MEASURES OF VARIABILITY

The information provided given by various measures

of central tendency is too limited. They only to
describe the central location od a set of values. To
illustrate, let us examine the three sets of data below:

Set A: 80 82 86 89 93
Set B: 83 85 86 87 89
Set C: 84 85 86 87 88
When the means of each of the 3 sets are computed,
we get 86. Notice that the spread of the scores in
each set are different though the 3 sets have equal
means. Apparently Set A has the most spread scores
while Set C has the least. We need to compute the
degree of dispersion of the scores from the average
to describe a set distribution adequately. This can be
determined by applying the different measures of
variability.
Measures Of Variation

Range
Mean Deviation

Standard Deviation and

Variance
 Quartile Deviation
Range
 Range refers to the difference between the highest
and the lowest score.
 If the highest score is 25 and the lowest score in a
distribution is 10, then the range is equal to 25–10
=15. This range is specifically called as the exclusive
range.
 If the difference between the exact lower limit of the
lowest score and the exact upper limit of the highest
score is solved, the result is called inclusive range.
 Generally, the exclusive range is used for ungrouped
data while the inclusive range is used for grouped
data.
Range
 The range is the easiest and simplest to determine
among the measures of variability because it depends
only on the pair of extreme values. However, it is also
the most unstable because its value easily fluctuates
with the change in either of the highest or lowest scores.
It is also considered the most unreliable because it does
not give the dispersion or spread of the scores in
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.
Average or Mean Deviation
 The average or mean deviation takes into account
all the variables in a given distribution . The formula
for mean deviation is:

σ/𝑿 −𝑿/
MD = Where; X = score of values
𝒏
X = mean
n = number of cases
Example:
 Solve the mean deviation using the three sets of
distribution:

Set A: 11 12 13 14 15
Set B: 18 20 25 28 34
Set C: 12 12 12 12 12
Solution for Set A:
Values Algebraic Deviation from Absolute Deviation from
(X) the Mean the Mean
(X–X) /X–X/
11 11 – 13 = -2 / -2 / = 2
12 12 – 13 = -1 / -1 / = 1
13 13 – 13 = 0 /0/=0
14 14 – 13 = 1 /1/=1
15 15 – 13 = 2 /2/=2

෍ 𝐗 = 𝟔𝟓 ෍ 𝐗 −𝐗 =𝟎 ෍/𝐗 − 𝐗/= 𝟔

σ/𝑿 −𝑿/ 6
X=
σX
=
65
= 13 MD = = = 1.2
n 5 𝒏 5
This means that on the average, the scores deviated
from the mean by 1.2
Solution for Set B:
Values Algebraic Deviation from Absolute Deviation from
(X) the Mean the Mean
(X–X) /X–X/
18 -7 7
20 -5 5
25 0 0
28 3 3
34 9 9

෍ 𝐗 = 𝟐𝟓 ෍ 𝐗 −𝐗 =𝟎 ෍/𝐗 − 𝐗/= 𝟐𝟒

σ/𝑿 −𝑿/ 24
MD = = = 4.8
𝒏 5
If Set C consists made up of the same score values,
then its mean is equal to the common score value. Thus,
MD = 0 since there is no deviation between each of
the score and the mean.

When the mean deviations for Sets A, B, and C are

1.2, 4.8, and 0 respectively, it can be concluded that
B has greater variability than A while C has no
variability from the mean.
Standard Deviation and Variance

 Most commonly used measure of variation

 Indicates how closely the values of a given data set
are clustered around the mean
 A lower value of the standard deviation means that
the values of that given data set are spread over a
smaller range around the mean
 It is the positive square root of the variance
Formula
For ungrouped data:
σ(𝑥 − 𝜇)2
𝛿= (population standard deviation)
𝑁
σ𝑛
𝑖=1(𝑥𝑖 −𝑥)
2
𝑠=
𝑛−1
(sample standard deviation)

Where; N – number of population

n – number of sample (sample size)
μ − population mean
x – sample mean
Example:
The final exam scores of 5 students were 80, 88, 92,
90 and 85. Determine the variance and standard
deviation.
Solution:
 Find the mean
σ𝑥 435
x= = = 87
𝑛 5
σ(𝑥 −𝑥)2 88
S= = = 4.69
𝑛−1 5−1
S2 = (4.69)2 = 22 If the standard deviation is
given , then the variance is its square.
Formula
For grouped data:
2
σ 𝑓(𝑑 ′ ) 𝑓𝑑′ 2
𝑠=𝑖 − ( )
𝑛 𝑛

