[ GEC-MMW: LESSON 3: Measures of Dispersion ]

_____________________________________________________________________________________
Intended Learning Outcomes:
Determine the degree of dispersion of data using different measures of variability.

4.3 Measure of Dispersion

Three students are named finalists in the search for A-1 Student of the Year. The evaluation
papers revealed the following scores of the students in five different areas:
Student A 97, 92, 96, 95, 90

Student B 94, 94, 92, 94, 96

Student C 95, 94, 93, 96, 92

In a contest like this, the statistic that is most appropriate to use is the mean. The one with the
highest means wins.

The mean scores of the three students however, are the same – 94.

What would be the next thing to do without considering new data from these students?

Statistics other than the mean may provide additional information from the same data. These
statistics are the measures of dispersion.

Measure of dispersion or variability refer to the spread of the values about the mean. These are
important quantities used by statisticians in evaluation. Intuitively, a smaller dispersion of scores arising
from the comparison often indicates more consistency and more reliability.

There are at least three measures of dispersion, namely range, mean deviation, and standard
deviation.

------------------------------------------------------------------------------------------------------------------------------------------

1) The Range
- The quickest way to determine the dispersion of scores is through the computation of the range
because it is the easiest measure to compute.
- Range is simply the difference of the highest (��) and lowest (��) scores in a set of data
under consideration.
The range of the data is
�� = �� − ��
where �� = range
�� = highest score in the data set
�� = lowest score in the data set

- The range is the most unstable because its value easily fluctuates with the change in either the
highest or lowest scores.
- It is also considered the most unreliable because it does not give the dispersion or spread of the
scores between the two extreme values. A more reliable measure should involve all the values
in a distribution to provide us an adequate spread of all the scores from the average.
 1
[ GEC-MMW: LESSON 3: Measures of Dispersion ]

Example 1 (Finding the range of the data set)

The range of each of the set of scores of the three students is as follows:
Student A 97, 92, 96, 95, 90 �� = 97, �� = 90, �� = 97 − 90
=7

Student B 94, 94, 92, 94, 96 �� = 96, �� = 92, �� = 96 − 92

=4

Student C 95, 94, 93, 96, 92 �� = 96, �� = 92, �� = 96 − 92

=4

2) The Mean Deviation

- The mean deviation considers all the variables in each distribution.
- The smaller the mean deviation implies better consistency because the scores deviate from the
average slightly.

i. Computation of the Mean Deviation for Ungrouped Data

The mean deviation of ungrouped data is computed using the formula

���� =∑|�� − ��̅
|
��
where ���� = mean deviation
��̅ = mean
�� = individual item
�� = number of items under observation

Example 2 (Finding the mean deviation of an ungrouped data)

Find the mean deviation of Student B and C. Which of performance is better?
Student B 97, 92, 96, 95, 90

Student C 95, 94, 93, 96, 92

Student B:
��̅=97 + 92 + 96 + 95 + 90
470
���� =∑|�� − ��̅
| �� 5= 5= ����

=|97 − 94| + |92 − 94| + |96 − 94| + |95 − 94| + |90 − 94|
5
=|3| + |−2| + |2| + |1| + |−4|

5=3 + 2 + 2 + 1 + 4
12
5= 5= ��. ��

Student C:
 ��̅=95 + 94 + 93 + 96 + 92
470
���� =∑|�� − ��̅
| �� 5= 5= ����

=|95 − 94| + |94 − 94| + |93 − 94| + |96 − 94| + |92 − 94|
5
=|1| + |0| + |−1| + |2| + |−2|

5=1 + 0 + 1 + 2 + 2
6
5= 5= ��. ��
The smaller the mean deviation implies the better consistency because the scores deviate from
the average slightly. Hence, student C’s performance is better.

2
[ GEC-MMW: LESSON 3: Measures of Dispersion ]

3) Standard Deviation and Variance

- The most important measure of dispersion is the standard deviation.
- The standard deviation is used to determine how far the data are from the mean. If the values are
clustered tightly about their mean, the standard deviation is small and if the values become more
and more scattered about their mean, the standard deviation for these sets is large.
- Like the mean deviation, standard deviation differentiates sets of scores with equal averages.
But the advantage of standard deviation has several applications in inferential statistics. -
Standard Deviation is calculated as the square root of variance.
- The standard deviation (and the variance) show whether or not the scores are grouped closely
around the mean of the distribution.
- The symbols for sample and population variances are ��2and ��2respectively. Variance is
frequently discussed by researchers as an indicator of how much variability there is in an entire
distribution of scores.

i. Computation of Standard Deviation and Variance for Ungrouped Data

• The population standard deviation (��) and variance of a population (��2) for ungrouped data
can be computed from the formula:

�� ��
���� =∑(�� − ��)
��
�� = √��(�� − ��)
��
where �� = population standard
deviation ��2= variance of a population
�� = values of the observations �� =
population mean
�� = total number of observations in the population

• The sample standard deviation (��) and sample variance (��2) for ungrouped data can
 be computed from the formula:

�� ��
�� − ���� =∑(�� − ��̅
)
�� of a sample �� = values of the observations ��̅
=
�� = √��(�� − ��̅
) sample mean
where �� = sample standard deviation ��2= variance
�� − ��

�� = total number of observations in the sample

Example 4 (Finding the standard deviation and variance of an ungrouped data)

Find the standard deviation and variance of the following sample data:
Score (�� − (�� −
(��) ��̅
) )��
��̅

7 -3 9

8 -2 4

10 0 0

12 2 4

13 3 9

Total: 26

3
[ GEC-MMW: LESSON 3: Measures of Dispersion ]

Solution:

Since the data is a sample data, we will get the sample standard deviation and sample

=7+8+10+12+13
variance. �� = 5 ��̅

5= 10

��
�� = √��(�� − ��̅
)

�� − ��= √����
����
�� − ��= √ ��= √��. �� = ��. ����

���� =∑(�� − ��̅

)��
 ����
�� − ��= ��= ��. ��
Thus, the sample standard deviation is 2.55 and the sample variance is 6.5