CHAPTER 3

Measures of Variation
OBJECTIVES

Upon the completion of this chapter, the student should be able to:

 Understand Range and Quartile Deviation, as a measure of variation and its

importance in describing a given set of data.
 Recognize the concept of Mean Absolute Deviation (MAD) in determining
amount by which each extreme value varies.
 Determine the Standard Deviation of grouped and ungrouped data.
 Perform operations with regards to Normal Distribution and graph it
through the use of Z-table distribution list.
 Understand Skewness and Kurtosis, and their importance.

INTRODUCTION

Proper allocation of resources and the view trend of how resources are distributed are just
some of the benefits that an economist gets from their knowledge about measure of distribution.
The importance of knowing this chapter is of best help, not just in the field of economics but also
to other fields such as education, medicine, surveying and even study on engineering.

A measure of distribution is otherwise known as a measures of dispersion or measures of

spread. It describes how the values in a set of data are spread out around the measure of central
tendency. These measures describes how homogeneous or how heterogeneous are the
observations (scores, elements, or entries) in a given set of data. Measures of distribution are
required to fully understand a given distribution by description.

This chapter presents major topics such as Normal Distribution, Skewness and Kurtosis
as well as other measures of variation including Range, Quartile Deviation, Mean Absolute
Deviation, Standard Deviation, and Coefficient of Variation.

45
 Range, Quartile Deviation and Mean Absolute Deviation (MAD)
Several measures of variation or dispersion are Range, Quartile Deviation and Mean
Absolute Deviation. Their definition is as follows:

Range is simply the difference between the lowest and highest values. It can also
mean all the output values of a function.

Range = 𝐻 − 𝐿

where H: highest value

L: lowest value

Quartile Deviation is one-half of the difference between the upper and lower, that
is, the third and first, quartiles also known as semi-inter quartile range.

𝑄3 −𝑄1
QD =
2
where 𝑄1: first quartile value
𝑄3 : third quartile value

Mean Absolute Deviation is the measure of the average of the absolute deviations
from the mean of all observations in a given data.

For the ungrouped data, the formula given below should be used.

∑𝑑
MAD =
𝑛
where d: |𝑥 − 𝑥̅ | (the deviation of each score from the mean)
x: individual score
𝑥̅ : mean score
n: total frequency

If the data given is being grouped or in frequency distribution, the formula is:

∑𝑓𝑑
MAD =
𝑛

46
 where d: absolute deviation (the difference between each
class midpoint and the mean of the distribution
f: frequency
n: number of items/total frequency

The mean absolute deviation or MAD is essential in order to distinguish the amount of
each measure of variation that may be varies from the mean of distribution. It may be obtained
according to the set of data such as grouped or ungrouped data.

We note that the above application of formulas under the Range, Quartile Deviation and
the mean absolute deviation will lead to the better understanding of the measures of variation in
describing the given set of data.

Standard Deviation

The Standard Deviation is a measure of statistical dispersion, it’s a way of

describing how spread a sets of values are around the mean of that set.

The more spread apart the data, the higher the deviation. It is useful in comparing sets
of data which may have the same mean but a different range. It has proven to be an extremely
useful measure of spread in part because it is mathematically tractable. The Standard
Deviation formula is simply the square root of the variance.

Standard Deviation for Ungrouped Data

The formula for the standard deviation for ungrouped data for an entire population is:

∑(𝑥−𝑥̅ )
S= √
𝑛

where S: standard deviation

x: each value in the population
𝑥̅ : the mean of the values
n: the number of values (population)

The formula for the standard deviation for ungrouped data for a sample of a population is:

∑(𝑥−𝑥̅ )2
S=√
𝑛−1

47
 where S: standard deviation
x: each value in the population
𝑥̅ : the mean of the values
n: the number of values (sample)

Standard Deviation for Grouped Data

By grouped data we mean the situation where we have, for example, sampled many
people or situations and it is convenient to classify our data into groups and subgroups.