Where;
i = class width
d’ = class deviation
f = class frequency
n = number of cases
Example
The table below illustrates the wages per day of the laborers in
a certain construction. Compute the standard deviation and
variance.
Wages No. of
laborers
(f)
80 - 84 8
75 - 79 12
70 - 74 16
65 - 69 13
60 - 64 9
Solution:

The class interval where the assumed mean lies has a deviation (d’) equal
to zero.
Solution:
2
σ 𝑓(𝑑 ′ ) 𝑓𝑑′ 2 93 −3 2
𝑠=𝑖 −( ) =5 − ( )
𝑛 𝑛 58 58

s = 6.32
s2 = (6.32)2 = 40.006
Quartile Deviation
 The quartile deviation or the semi-interquartile
range provides the spread of half of the range of
the middle 50 percent of the scores or values in a
distribution.
 It is calculated using the following equation:
𝑸𝟑 − 𝑸𝟏
Q=
𝟐
Where; Q = quartile deviation
Q3 = third quartile
Q1 = first quartile
Example:
Given the Frequency distribution below, compute the quartile
deviation. Class Interval F
64 -67 7
60 – 63 6
56 – 59 7
52 – 55 5
48 – 51 10
44 – 47 14
40 – 43 10
36 – 39 5
32 – 35 9
28 – 31 7
24 – 27 6
20 - 23 4
Soution:
Solution:
Solve for 𝑄1 & 𝑄3 (review the formula on the
previous lesson)
𝑄1 = 33.94
𝑄3 = 53.5

𝟓𝟑.𝟓 −𝟑𝟑.𝟗𝟒
Hence, Q = = 9.78
𝟐
In our computation, the quartile deviation is 9.78, if
the median is 44.64,adding one quartile deviation to
the median, 44.64 + 9.78 = 54.42 and subtracting
one quartile deviation from the median, 44.64 – 9.78
is 34.86. This means that 50% of the scores lie
between 34.6 and 54.42.
MEASURES OF RELATIVE
VARIABILITY
Coefficient of Variation
The coefficient of variation is used to:
 express the standard deviation as a percentage of the
mean.
 To compare two distribution with different means and
standard deviation
To illustrate, we can use the ff. formula:
𝑺
V = x 100% where; V = coefficient of variation
ഥ
𝒙
s = standard deviation
ഥ = mean
𝒙
Example

Department store A has a mean weekly sales of 340

bags with a standard deviation of 12. Department
store B has a mean weekly sales of 550 bags with a
standard deviation of 15. which store has the greater
variability in their weekly sales in relative means.
Solution
Dept. Store A
𝑺 𝟏𝟐
V = x 100% =
ഥ
x 100% = 3.53%
𝒙 𝟑𝟒𝟎

Dept. Store B
𝑺 𝟏𝟓
V = x 100% =
ഥ
x 100% = 2.73%
𝒙 𝟓𝟓𝟎

Thus, department store A has the larger variation from

the mean.
SKEWNESS AND KURTOSIS
Skewness
 Skewness refers to the measure of the lack of
symmetry of a distribution.
 The distribution is said to be skewed when the spread
of the measurements is greater on one side than on
the other side of the point of central tendency.
 A distribution that is skewed to the right has a positive
value for skewness. A distribution that is skewed to the
left has a negative value for skewness, and a normal
or symmetrical distribution has zero skewness.
 𝟑 (𝐗 −𝐌𝐝)
Skewness (Sk) =
𝐬
where; X = mean
Md = median
s = standard deviation

Sk = 0 , indicates that the distribution of the data is symmetric

Sk < 0 , indicates that the distribution is negatively skewed
Sk > 0 , indicates that the distribution is positively skewed
KURTOSIS
 Kurtosis refers to the measure of the degree of
peakedness or flatness of a distribution.

Types of Kurtosis:
 Leptokurtic or tall distribution – involve unusually
large number of scores or values at the center of
the distribution. It is more peaked than the normal
curve since the scores are concentrated within a
very narrow interval at the center. Its tails are high
and long.
 Platykurtic distributions or flat distributions – the
values or scores are distributed over a wider range
about the center making the hump of the curve flat.
It is flatter than the normal distribution. Its tails are
short.
 Mesokurtic distributions – it refers to the normal or
symmetrical distributions. The values or scores are
moderately distributed about the center of the
distribution. It is neither too flat nor too peaked.
 Formula for Kurtosis

Kurtosis (Ku) =

Ku = 3, normal or mesokurtic
Ku > 3, leptokutic
Ku < 3, platykurtic