AIUB

Master of Business Administration

Course Instructor: Dr. Swapan Kumar Dhar

Estimation
Estimation: The method to estimate the value of a population parameter from the sample.
Estimation of parameter takes two forms: (i) Point Estimation and (ii) Interval estimation.
A point estimate is a single value (point) derived from a sample and used to estimate a population
value.
A confidence interval estimate is a range of values constructed from sample data so that the
population parameter is likely to occur within that range at a specified probability. The specified
probability is called the level of confidence.
Example: The American Management Association wishes to have information on the mean income of
middle managers in the retail industry. A random sample of 256 managers reveals a sample of mean
of $45,420. The standard deviation of this sample is $2,050. The association would like answers to
the following questions:
(a) What is the population mean?
(b) What is the reasonable range of values for the population mean?
(c) What do these results mean?
Solution:
(a) In this case, we do not know the population mean? But we do know only the sample mean which
is $45420. Hence our best estimate of the unknown population value is the corresponding sample
statistic. Thus the sample mean of $45420 is an estimate of the unknown population mean. This is a
point estimate of the population mean.
(b) The association decides to use the 95% level of confidence. Here the level of confidence
describes how confident we are that the population parameter is in the interval by making a probability
statement. To determine the corresponding confidence interval we use the following formula

X Z

s
2050
45420 1.96
45420 251
n
256

That is from 45169 to 45671. These endpoints are called the confidence limits. The degree of confidence or the level
of confidence is 95% and the confidence interval is from 45169 to 45671.
(c) Suppose we select many samples of 256 managers, perhaps several hundred. For each sample, we compute the
mean and the standard deviation and then construct a 95 % confidence interval. We could expect about 95 percent of
these confidence intervals to contain the population mean. About 5 percent of the intervals would not contain the
population mean.
Selected Confidence Levels and Corresponding Values of
Confidence Level

90%
0.10
1.645

95%
0.05
1.96

98%
0.02
2.33

99%
0.01
2.58

Example: The mean daily sales at the Bun-and-Run, a fast food outlet, is $20,000 for a sample of 40 days. The
standard deviation of the sample is $3.000.
What is the population mean?
What is the estimated mean daily sales of the population? What is this estimate called?
What is the 99 percent confidence interval?
Interpret your findings.
Solution: (a) Population mean is unknown. This is the true value we want to estimate.
(b) The estimated daily sale is $20,000. This estimate is called point estimate.
(c)

$20,000 2.58

$3,000
40

$20,000 $1.224 ($18,776,$21,224).

(d) About 99% of the intervals similarly constructed would include the population mean.
Example: A sample of 49 observations is, taken from a normal population. The sample mean is 55, and the sample
standard deviation is 10. Determine the 99 percent confidence interval for the population mean.
Solution:

55 2.58

10
49

55 3.686 (51.314,58.686).

Example. A sample of 81 observations is taken from a normal population. The sample mean is 40, and the sample
standard deviation is 10. Determine the 95 percent confidence interval for the population mean.
Solution:

40 1.96

Usually a sample size n

5
81

40 1.089 (38.911, 41.089).

30 is considered to be a large sample.

Confidence Interval Estimates for the Mean:

Characteristics

C.I.

Population variance or S.D. known irrespective of

sample size

X Z

n
n

s
X Z
s
n , where
s
X t
n

Population variance or S.D. known & n 30

Population variance or S.D. unknown & n 30

(Xi X)

i1

n1

Example: A sample of 10 observations is selected from a normal population for which the population standard
deviation is known to be 5. The sample mean is 20.
Determine the standard error of the mean.
Determine the 95 percent confidence interval for the population mean.
Solution:
(a) We know the standard error of the mean =

5
10

1.581.

5
20 1.96
20 3.099 (16.901,23.099).
n
10
Example: Average January temperature (in F 0 ) of a city for the last 40 years are given in the
(b)

X Z

following table.
52.8
48.5
54.0
52.3

52.2
52.3
51.9
54.9

52.7
51.6
50.4
52.1

53.8
43.7
50.7
54.6

54.5
49.7
54.0

48.5
49.9
52.4

53.3
52.6
51.5

52.4
51.2
48.4

51.7
50.7
46.7

43.2
54.2
53.0

51.4
48.7
51.4

42.8
56.0
49.6

(a) Identify the population, sample and variable.

