Because learning changes everything.

Chapter 3
Describing Data: Numerical Measures

© McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.
 Learning Objectives
LO3-1 Compute and interpret the mean, the median, and the
mode.
LO3-2 Compute a weighted mean.
LO3-3 Compute and interpret the geometric mean.
LO3-4 Compute and interpret the range, variance, and
standard deviation.
LO3-5 Explain and apply Chebyshev’s theorem and the
Empirical Rule.

© McGraw Hill LLC 2

 Measures of Location
A measure of location is a value used to describe the central
tendency of a set of data.
Common measures of location.
• Mean.
• Median.
• Mode.
The arithmetic mean is the most widely reported measure of
location.
The mean is both a population parameter and sample
statistic.

© McGraw Hill LLC 3

 Population Mean 1

Many studies involve all the individuals in a population.

When the values are not summarized in a frequency distribution, =
 x
N
•  is the mean.
• N is the number of values in the population.
• x is any particular value.

•  is “sigma” and indicates the operation is adding.

•  x is the sum of the values.
Parameter A characteristic of a population.
The mean,  , of a population is a parameter.

© McGraw Hill LLC 4

 Population Mean 2

• Example: There are 46 exits on I-75 through the state of

Kentucky, here are the distances between exits (in miles).
11 4 10 4 9 3 8 10 3 14 1 6
4 3 5 2 2 5 4 2 3 2 5 5
1 1 2 7 8 10 2 3 7 5 4 3
2 1 1 2 1 1 2 1 2 1

• Why is this information a population?

• What is the mean number of miles between exits?

© McGraw Hill LLC 5

 Population Mean 3

• Example continued
11 4 10 4 9 3 8 10 3 14 1 6
4 3 5 2 2 5 4 2 3 2 5 5
1 1 2 7 8 10 2 3 7 5 4 3
2 1 1 2 1 1 2 1 2 1

• This is a population because we are considering all the

exits on I-75 and the distances between them

σ 𝑥 11 + 4 + 10+. . . +1 192
• 𝜇= = = = 4.17 miles
𝑁 46 46

© McGraw Hill LLC 6

 Sample Mean 1

We select a sample from the population to estimate a specific

characteristic.

The sample mean is x=

 x
n
• x is read "X bar"
• n is the number of values in the sample.
• x is any particular value.

•  is “sigma” and indicates the operation is adding.

•  x is the sum of the values.
Statistic A characteristic of a sample.
The sample mean is a statistic.

© McGraw Hill LLC 7

 Sample Mean 2

Example: The number of hours per day that Verizon

customer use their mobile phones.

4.1 3.7 4.3 4.2 5.5 51

4.2 5.1 4.2 4.6 5.2 3.8

What is the arithmetic mean number of hours per day used?

σ 𝑥 4.7 + 3.7+. . . +3.8 54.0

• 𝑥ҧ = = = = 4.5 hours
𝑛 12 12

© McGraw Hill LLC 8

 The Mean
• Interval or ratio scale of measurement is required.
• All the data values are used in the calculation.
• The mean is unique.
• The sum of the deviations from the mean equals zero.
• A weakness of the mean is that it is affected by extreme
values (large or small).

Access the text alternative for slide images.

© McGraw Hill LLC 9

 The Median 1

• For data containing extreme values, the mean may not

fairly represent the central location.
Median The midpoint of the values after they have been
ordered from the minimum to the maximum values.
• Example: The median price of housing units.

Price Ordered from Price Ordered from

Minimum to Maximum Maximum to Minimum
$60,000 $275,000
65,000 80,000
70,000 ← Median → 70,000
80,000 65,000
275,000 60,000
© McGraw Hill LLC 10
 The Median 2

• The median is the value in the middle of a set of ordered

data.
• At least the ordinal scale of measurement is required.
• It is not influenced by extreme values.
• Fifty percent of the observations are larger than the
median.
• Fifty percent of the observations are smaller than the
median.
• It is unique to a set of data.