The formula for the standard deviation for grouped data for an entire population is:

∑ 𝑓𝑥 2 ∑ 𝑓𝑥 2
S= √ −( )
𝑛 𝑛
where f: frequency of each class
x: midpoint of every class
n: total number of frequency

The formula for the standard deviation for grouped data for a sample of a population is:

𝑛(∑ 𝑓𝑥 2 )−(∑ 𝑓𝑥)2

S =√
𝑛(𝑛−1)

where f: frequency of each class

x: midpoint of every class
n: total number of frequency

Coefficient of Variation
The Coefficient of Variation is useful tool in statistic for comparing the degree of
variation from one data series to another, even if the means are drastically different from each
other a statistical measure of the dispersion of data points in a data series around the mean.

The coefficient of variation represents the ratio of the standard deviation to the mean.

Standard Deviation
CV = × 100%
Mean
Suppose you want to evaluate the relative dispersion of grades for two classes of
students: Class A and Class B. The coefficient of variation can be used to compare these two

48
groups and determine how the grade dispersion in Class A compares to the grade dispersion in
Class B.

Skewness
Skewness gives us an idea about the shape of the curve which we can draw with the help
of the given data. A distribution is symmetric if the mean, median and mode all coincide with
each other.

Skewness simply means “lack of symmetry”

But if the mean, median and mode do not have equal values, the data set is said to be
skewed distribution. It can come in the form of “positive skewness” or “negative skewness”
depending on whether the data points are skewed to the right (positive skew) or to the left
(negative skew).
Kinds of skewness:

a. Symmetrical distribution

It is a symmetrical distribution because the mean, median and mode have equal values.
The spread of the frequencies looks the same to the left and right of the center point.

49
b. Positively skewed distribution

It is a positively skewed distribution because the value of the mean is maximum, the
mode is least and the median lies in between the two. The spread of the frequencies has greater
range of values on the right side than on the left side.

c. Negatively skewed distribution

It is a negatively skewed distribution because the value of the mode is maximum, the
mean is least and the median lies in between the two. The spread of the frequencies has greater
range of values on the left side than on the right side.

Measure of skewness:

a. Karl-Pearson’s coefficient of skewness

According to Karl-Pearson, the absolute measure of skewness = mean – mode. It is based

upon the divergence of mean from mode in a skewed distribution. A relative measure,

50
independent of the units of measurement, is defined as the Karl Pearson’s coefficient of
skewness, 𝑆𝐾 . The formula is given as:

𝑥̅ − 𝑥̂
𝑆𝐾 =
𝑆
where 𝑥̅ : mean
𝑥̂: mode
S: standard deviation

The sign of 𝑆𝐾 gives the direction and its magnitude give the extent of skewness.

Symmetrical distribution 𝑆𝐾 = 0
Positively skewed distribution 𝑆𝐾 > 0
Negatively skewed distribution 𝑆𝐾 < 0

If mode is not given in the distribution, the empirical relation between mean, median and
mode is use which states that Mean – Mode = 3(Mean – Median). Hence, Karl Pearson’s
coefficient of skewness is defined in terms of median as:

3(𝑥̅ − 𝑥̃ )
𝑆𝐾 =
𝑆
where 𝑥̅ : mean
𝑥̃: median
S: standard deviation

b. Bowley’s coefficient of skewness

According to Bowley, the quartiles are equidistant from the value of the median in a
symmetrical distribution. But in a skewed distribution, the quartiles will not be equidistant from
the median. He has suggested a formula based on relative position of quartiles, given as:

𝑄3 − 2𝑄2 + 𝑄1
𝑆𝑄 =
𝑄3 − 𝑄1
c. Kelly’s measure of skewness

He gave the formula in terms of percentiles and deciles, given as:

𝑃90 − 2𝑃50 + 𝑃10

𝑆𝑃 =
𝑃90 − 𝑃10

51
 𝐷9 − 2𝐷5 + 𝐷1
𝑆𝐷 =
𝐷9 − 𝐷1

Kurtosis
Kurtosis used to describe the peakedness of a curve. All the frequency curves expose
different degrees of flatness or peakedness. Measure of kurtosis denotes the shape of top of a
frequency curve.