(b) What is the point estimate?
(c) Find the 95% confidence interval for the mean January average temperature.
Solution:
(a) For the above data set, we identify the following:
Population: January temperature of that city.
Sample: Collection of January temperature for the last 40 years.
Variable: Average temperature during the month of January ( this average might have been taken
over hourly, daily or weekly values throughout the month).
(b) The point estimate is the sample mean which is 51.16 F 0 .
(c) Here since it is a large sample, the confidence interval is :

X Z

s
.
n

The sample mean and sample standard deviation calculated from the data are 51.16 and 3.04 respectively.
So, we have X 51.16 and s 3.04 .
C.I. =

51.16 1.96

3.04
40

( 50.22F 0, 52.10F 0 ) .

Unknown Population Standard Deviation and a Small Sample:

df

80%

90%

1
2
3
4
5
6
7
8
9
10

0.20
3.078
1.886
1.638
1.533
1.476
1.440
1.415
1.397
1.383
1.372

0.10
.6.314
2.920
2.353
2.132
2.015
1.943.
1.895
1.860
1.833
1.812

11
12
13
14
15
16

1.363
1.356
1.350
1.345
1.341
1.337

1.796
1.782
1.771
1.761
1.753
1.746

Confidence Intervals
95%

96%

99%

0.05
12.706
4.303
3.182
2.776
2.571
2.447
2.365
2.306
2,262
2.228

0.04
31.821
6.965
4.541
3.747
3.365
3.143
2.998
2.896
2.821
2.764

0.01
63.657
9.925
5.841
4.604
4.032
3.707
3.499
3.355
3.250
3.169

2.201
2.179
2.160
2.145
2.131
2.120

2.718
2.681
2.650
2.624
2.602
2.58.

3.106
3.055
3.012
2.977
2.947
2.921

Chart : A portion of the t table

The following example will illustrate a confidence interval for a population mean when the population standard
deviation is unknown and how to find the appropriate value of t in a table.
Example: A tyre manufacturer wishes to investigate the tread life of its tyres. A sample of 10 tyres driven
50,000 miles revealed a sample mean of 0.32 inch of tread remaining with a standard deviation of 0.09 inch.
Construct a 95 percent confidence interval for the population mean. Would it be reasonable for the
manufacturer to conclude that after 50,000 miles the population mean amount of tread remaining is 0.30
inches?
Solution: We do not know the population standard deviation, but we know the sample standard deviation,
which is .09 inches. Also n < 30.
In this case we will use the following formula relating to t distribution,

X t

s
0.09
0.32 2.262
0.32 0.64 . So confidence interval is (0.256, 0.384).
n
10

Interpretation: The manufacturer can be reasonably sure (95 percent confident) that the mean remaining
tread depth is between 0.256 and 0.384 inches.
Example: The manager of a Super shop wants to estimate the mean amount spent per shopping visit by
customers. A sample of 20 customers reveals the following amounts(in $) spent.
48.16
61.83

42.22
61.69

46.82
49.17

51.45
61.46

23.78
51.35

41.86
52.68

54.86
58.84

37.92
43.88

52.64

48.59

50.82

46.94

What is the best estimate of the population mean? Determine a 95 percent confidence interval. Interpret the
result. Would it be reasonable to conclude that the population mean is $50? What about $60?
Solution: The mall manager assumes that the population of the amounts spent follows the normal
distribution. This-is a reasonable assumption in this case. The population standard deviation is not known
and the size of the sample is less than 30. Hence, it is appropriate to use the t distribution to find the
confidence interval.
The mall manager does not know the population mean. The sample mean is the best estimate of that value.
From the calculation it is found that, the mean is $49.35, which is the best estimate, the point estimate, of the
unknown population mean
We use confidence formula relating to t to find the confidence interval. The value of t is available from the
Table. The value is 2.093. We substitute these values into formula to find the confidence interval.

s
9.01
49.35 2.093
49.35 4.22
n
20
.

X t

The endpoints of the confidence interval are $45.13 and $53.57. It is reasonable to conclude that the
population mean is in that interval.
Example: A Telephone Company claims in its annual report that the typical customer spends $60 per month
on local and long distance service. A sample of 12 subscribers revealed the following amounts spent (in $)
last month.
64

66

64

66

59

62

67

61

64

58

54

66

What is the point estimate of the population mean?

