Chapter 3

Descriptive
Measures

1
Some Basic Measurements
•Measures of Central Location
•Measures of Variability
•Fractiles
Measures of Central
Location
Measure of Central Location

• It is the most common way of

describing a set of observations
•summarizes a set of observations
into a single value
What are the
different measures
of central location?
Measures of Central Location
•Arithmetic mean
(or mean)
•Median
•Mode
 Measure of Central Location: MEAN

MEAN
•the most popular measure of central
tendency

��� �� �ℎ� ���� ������

•
������ �� ���� ������ �ℎ�� ���� ������
 Measure of Central Location: MEAN

MEAN
If a set of data is represented by the notation �1 , �2 ,…,
�� , not necessarily distinct, then the mean is
computed using this formula:

•Population Mean
N

x i
 i 1
N
These sample observations, which will be written in
mathematical notation as �1 , �2 ,…, �� is computed
using this formula:

•Sample Mean
n

x i
x i 1

9
 Measure of Central Location: MEAN

The weights of each of the � distinct observation is

denoted by �1 , �2 ,…, �� is computed by using this
formula:

• Weighted Mean
k

w x i i
X i 1
k

w
i 1
i
 Example 1 (from stat manual)

The student ’s final grades are as

given: Subject Grade Unit
Math 17 2.00 6
Philo 1 2.25 3
Eng 1 1.75 3
Bio 1 2.00 4

D ete r m i n e t h e st u d e nt ’s G PA o r
weighted average grade.
Properties of the Mean
1. The sum of the deviations of the observations from the
mean is always equal to zero, that is, �
�=1
�� − � = 0 or
�
�=1
�� − � = 0.
2. The sum of the squared deviations of the observations
� 2
from a point �, �=1 �� − � , is minimum when � = � or
� = �, for sample observations.
3. The mean reflects the magnitude of every observation
since every observation contributes to the value of the
mean.
4. It is easily affected by the presence of extreme values, and
hence not a good measure of central tendency when 12
extreme observations occur.
 Measure of Central Location: MEDIAN

MEDIAN
•m i d d l e v a l u e o f a s e t o f
observations arranged in an
increasing or decreasing order of
magnitude
 Measure of Central Location: MEDIAN

MEDIAN
•Population median

•Sample median
Note
If the original set of observations is
denoted by �1 , �2 ,…, �� , the ������� set
of observations is denoted by � 1 , � 2 ,…,
� � , where � 1 ≤ � 2 ≤,…, ≤ � � .

15
Properties of the Median
1.It is a positional value and unlike the mean, it is not
affected by the presence of extreme values. When
abnormal values or outliers are present. It is
preferable to use the median rather than the mean
as a measure of central location.
2.The sum of the absolute deviations of the
observations from a point, say �, is smallest when
� = median.
3.It is an appropriate measure for data which are at
least in the ordinal scale.
16
 Measure of Central Location: MODE

MODE
•value or values which occur the
most number of times
Note:
If observations occur with equal frequency then there is no
modal value for the data set.
Properties of the Mode
1.The mode is determined by the frequency
and not by the values of the observations.
2.The mode may be defined for qualitative or
quantitative variables.
3.It is an appropriate measure even for a
nominal type of data.

18
 Example 2
The following data shows
the family sizes of 9 families:
2, 3, 5, 5, 4, 3, 2, 1, 5. Find
the following:
1. Mean
2. Median
3. Mode
Measures of
Variability
 Measure of Variability

Measures of Variability
• measures how the data spreads from
the central location
• the lesser the measure is, the closer the
values of the observations from the
central value
What are the
different
measures of
dispersion?
 Measure of Variability

Measures of Variability

•Range
•Variance
•Standard Deviation
•Coefficient of Variation
RANGE
• Is the simplest to understand and easy to
compute.
• The range of a set of observations is the
difference between the largest and the
smallest values in the set. It is denoted by �.