Measure of kurtosis tell us the extent to which a distribution is more peaked or more
flat topped than the normal curve, which is symmetrical and bell-shaped.

It is designated as Mesokurtic. If a curve is relatively narrower and peaked at the top, it is

designated as Leptokurtic. If the frequency curve is more flat than normal curve, it is designated
as Platykurtic.

Measures of Kurtosis:

If k = 0.263, the distribution is said to be normal and the curve is Mesokurtic.

If k > 0.263, the distribution is said to be more peaked and the curve is Leptokurtic.
If k < 0.263, the distribution is said to be flat topped and the curve is Platykurtic.

To find the coefficient of kurtosis, the formula is given as:

𝑄𝐷
𝐾=
𝑃90 − 𝑃10
(𝑄3 − 𝑄1 )
where: QD =
2

52
EXAMPLES

Let us take the following examples on how to compute the range, quartile deviation,
mean absolute deviation, standard deviation, coefficient of variation, skewness and kurtosis
for the given set of data:

Examples for Ungrouped Data

Example 3.1

Given the following set of data for the diameter of screw drivers.

Solution:

𝒙 |𝒙 − 𝒙
̅| ̅ |𝟐
|𝒙 – 𝒙
1.1 1.89 3.5721
1.6 1.39 1.9321
1.6 1.39 1.9321
1.7 1.29 1.6641
1.8 1.19 1.4161
2.1 0.89 0.7921
2.2 0.79 0.6241
2.3 0.69 0.4761
2.3 0.69 0.4761
2.5 0.49 0.2401
2.9 0.09 0.0081
3.4 0.41 0.1681
3.5 0.51 0.2601
4 1.01 1.0201
4.3 1.31 1.7161
4.4 1.41 1.9881
4.5 1.51 2.2801
4.5 1.51 2.2801
4.6 1.61 2.5921
4.8 1.81 3.2761
∑𝒅 = 21.88 𝟐
∑𝒅 = 28.714

RANGE

Range = 𝐻 − 𝐿
Range = 4.8 − 1.1
Range = 3.7

53
QUARTILE DEVIATION

𝑄1 = 25% (N)
𝑄1 = .25 (20)
𝑄1 = 5 rank
𝑄1 = 1.8

𝑄3 = 75% (N)
𝑄3 = .75 (20)
𝑄3 = 15 rank
𝑄3 = 4.3

𝑄3 −𝑄1
QD =
2
4.3−1.8
QD =
2
QD = 𝟏. 𝟐𝟓

MEAN ABSOLUTE DEVIATION

1.1 + 1.6 + 1.6 + 1.7 + 1.8 + 2.1 + 2.2 + 2.3 + 2.3 + 2.5 + 2.9 + 3.1 + 3.5 + 4 + 4.3 + 4.4 + 4.5 + 4.5 + 4.6 + 4.8
𝑥̅ =
20
𝑥̅ = 2.99

∑𝑑
MAD =
𝑛
21.88
MAD =
20
MAD = 𝟏. 𝟎𝟗𝟒

STANDARD DEVIATION

∑(𝑥−𝑥̅ )2
S =√
𝑛−1
28.714
S =√
20−1
S = 𝟏. 𝟓𝟏𝟏𝟑

COEFFICIENT OF VARIATION

S
CV = × 100%
𝑥̅
1.5113
CV = × 100%
2.99
CV = 50.5452 %

54
SKEWNESS

𝑃10 = 10% (N)

𝑃10 = 0.10 (20)
𝑃10 = 2 rank
𝑃10 = 1.6

𝑃50 = 50% (N)

𝑃50 = 0.50 (20)
𝑃50 = 10 rank
𝑃50 = 2.5

𝑃90 = 90% (N)

𝑃90 = 0.90 (20)
𝑃90 = 18 rank
𝑃90 = 4.5

𝑃90 − 2𝑃50 + 𝑃10

𝑆𝑃 =
𝑃90 − 𝑃10
4.5− 2(2.5)+ 1.6
𝑆𝑃 =
4.5−1.6
𝑺𝑷 = 0.3793

KURTOSIS

𝑄𝐷
𝐾=
𝑃90 − 𝑃10
1.25
𝐾=
4.5−1.6
𝑲 = 0.4310

55
Example 3.2

Mike is deciding on tile for his bathroom. He has narrowed it down to 12 tiles. The prices
of the 12 tiles are 3.29, 4.15, 2.97, 2.61, 5.00, 2.99, 3.75, 3.50, 2.75, 4.30, 4.45 and 2.83 dollars.