Develop a 90% C.I. for the population mean.
Is the companys claim that the typical customer spends $60 per month reasonable? Justify your answer.
Solution:
Point estimate of the population mean is sample mean. Sample mean is $751/12 = $62.583.
Here we do not the population standard deviation. So we have to calculate sample standard deviation. The

( X)2
formula is
n , where X 62.583 . So s 3.94 .
s i1

n1
n1
s
3.94
62.583 1.796
($60.54,$64.63).
C.I. formula is X t
n
12
n

(Xi X)

2
X

(c) $60 is not reasonable, because this value is outside the confidence interval.
Example: Dr Hamid is an industrial psychologist. He is currently studying stress among executives of Internet
companies. He has developed a questionnaire that he believes measures stress. A score above 80 indicates
stress at a dangerous level. A random sample of 15 executives revealed the following stress level scores.
94

78

83

90

78

99

97

90

97

90

93

94

100

75

84

Find the mean stress level for this sample. What is the point estimate of the population mean?
Construct a 95% confidence level for the population mean.
Is it reasonable to conclude that Internet executives have a mean stress level in the dangerous level,
according to Dr Hamids test?
Solution:
(a) Sample mean = 1342/15 = 89.4667.
(b)Since we do not know population S.D. and moreover sample size is less than 30, we have to use C.I. as
C.I. = X

s
. Here we s is calculated as using the formula
n

(Xi X)

i1

n1

(94 78 ... 84)2

( X)2
942 782 ... 842
15
n
8.08
n1
15 1

2
X

.
So, C.I. = 89.4667 2.145

8.08
89.4667 4.4750 (84.99,93.94) .
15

(c) Yes, it is in the dangerous level, because even the lower limit of the C.I. is above 80.
0

Example: Average January temperature (in F ) of a city for the last 24 years are given in the following
table.
(a) Identify the population, variable.
(b) What is the point estimate?
(c) Find the 95% confidence interval for the mean January average temperature.
52.8
48.5

52.2
52.3

52.7
51.6

53.8
43.7

54.5
49.7

48.5
49.9

53.3
52.6

52.4
51.2

51.7
50.7

43.2
54.2

51.4
48.7

42.8
56.0

Solution: For the above data set, we identify the following:

Population: Collection of January temperature. Variable: Average temperature during the month of January
( this average might have been taken over hourly, daily or weekly values throughout the month).
(b) The point estimate is the sample mean which is 50.767 F 0 .
(c) Here since it is a small sample, the confidence interval is: X

s
.
n

The sample mean and sample standard deviation calculated from the data are 50.467 and 3.4659
respectively.
So, we have X 50.767 and s 3.4659 .
C.I. =

50.467 2.069

3.4659
24

( 49.303F 0, 52.230F 0 ) .

Example: A businesswoman is considering whether to open a coffee shop in a local shopping center.
Before making this decision, she wants to know how much money people spend per week at coffee
shops in that area. She took a random sample of 26 customers from the area who visit coffee shops
and asked them to record the amount of money (in dollars) they would spend during the next week at
coffee shops. At the end of the week, she obtained the following data (in dollars) from these 26
customers:
16.96

38.83

15.28

14.84

5.99

64.50

12.15

14.68

33.37

37.10

18.15

67.89

12.17
5.29

40.13
9.09

5.51

8.80

34.53

35.54

8.51

37.18

41.52

13.83

12.96

22.78

Assume that the distribution of weekly expenditures at coffee shops by all customers who visit coffee
shops in this area is approximately normal.
(a) What is the point estimate of the corresponding population mean?
(b) Make a 95% confidence interval for the average amount of money spent per week at coffee
shops by all customers who visit coffee shops in this area.
Solution: Here we have,

n 26, X 627.58,

(a) Point estimate of the population mean is

X 22,726.0034.
X 627.58
which is

$24.14.
n

(b) 95% confidence interval for the average amount is

n 1

X t

26

s
n

, where,

(627.58)2
26
$17.4099632.
26 1

22,726.0034

Here t value is 2.060 for degrees of freedom 25.