� = ���ℎ��� ����� − ������ �����

24
 Measure of Variability: VARIANCE

VARIANCE
Given the finite population observations �1 , �2 ,…,
�� , the

•Population Variance
N 2
N
 ( xi   )
2 x
 i  N  2

 
2 i 1 alternatively  2i 1
N
N
•Sample Variance
n n n
2
 (x  x)
2
i
2
n  xi  (  xi )
2
2
s  i 1 s
alternatively  i 1 i 1

n 1 n( n  1)

26
 Measure of Variability: VARIANCE

Properties of the variance

1. The variance is always non-negative and
thus it can never be negative.
2. A large variance corresponds to a highly
dispersed set of values.
3. The variance makes use of all
observations.
4. Its unit of measure is the square of the
unit of measure of the given set of
values.
 Measure of Variability: STANDARD DEVIATION

STANDARD DEVIATION
•Population Standard Deviation

2
 
•Sample Standard Deviation
2
s s
 Measure of Variability: STANDARD DEVIATION

PROPERTIES OF THE STANDARD DEVIATION

The standard deviation has

the same properties as the
variance except the last one. Its
unit of measure is the same as
that of the observations in a set of
data.
 Measure of Variability: COEFFICIENT OF VARIATION

COEFFICIENT OF VARIATION
• denoted by CV, is a measure of
relative variation expressed as
percentage.
• The ratio of the standard deviation
and the mean multiplied by 100%.
 Measure of Variability: COEFFICIENT OF VARIATION

COEFFICIENT OF VARIATION
•Population CV

CV   100%

•Sample CV

s
CV   100%
x
 Property of the Coefficient of Variation
A desirable property of the �� is its being
unit-less. Thus, it can be used to compare
the dispersion of two or more sets of
data even if they have different units of
measurements.

32
 Example 2
The following data shows
the family sizes of 9 families:
2, 3, 5, 5, 4, 3, 2, 1, 5. Find
the following:
3. Range
4. Variance
5. Standard Deviation
6. Coefficient of Variation
34
fractiles
•measures of location that describe
or locate the non-central position of
a set of data
•also known as quantiles
•Percentile
• divide an ordered set of observations into 100
equal parts
•Decile
• divide an ordered set of observations into 10
equal parts
•Quartile
• divide an ordered set of observations into 4
equal parts
Percentile
�� - 1% of the values falls below ��
�� - 2% of the values falls below ��
�� - 3% of the values falls below ��
⋮
��� - 99% of the values falls below ���
Decile
�� - 10% of the values falls below ��
�� - 20% of the values falls below ��
�� - 30% of the values falls below ��
⋮
�� - 90% of the values falls below ��
Quartile
�� - 25% of the values falls below ��
�� - 50% of the values falls below ��
�� - 75% of the values falls below ��
Procedure
Steps:
1. Arrange data in increasing order.
2. Solve �: ��
��� ��
100
��
�= ��� ��
10
��
��� ��
4
� � +� �+1
3. If � is integer: �������� =
2
If � is fractional: get the next higher integer,
say �, then �������� = � �
Example 2
The following data shows the family sizes
of 9 families: 2, 3, 5, 5, 4, 3, 2, 1, 5 .
Find the following:
8. �50
9. �3
Example 3
The magazine Forbes publishes annually a list
of the world’s wealthiest individuals. For
2007, the net worth of a sample of 10 richest
individuals, in billions of dollars, is as follows:
33, 26, 24, 21, 19, 20, 18, 18, 52, 56
Find the following:
1. Mean 5. Variance
2. Median 6. Standard deviation
3. Mode 7. Coefficient of variation
4. Range 8. �3
 Example 4 (from stat manual)
The number of hours spent by a sample of ten students
in studying per day were recorded as follows: 5, 8,
4, 2, 2, 5, 2, 2, 5 and 4.
Find the following:
1. Mean 5. Variance
2. Median 6. Standard deviation
3. Mode 7. Coefficient of variation
4. Range 8. �1 and�6
FOR PRACTICE!
A random sample of 10 students was given a special
test. The time it took the students to finish the
exam were taken and are given as follows:
15 30 26 40 35 19 22 28 17 38
Find the following:
1. Show that the mean and the median values are
equal.
2. Find the mode of the data
3. Find the values of the standard deviation,
coefficient of variation, D7 and P35.