Solution:

𝒙 |𝒙 − 𝒙
̅| ̅ |𝟐
|𝒙 – 𝒙
2.61 0.9392 0.8821
2.75 0.7992 0.6387
2.83 0.7192 0.5172
2.97 0.5792 0.3355
2.99 0.5592 0.3127
3.29 0.2592 0.0672
3.50 0.0492 0.0024
3.75 0.2008 0.0403
4.15 0.6008 0.3610
4.30 0.7508 0.5637
4.45 0.9008 0.8114
5.00 1.4508 2.1048
∑𝒅 = 7.8084 ∑𝒅𝟐 = 6.637

RANGE

Range = 𝐻 − 𝐿
Range = 5.00 − 2.61
Range = 2.39

QUARTILE DEVIATION

𝑄1 = 25% (N)
𝑄1 = .25 (12)
𝑄1 = 3 rank
𝑄1 = 2.83

𝑄3 = 75% (N)
𝑄3 = .75 (12)
𝑄3 = 9 rank
𝑄3 = 4.15

𝑄3 −𝑄1
QD =
2
4.15−2.83
QD =
2
QD = 𝟎. 𝟔𝟔

56
MEAN ABSOLUTE DEVIATION

2.61+2.75+2.83+2.97+2.99+3.29+3.50+3.75+4.15+4.30+4.45+5.00
𝑥̅ = 12
𝑥̅ = 3.5492

∑𝑑
MAD =
𝑛
7.8084
MAD =
12
MAD = 𝟎. 𝟔𝟓𝟎𝟕

STANDARD DEVIATION

∑(𝑥−𝑥̅ )2
S =√
𝑛−1
6.637
S =√
12−1
S = 𝟎. 𝟕𝟕𝟔𝟖

COEFFICIENT OF VARIATION

S
CV = × 100%
𝑥̅
0.7768
CV = × 100%
3.5492
CV = 21.8866 %

SKEWNESS

3.29+3.50
𝑥̃ =
2
𝑥̃ = 3.395

3(𝑥̅ −𝑥̃)
𝑆𝐾 =
𝑆
3(3.5492−3.395)
𝑆𝐾 =
0.7768
𝑺𝑲 = 0.5955

KURTOSIS

𝑃10 = 10% (N)

𝑃10 = 0.10 (12)

57
 𝑃10 = 1.2 rank or 2 rank
𝑃10 = 2.75

𝑃90 = 90% (N)

𝑃90 = 0.90 (12)
𝑃90 = 10.8 rank or 11 rank
𝑃90 = 4.45

𝑄𝐷
𝐾=
𝑃90 − 𝑃10
0.66
𝐾=
4.45− 2.75
𝑲 = 0.388

Examples for Grouped Data

Example 3.3

The following are the size of radius of a water tank that are available on the market with
their corresponding quantities.

Radius (dm) f
0.98 – 1.01 7
0.94 – 0.97 5
0.90 – 0.93 2
0.86 – 0.89 6
0.82 – 0.85 4
0.78 – 0.81 5
0.74 – 0.77 3
0.70 – 0.73 8
0.66 – 0.69 4
0.62 – 0.65 2
0.58 – 0.61 1
0.54 – 0.57 3

Compute the range, quartile deviation, mean absolute deviation, standard deviation,
coefficient of variation, Karl Pearson’s coefficient of skewness and the coefficient of kurtosis
from the table above.