The 95% confidence interval is 24.14 2.060 3.414375 24.14 7.03 $17.11 to $31.17.
Example: The following data give the annual incomes (in thousands of dollars) before taxes for a
sample of 36 randomly selected families from a city:
21.6
33.0
25.6
37.9
50.0
148.1 50.1
21.5
70.0
72.8
58.2
85.4
91.2
57.0
72.2
45.0
95.0
27.8
92.8
79.4
45.3
76.0
48.6
69.3
40.6
69.0
75.5
57.5
49.7
75.1
96.3
44.5
84.0
43.0
61.7
126.0

Construct a 99% confidence interval for

assuming that the population standard deviation is $
23.75 thousand.
Example: The following data give the prices (in thousands of dollars) of 16 recently sold houses in an
area.
341
163
327
204
197
203
313
279
456
228
383
289
533
399
271
381
Construct a 99%confidence interval for the mean price of all houses in this area. Assume that the
distribution of prices of all houses in the given area is normal.

Example: The following data give the checking account balances (in dollars) on a certain day for a
randomly selected sample of 30 households:
500
100
650
1917
2200
500
180
3000
1500
1300
319
1500
1102
405
124
1000
134
2000
150
800
200
750
300
2300
40
1200
500
900
20
160
Construct a 95% confidence interval for
unknown.

assuming that the population standard deviation is

Example: A private bank, like most other large banks, found that using automatic teller machines
(ATM) reduces the cost of routine bank transactions. The bank installed an ATM inside the Campus 1.
The ATM is for the exclusive use of 1500 Business students. After several months of operation, a
sample of 100 students revealed the following use of the ATM machine by 1500 Business students in
a month.
No of times ATM used
Frequency

0
25

1
30

2
20

3
10

4
10

5
5

(a) How many transactions does the average student make per month?
(b) Develop a 95% confidence interval for the mean number of transactions per month?
(c) Is it possible that the population mean is 0.7? Explain.
Solution:
(a) 1.65 2 found by 165/100.
(b) C.I. =

x t

s
n

N n
1.4659 1500 100
= 1.65 1.984
= (1.369, 1.931).
N 1
1500 1
100

Note s = 1.4659.
(c) No, because 0 is not in the interval between 1.369 and 1.931.
Example: In an effort to estimate the mean amount spent per customer for dinner at Battala in JU, data were
collected for a sample of 49 customers. Assume population standard deviation of Taka 25.
At 95% confidence, what is the margin of error?
If the sample mean is Taka 150, what is the 95% C.I. for the population mean?
Solution:
(a) Margin of error =
(b) C.I. = 150

z
n

ME z

s
= 1.96 X 25/7 = 7
n

= 150 1.96 X 25/7 = (143, 157).

Choosing an Appropriate Sample Size:

A concern that usually arises when designing a statistical study is "How many items should be in the
sample?" If a sample is too large, money is wasted collecting the data. Similarly, if the sample is too small, the
resulting conclusions will be uncertain. The necessary sample size depends on three factors:
1. The level of confidence desired.
2. The margin of error the researcher will tolerate.
3. The variability in the population being studied.
The first factor is the level of confidence. The second factor is the allowable error. The third factor in
determining the size of a sample is the population standard deviation. If the population is widely dispersed, a
large sample is required.
We know that Margin of Error (M.E.) =

ME z

. Solving this equation, we get

n

z , which is the sample size for estimating the population mean.

ME

Where,
n = size of the sample
z = z value
ME = margin of error or maximum allowable error.
If the population standard deviation

is not known, the sample size

6

zs , where s = estimate of the population standard deviation.

ME

The result of this calculation is not always a whole number. When the outcome is not a whole number, the
usual practice is to round up any fractional result. For example, 201.22 would be rounded up to 202.
Example: A marketing researcher wants to find a 95% confidence interval for the mean amount that
visitors to a theme park spend per person per day. She knows that the standard deviation of the
amounts spent per person per day by all visitors to this park is $10. How large a sample should the
researcher select so that the estimate will be within $2 of the population mean?
Solution:
2

z 1.96 10

2
ME

96.04 96.