© McGraw Hill LLC 11

 The Median 3

Odd numbered data: The median is the middle value

Even numbered data: The median is the average of the two
middle values.
Example: The number of hours a sample of 10 adults used
Facebook last month.
• Unsorted data: 3 5 7 5 9 1 3 9 17 10
• Sorted data: 1 3 3 5 5 7 9 9 10 17
• The median is 6

© McGraw Hill LLC 12

 The Mode
MODE The value of the observation that occurs most
frequently.
• The mode can be found for nominal level data.
• A set of data can have more than one mode.
• A set of data could have no mode.
• Example: The number of respondents that favor bath oils.

Access the text alternative for slide images.

© McGraw Hill LLC 13

 Relative Positions of Mean, Median, and
Mode

Access the text alternative for slide images.

© McGraw Hill LLC 14

 The Weighted Mean 1

The weighted mean is found by multiplying each observation by its

corresponding weight.
A convenient way to compute the mean when there are several
observations with the same value.
(𝑤1 𝑥1 ) + (𝑤2 𝑥2 )+. . . +(𝑤𝑛 𝑥𝑛 ) σ 𝑤𝑥
𝑥lj 𝑤 = =
𝑤1 + 𝑤2 +. . . +𝑤𝑛 σ𝑤

• xw is read "  bar sub w"

• x1 , x2 ,..., xn is the set of numbers

• w1 , w2 ,..., wn are the corresponding weights
The denominator is always the sum of the weights.

© McGraw Hill LLC 15

 The Weighted Mean 2

• Example: The Carter Construction Company pays its

hourly employees $16.50, $19.00, or $25.00 per hour.
• There are 26 hourly employees: 14 are paid at the $16.50
rate, 10 at the $19.00 rate, and 2 at the $25.00 rate.
• What is the mean hourly rate paid for the 26 employees?
14 $16.50 + 10 $19.00 + 2 $25
𝑥lj 𝑤 =
14 + 10 + 2

$471.00
= = $18.1154
26

© McGraw Hill LLC 16

 The Geometric Mean 1

• The geometric mean is useful in finding average rates of

change over time.
• The rates can be expressed as percentages (or ratios).
• A percentage change is always 1.0 + change
• Wide applications in business and economics (example
GDP).
• The geometric mean will always be no more than the
arithmetic mean.
• The data values must be positive.
𝑛
• 𝐺𝑀 = 1 + 𝑥1 1 + 𝑥2 . . . 1 + 𝑥𝑛 − 1

© McGraw Hill LLC 17

 The Geometric Mean 2

• Example: The RIO earned by a company for four

consecutive years: 30%, 20%, −40% and 200%.
4
• 𝐺𝑀 = 1.30 1.20 0.60 3.00 − 1

= 1.294 − 1 = 0.294

• The RIO is 29.4%.

• Note if you compute the arithmetic mean it would be
52.5%.
• This would overstate the true rate of return.

© McGraw Hill LLC 18

 The Geometric Mean 3

• A second application of the geometric mean is based on

the beginning and ending values over a specified time
period.

• 𝑛 Value at end of period

GM = −1
Value at start of period

• Example: You earned $45,000 in 2010 and $100,000 in

2022.
• 12 $100,000
𝐺𝑀 = − 1 = 1.0688 − 1 = 6.88%
$45,000

© McGraw Hill LLC 19

 Why Study Dispersion? 1

Measures of location only describe the center.

Do not describe the spread or variation.
The dispersion is the variation or spread in a set of data.
Study dispersion to compare the spread in two or more
distributions.
Measures of dispersion include.
• Range.
• Variance.
• Standard Deviation.

© McGraw Hill LLC 20

 Why Study Dispersion? 2

• Example: Hourly production at two computer monitor

plants.

Access the text alternative for slide images.

© McGraw Hill LLC 21

 Range
The simplest measure of dispersion is range.
Range = Maximum value − Minimum value.
• Only two values are used in its calculation.
• It is influenced by extreme values.
• It is easy to compute and to understand.

Example: Hourly production at two

computer monitor plants.
• Baton Rouge: 52 − 48 = 4.
• Tucson: 60 − 40 = 20.

Access the text alternative for slide images.

© McGraw Hill LLC 22

 Population Variance 1

The range is based on only two numbers.

The variance measures how much the values vary from their mean.
• The mean squared deviation from the mean.
• Units are the units of measurement squared.

( x −  )
2

2 =
N
•  2 is lower case Greek “sigma squared”.
• X is the value of a particular observation.