58
Solution:

Radius (dm) 𝒇 𝒙 𝒇𝒙 < 𝐶𝐹 > 𝐶𝐹 𝒙𝟐 𝒇𝒙𝟐 |𝒙 − 𝒙

̅| 𝒇(𝒙 − 𝒙 ̅)
0.98 – 1.01 7 0.995 6.965 50 7 0.99 6.93 0.188 1.316
0.94 – 0.97 5 0.955 4.775 43 12 0.912 4.56 0.148 0.74
0.90 – 0.93 2 0.915 1.83 38 14 0.837 1.674 0.108 0.216
0.86 – 0.89 6 0.875 5.25 36 20 0.766 4.596 0.068 0.408
0.82 – 0.85 4 0.835 3.34 30 24 0.697 2.788 0.028 0.112
0.78 – 0.81 5 0.795 3.975 26 29 0.632 3.16 0.012 0.06
0.74 – 0.77 3 0.755 2.265 21 32 0.57 1.71 0.052 0.156
0.70 – 0.73 8 0.715 5.72 18 40 0.511 4.088 0.092 0.736
0.66 – 0.69 4 0.675 2.7 10 44 0.456 1.824 0.132 0.528
0.62 – 0.65 2 0.635 1.27 6 46 0.403 0.806 0.172 0.344
0.58 – 0.61 1 0.595 0.595 4 47 0.354 0.354 0.212 0.212
0.54 – 0.57 3 0.555 1.665 3 50 0.308 0.924 0.252 0.756
∑𝒇 = 50 ∑𝒇𝒙 = 40.35 ∑𝒇𝒙𝟐 = ∑𝒇(𝒙 − 𝒙̅) =
33.414 5.584

For the solution of the following, refer from the previous chapter (Page 35).

Mean: 0.807
Median: 0.807
Mode: 0.71
Q1: 0.708
Q3: 0.925

RANGE

Range = 𝐻 − 𝐿
Range = 1.01 − 0.54
Range = 0.47

QUARTILE DEVIATION

𝑄3 −𝑄1
QD =
2
0.925−0.708
QD =
2
QD = 𝟎. 𝟏𝟎𝟖𝟓

MEAN ABSOLUTE DEVIATION

∑𝑓𝑑
MAD =
𝑛
5.584
MAD =
50
MAD = 𝟎. 𝟏𝟏𝟏𝟕

59
STANDARD DEVIATION

𝑛(∑ 𝑓𝑥 2 )−(∑ 𝑓𝑥)2

S =√
𝑛(𝑛−1)
50(33.414)−(40.35)2
S =√
50(50−1)
1670.7−1628.1225
S =√
2450
S = 𝟎. 𝟏𝟑𝟏𝟖

COEFFICIENT OF VARIATION

S
CV = × 100%
𝑥̅
0.1318
CV = × 100%
0.807
CV = 16.3321 %

SKEWNESS

𝑥̅ − 𝑥̂
𝑆𝐾 =
𝑆
0.807−0.71
𝑆𝐾 =
0.1318
𝑺𝑲 = 0.736

KURTOSIS
10𝑁
−𝐹𝑃10
100
𝑃10 = 𝐿𝐿 + ( )𝑖
𝑓𝑃10
5−4
𝑃10 = 0.615 + ( ) 0.04
2
𝑃10 = 0.635
90𝑁
−𝐹𝑃90
100
𝑃90 = 𝐿𝐿 + ( )𝑖
𝑓𝑃90
45−43
𝑃90 = 0.975 + ( ) 0.04
7
𝑃90 = 0.986

𝑄𝐷
𝐾=
𝑃90 − 𝑃10

60
 0.1085
𝐾=
0.986− 0.635
𝑲 = 0.3091

Example 3.4

The following are the mass of the Milkis powder repacks with their corresponding
numbers.

Mass f
65.5 – 67.5 15
62.5 – 64.5 8
59.5 – 61.5 17
56.5 – 58.5 6
53.5 – 55.5 4
50.5 – 52.5 11
47.5 – 49.5 5
44.5 – 46.5 3
41.5 – 43.5 4
38.5 – 40.5 7
35.5 – 37.5 3
32.5 – 34.5 2

Compute the range, quartile deviation, mean absolute deviation, standard deviation,
coefficient of variation, Bowley’s measure of skewness and the coefficient of kurtosis from the
table above.