Example: A company that produces detergents wants to estimate the mean amount of detergent in
64-ounce jugs at a 99% confidence level. The company knows that the standard deviation of the
amounts of detergent in all such jugs is 0.20 ounce. How large a sample should the company select
so that the estimate is within .04 ounce of the population mean?
2

z 2.58 0.20

Solution: n

0.04
ME

166.41 166.

Example: A department store manager wants to estimate at a 95% confidence level the mean
amount spent by all customers at this store. The manager knows that the standard deviation of
amounts spent by all customers at this store is $31. What sample size should he choose so that the
estimate is within $3 of the population mean?
2

z 1.96 31
Solution: n

3
ME

410.20 420.

Example: A city planner wants to estimate, with a 95% confidence level, the average monthly
residential water usage in the city. Based on earlier data, the population standard deviation of the
monthly residential water usage in this city is 389.60 gallons. How large a sample should be selected
so that the estimate for the average monthly residential water usage in this city is within 100 gallons of
the population mean?
2

Solution:

z 1.96 389.60

100
ME

58.31 58.

Example: You are interested in estimating the mean commuting time from home to school for all
commuter students at your school. Briefly explain the procedure you will follow to conduct this study.
Collect the required data from a sample of 30 or more such students and then estimate the population
mean at a 95% confidence level. Assume that the population standard deviation for such times is 5.5
minutes.
Solution: To estimate , the mean commuting time at a 95% confidence level,
(a) Take a random sample of 30 or more such commuter students at your school.
(b) Determine the commuting time of each student.
(c) Find X , the mean of the sample.
(d) Calculate the 95% confidence interval for

using the formula X 1.96

.
n

Example: A population is estimated to have a standard deviation of 10. We want to estimate the population
mean within 2, with a 95 percent level of confidence. How large a sample is required?
Solution:
2

zs 1.96 10

2
ME

96.04 96.

Example: We want to estimate the population mean within 5, with a 99 percent level of confidence. The
population standard deviation is estimated to be 15. How large a sample is required?
Solution:
2

zs 2.58 15

5
ME

59.91 60.

Example: A survey is being planned to determine the mean amount of time corporation executives watch
television. A pilot survey indicated that the mean time per week is 12 hours, with a standard deviation of 3
hours. It is desired to estimate the mean viewing time within one-quarter hour. The 95 percent level of
confidence is to be used. How many executives should be surveyed?
Solution:
2

1.96 3
n
553.19 553.
0.25
Example: A student of MBA conducted a study and reported that the 95% confidence interval for the mean
ranged from 46 to 54. He was sure that the mean of the sample was 50, that the standard deviation of the
sample was 16 and that the sample size was at least 30, but could not remember the exact number. Can you
help him out?
Solution: We know that M.E. for this problem is defined as M.E. = Z

s
n

s
is the confidence interval, where
n
s
s
s
X Z
46 and X Z
54 . Solving these two equations we get Z
4.
n
n
n

Also we know that

X Z

zs 1.96 16

That is M.E. = 4. Hence, n

4
ME

61.4656 61.

Example: You are to conduct a sample survey to determine the mean family income in a rural area. The
question is, how many families should be sample? In a pilot survey of 10 families, the standard deviation was
found as Taka 500. The sponsor of the survey wants you to use the 95% confidence level. The estimate is to
be within Taka 100. How many families should be interviewed?
Solution:
2

zs 1.96 500

100
ME

96.04 96.

Chapter Outline:
A point estimate is a single value (statistic) used to estimate a population value (parameter).
A confidence Interval is a range of values within which the population parameter is expected to occur.
1. The factors that determine the width of a confidence Interval for a mean are the number of observations in
the sample, n.
2. The variability in the population, usually estimated by the sample standard deviation, s.
3. The level of confidence.
a. To determine the confidence limits when the population standard deviation is known or the sample is 30 or
more, we use the z distribution. The formula is

X z

s
n

b. To determine the confidence limits when the population standard deviation is unknown and the sample is
less than 30, we use the t distribution. The formula is

X t

s
n

4. We can determine an appropriate sample size for estimating mean. A. There are three factors that
determine the sample size when we wish to estimate the mean.
1. The desired level of confidence, which is usually expressed by z.
2. The maximum allowable error,
3. The variation in the population, expressed by s.
4. The formula to determine the sample size for the mean is

zs

ME