•  is the population mean.

• N is number of observations in the population.

© McGraw Hill LLC 23

 Population Variance 2

The process for computing the mean is implied by the

formula.
1. Begin by finding the mean.
2. Find the difference between each observation and the
mean, square that difference.
3. Sum all the squared differences.
4. Divide the sum of the squared differences by the number
of items in the population.

© McGraw Hill LLC 24

 Population Variance 3

• Example: The number of traffic citations.

Citations by Month
January February March April May June July August September October November December
19 17 22 18 28 34 45 39 38 44 34 10

• =  x 19 + 17 + ... + 10 348
= = = 29
N 12 12

© McGraw Hill LLC 25

 Population Variance 4

Citations

( x −  )
2
1, 488 Month (x) (x−μ) (x−μ)2
• 2 = = = 124 January 19 −10 100
N 12
February 17 −12 144
• Units are citations squared!
March 22 −7 49

April 18 −11 121

May 28
In the following −1
table, 1
read ‘(x − μ)’ as x minus
mu and (x − μ)2 as open
June paren x34 5
minus mu close 25
paren squared.
August 39 10 100

September 38 9 81

October 44 15 225

November 34 5 25

December 10 −19 361

Total 348 0 1,488

© McGraw Hill LLC 26

 Standard Deviation
The units of the variance is the units of measure squared.
The variance is difficult to interpret.
The standard deviation is the square root of the variance.

( x −  )
2

=
N
Example: The number of traffic citations.
• The variance is 124 citations 2
• The standard deviation is 11.14 citations.

© McGraw Hill LLC 27

 Sample Variance and Standard Deviation 1

The sample variance and standard deviation uses the sample.

mean, x=
 x
n

 (x − x) ( x − x )
2 2

s 2
= and s =
n −1 n −1
• Using n in the denominator tends to underestimate the
population variance.
• Using n − 1 provides an appropriate correction.
The units of the variance is the units of measurement
squared.

© McGraw Hill LLC 28

 Sample Variance and Standard Deviation 2

• Example: The hourly wages for part-time employees are $12, $20,
$16, $18 and $19.
• x=
 x $85
= = $17
n 5
Hourly Wage (x) x − X̅ (x − X̅)2
$12 −$5 25
In the following table, read ‘x − x¯’ as x
minus20 3 as open paren9
x bar and (x − x¯)2
x minus
16x bar close paren−1 squared. 1
18 1 1
19 2 4
$85 0 40

( x − x )
2
• 40
s =
2
= = 10 dollars squared
n −1 5 −1
• 𝑠 = 3.16 dollars.

© McGraw Hill LLC 29

 Interpretations and Uses of the Standard
Deviation 1

The standard deviation is to compare the spread of two or more sets of

observations.
• Small: The values are close to the mean.
• Large: The values are widely scattered about the mean.
Chebyshev’s theorem defines the dispersion of data around the mean.
• For any set of observations, the proportion of values within 𝑘 standard deviations
1
is at least 1 − for k  1.
k2
1
• k = 2 then 1− = 0.75 at least 75% of the observation are within 2 standard
22
deviation of the mean.
1
• k = 3 then 1 − 2
= 0.889 at least 88.9% of the observation are within 3 standard
3
deviation of the mean.

© McGraw Hill LLC 30

 Interpretations and Uses of the Standard
Deviation 2

Example: Employees at a company contribute a mean of $51.54 to the

company profit-sharing plan every 2 weeks.
The standard deviation is $7.51.
At least what proportion of employees make a contribution within 3.5
standard deviations of the mean?
3.5 standard deviations of the mean is a range of values.
• 51.54 − 3.5×7.51 = $25.26
• 51.54 + 3.5×7.51 = $77.83
1
k = 3.5 then 1 − 2
= 0.92
3.5
At least 92% of the employees contribute between $25.26 and $77.83.

© McGraw Hill LLC 31

 Interpretations and Uses of the Standard
Deviation 3

Chebyshev’s theorem is for any set of values regardless of

the shape of the distribution.
If the data have a symmetrical and bell-shaped distribution,
we can be more precise without the “at least”.
The Empirical Rule or Normal Rule provides an
approximation.
• 1 standard deviation of the mean: about 68% of values.
• 2 standard deviations of the mean: about 95% of values.
• 3 standard deviations of the mean: about 99% of values.