Solution:

Mass 𝒇 𝒙 𝒇𝒙 < 𝐶𝐹 > 𝐶𝐹 𝒙𝟐 𝒇𝒙𝟐 |𝒙 − 𝒙

̅| 𝒇(𝒙 − 𝒙̅)
65.5 – 67.5 15 66.5 997.5 85 15 4422.25 66333.75 11.611 174.165
62.5 – 64.5 8 63.5 508 70 23 4032.25 32258 8.611 68.888
59.5 – 61.5 17 60.5 1028.5 62 40 3660.25 62224.25 5.611 95.387
56.5 – 58.5 6 57.5 345 45 46 3306.25 19837.5 2.611 15.666
53.5 – 55.5 4 54.5 218 39 50 2970.25 11881 0.389 1.556
50.5 – 52.5 11 51.5 566.5 35 61 2652.25 29174.75 3.389 37.279
47.5 – 49.5 5 48.5 242.5 24 66 2352.25 11761.25 6.389 31.945
44.5 – 46.5 3 45.5 136.5 19 69 2070.25 6210.75 9.389 28.167
41.5 – 43.5 4 42.5 170 16 73 1806.25 7225 12.389 49.556
38.5 – 40.5 7 39.5 276.5 12 80 1560.25 10921.75 15.389 107.723
35.5 – 37.5 3 36.5 109.5 5 83 1332.25 3996.75 18.389 55.167
32.5 – 34.5 2 33.5 67 2 85 1122.25 2244.5 21.389 42.778
∑𝒇 = 85 ∑𝒇𝒙 = 4665.5 ∑𝒇𝒙𝟐 = ∑𝒇(𝒙 − 𝒙̅) =
264069.25 708.277

61
For the solution of the following, refer from the previous chapter (Page 37).

Mean: 54.889
Median: 57.75
Mode: 60.35
Q1: 48.35
Q3: 62.656

RANGE

Range = 𝐻 − 𝐿
Range = 67.5 − 32.5
Range = 35

QUARTILE DEVIATION

𝑄3 −𝑄1
QD =
2
62.656−48.35
QD =
2
QD = 𝟕. 𝟏𝟓𝟑

MEAN ABSOLUTE DEVIATION

∑𝑓𝑑
MAD =
𝑛
708.277
MAD =
85
MAD = 𝟖. 𝟑𝟑𝟐𝟕

STANDARD DEVIATION

𝑛(∑ 𝑓𝑥 2 )−(∑ 𝑓𝑥)2

S =√
𝑛(𝑛−1)
85(264069.25)−(4665.5)2
S =√
85(85−1)
22445886.25−21766890.25
S =√
7140
S = 𝟗. 𝟕𝟓𝟏𝟖

COEFFICIENT OF VARIATION

S
CV = × 100%
𝑥̅

62
 9.7518
CV = × 100%
54.889
CV = 17.7664 %

SKEWNESS

Since median and Q2 have the same value, therefore Q2 is equal to 57.75.
𝑄3 − 2𝑄2 + 𝑄1
𝑆𝑄 =
𝑄3 − 𝑄1
62.656− 2(57.75)+ 48.35
𝑆𝑄 =
62.656− 48.35
𝑺𝑸 = −0.3141

KURTOSIS

10𝑁
−𝐹𝑃10
𝑃10 = 𝐿𝐿 + ( 100 )𝑖
𝑓𝑃10
8.5−5
𝑃10 = 38 + ( )3
7
𝑃10 = 39.5
90𝑁
−𝐹𝑃90
100
𝑃90 = 𝐿𝐿 + ( )𝑖
𝑓𝑃90
76.5−70
𝑃90 = 65 + ( )3
15
𝑃90 = 66.3

𝑄𝐷
𝐾=
𝑃90 − 𝑃10
7.153
𝐾=
66.3− 39.5
𝑲 = 0.2669

63
Example 3.5

The following data are the scores of the students in the recent National Achievement Test
in Section 3 of Kabayao High School.

