episode of lost.

Problem 12 ( Interval estimate for a population proportion)

A random sample of 441 shoppers revealed that 76% made at least one purchase at a discount store
last month.

1. What are the population, the variable and the parameter of interest in this case?
Population: shoppers
Variable: Whether a purchase was made at a discount store last month (Yes or No)
Parameter: proportion of shoppers who made purchases at a discount store last month

2. Based on this sample information, what is the 95% confidence interval for the population
proportion of shoppers who made at least one discount store purchase last month?
 We need to check that n ^p=441∗0.76>5∧n (1−^p )=441∗0.24 >5

^p ± z α /2
√ ^p (1− ^p )
n

^p ± z 0.025
√ ^p (1− ^p )
n

0.76 ± 1.96
√ 0.76 (0.24)
441
LCL=0.72; UCL=0.80

Problem 13 ( Interval estimate for a population variance)

A manufacturer is concerned about the variability of the levels of impurity contained in

consignements of raw material from a supplier. A random sample of 15 consignments showed a
standard deviation of 2.36 in the concentration of impurity levels. Assume normality.

1. Find a 95% confidence interval for the population variance.

2 2
s =2.36
n=15
2 2 2 2
1−α=0.95 so χ n−1 , α = χ 14 ,0.025=26.119 and χ n−1 , 1− α = χ 14 ,0.975=5.629
2 2
2
(n−1)s (14)(5.57)
LCL= =
χ2 α 26.119 =2.98
n−1 ,
2

(n−1)s 2 (14)(5.57)
UCL= 2 = =13.85
χ α 5.629
n−1 ,1−
2
(We can use the formula as the population is normally distributed)

2. Would a 99% confidence interval for this variance be wider or narrower than that found in
question #1?

As the confidence level increases, the interval becomes wider.

Problem 14 (Finite populations, mean and total)

A firm employs 189 junior accountants. In a random sample of 50 of these, the mean number of
hours overtime billed in a particular week was 9.7, and the sample standard deviation was 6.2 hours.
a. Find a 95% confidence interval for the mean number of hours overtime billed per junior
accountant in this firm that week.

Here the sample size is big compared to the population size as n/N=50/189=0.26>0.05. As n>30, We
need to use the formula:
 X ±tα
2
, n−1 √
s
√n
N −n
N −1

X ± t 0.025, 49
√
s
√n
N −n
N −1
9.7 ± 2.021
6.2
√ 50√ 189−50
189−1

LCL=8.18
UCL=11.22

b. Find a 99% confidence interval for the total number of hours overtime billed by junior accountants
in the firm during the week of interest.
We need to estimate the total of the population, so we use the formula:
N X ±N tα
2
s N−n
,n−1 √ n N−1 √
N X ± N t 0.005 ,49
s N−n
√ n N−1 √
189∗9.7 ± 189∗2.704
6.2 189−50
√ 50 189−1 √
LCL=1448
UCL=2218.6

Problem 15 (Finite populations, proportion)

An accounting firm has 1200 clients. From a random sample of 120 clients, 110 indicated very high
satisfaction with the firm’s service. Find a 95% confidence interval for the proportion of all clients
who are very highly satisfied with this firm.

As the sample size is big compared to the population size (n/N=120/1200=0.10>0.05), we need to use
the formula:

^p ± z α /2
√ n √
^p (1− ^p ) N−n
N−1
^p=0.92∧z α / 2=1.96 (we check that n ^p >5∧n ( 1−^p ) >5 )

0.92 ±1.96
√ 120 √
0.92(0.08) 1200−120
1200−1

LCL=0.87
UCL=0.97

Problem 16 (Finite populations, total)

A class has 420 students. The final examination is optional—taking it can raise, but cannot lower, a
student’s grade. Of a random sample of 80 students, 31 said that they would take the final
examination. Find a 90% confidence interval for the total number of students in this class intending
to take the final examination.
We are estimating a total of a finite population and the sample size is big compared to the population
size as n/N=80/420=0.19>0.05

N ^p ± N z α / 2
√ n √
^p (1− ^p ) N −n
N −1

31
^p= =0.39; N =420 ; z α / 2=z 0.05=1.645 and n=80
80
LCL=130
UCL=198