© McGraw Hill LLC 32

 Interpretations and Uses of the Standard
Deviation 4

• Example: A mean of 100 and a standard deviation of 10.

Access the text alternative for slide images.

© McGraw Hill LLC 33

 Interpretations and Uses of the Standard
Deviation 5

• Example: Rental rates are approximately symmetric and

bell shaped. The mean is $500 and the standard deviation
is $20.
• About 68%: 500 ± 1×20 = $480 to $520.
• About 95%: 500 ± 2×20 = $460 to $540.
• About 99%: 500 ± 3×20 = $440 to $560.

© McGraw Hill LLC 34

 Ethics and Reporting Results
• Useful to know the advantages and disadvantages of
mean, median, and mode as we report statistics and as we
use statistics to make decisions.
• Similarly for measures of dispersion.
• Important to maintain an independent and principled point
of view.
• Statistical reporting requires objective and honest
communication of any results.

© McGraw Hill LLC 35

 Chapter 3 Practice Problems

© McGraw Hill LLC 36

 Question 19 LO3-1

The accounting firm of Rowatti and Koppel specializes in

income tax returns for self-employed professionals, such as
physicians, dentists, architects, and lawyers. The firm
employs 11 accountants who prepare the returns. For last
year, the number of returns prepared by each accountant
was:
58 75 31 58 46 65 60 71 45 58 80

Find the mean, median, and mode for the number of returns
prepared by each accountant. If you could report only one,
which measure of location would you recommend reporting?

© McGraw Hill LLC 37

 Question 25 LO3-2

The Loris Healthcare System employs 200 persons on the

nursing staff. Fifty are nurse’s aides, 50 are practical nurses,
and 100 are registered nurses. Nurse’s aides receive $12 an
hour, practical nurses $20 an hour, and registered nurses
$29 an hour. What is the weighted mean hourly wage?

© McGraw Hill LLC 38

 Question 27 LO3-3

Compute the geometric mean of the following monthly

percent increases: 8, 12, 14, 26, and 5.

© McGraw Hill LLC 39

 Question 35 LO3-3

In 2010 there were 232.2 million cell phone subscribers in

the United States. By 2020 the number of subscribers
increased to 276.7 million.
a. What is the geometric mean annual percent increase for
the period?
b. Further, the number of subscribers is forecast to
increase to 276.7 million by 2020.
c. What is the rate of increase from 2010 to 2020?
d. Is the rate of increase expected to slow?

© McGraw Hill LLC 40

 Question 39 LO3-1,4

Dave’s Automatic Door installs automatic garage door

openers. The following list indicates the number of minutes
needed to install 10 door openers: 28, 32, 24, 46, 44, 40, 54,
38, 32, and 42.
Calculate the following:
a. Range
b. Mean
c. Variance

© McGraw Hill LLC 41

 Question 47 LO3-1,4

Plywood Inc. reported these returns on stockholder equity for

the past 5 years: 4.3, 4.9, 7.2, 6.7, and 11.6. Consider these
as population values.
Compute the following:
a. Range.
b. Arithmetic mean.
c. Variance.
d. Standard deviation.

© McGraw Hill LLC 42

 Question 51 LO3-4

Dave’s Automatic Door installs automatic garage door

openers. Based on a sample, following are the times, in
minutes, required to install 10 door openers: 28, 32, 24, 46,
44, 40, 54, 38, 32, and 42.
a. Compute the sample variance.
b. Determine the sample standard deviation.

© McGraw Hill LLC 43

 Question 55 LO3-5

According to Chebyshev’s theorem, at least what percent of

any set of observations will be within 1.8 standard deviations
of the mean?

© McGraw Hill LLC 44

 Question 57 LO3-5

The distribution of the weights of a sample of 1,400 cargo

containers is symmetric and bell-shaped. According to the
Empirical Rule, what percent of the weights will lie:

• Between x − 2s and x + 2s ?
• Between x and x + 2s ? Above x + 2s ?

© McGraw Hill LLC 45

 Because learning changes everything. ®

www.mheducation.com

© McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.