Scores f
91 – 96 10
85 – 90 4
79 – 84 12
73 – 78 25
66 – 72 10
61 – 66 7
55 – 60 33
49 – 54 15
43 – 48 18
37 – 42 6
31 – 36 7
25 – 30 3

Compute the range, quartile deviation, mean absolute deviation, standard deviation,
coefficient of variation, Kelly’s measure of skewness and the coefficient of kurtosis from the
table above.

Solution:

Scores 𝒇 𝒙 𝒇𝒙 < 𝐶𝐹 > 𝐶𝐹 𝒙𝟐 𝒇𝒙𝟐 |𝒙 − 𝒙

̅| 𝒇(𝒙 − 𝒙 ̅)
91 – 96 10 93.5 935 150 10 8742.25 87422.5 31.28 312.8
85 – 90 4 87.5 350 140 14 7656.25 30625 25.28 101.12
79 – 84 12 81.5 978 136 26 6642.25 79707 19.28 231.36
73 – 78 25 75.5 1887.5 124 51 5700.25 142506.25 13.28 332
66 – 72 10 69.5 695 99 61 4830.25 48302.5 7.28 72.8
61 – 66 7 63.5 444.5 89 68 4032.25 28225.75 1.28 8.96
55 – 60 33 57.5 1897.5 82 101 3306.25 109106.25 4.72 155.76
49 – 54 15 51.5 772.5 49 116 2652.25 39783.75 10.72 160.8
43 – 48 18 45.5 819 34 134 2070.25 37264.5 16.72 300.96
37 – 42 6 39.5 237 16 140 1560.25 9361.5 22.72 136.32
31 – 36 7 33.5 234.5 10 147 1122.25 7855.75 28.72 201.04
25 – 30 3 27.5 82.5 3 150 756.25 2268.75 34.75 104.16
∑𝒇 = 150 ∑𝒇𝒙 = 9333 ∑𝒇𝒙𝟐 = ∑𝒇(𝒙 − 𝒙 ̅) =
622429.5 2118.08

For the solution of the following, refer from the previous chapter (Page 40).

Mean: 62.22
Median: 59.227
Mode: 58.045

64
Q1: 49.9
Q3: 75.74

RANGE

Range = 𝐻 − 𝐿
Range = 96 − 25
Range = 71

QUARTILE DEVIATION

𝑄3 −𝑄1
QD =
2
75.74−49.9
QD =
2
QD = 𝟏𝟐. 𝟗𝟐

MEAN ABSOLUTE DEVIATION

∑𝑓𝑑
MAD =
𝑛
2118.08
MAD =
150
MAD = 𝟏𝟒. 𝟏𝟐𝟎𝟓

STANDARD DEVIATION

𝑛(∑ 𝑓𝑥 2 )−(∑ 𝑓𝑥)2

S =√
𝑛(𝑛−1)
150(622429.5)−(9333)2
S =√
150(150−1)
93364425−87104889
S =√
22350
S = 𝟏𝟔. 𝟕𝟑𝟓𝟑

COEFFICIENT OF VARIATION

S
CV = × 100%
𝑥̅
16.7353
CV = × 100%
62.22
CV = 𝟐𝟔. 𝟖𝟗𝟕𝟎 %

65
SKEWNESS

10𝑁
−𝐹𝑃10
100
𝑃10 = 𝐿𝐿 + ( )𝑖
𝑓𝑃10
15−10
𝑃10 = 36.5 + ( )6
6
𝑃10 = 41.5
50𝑁
−𝐹𝑃50
100
𝑃50 = 𝐿𝐿 + ( )𝑖
𝑓𝑃50
75−49
𝑃50 = 54.5 + ( )6
33
𝑃50 = 59.23
90𝑁
−𝐹𝑃90
𝑃90 = 𝐿𝐿 + ( 100 )𝑖
𝑓𝑃90
135−124
𝑃90 = 78.5 + ( )6
12
𝑃90 = 84
𝑃90 − 2𝑃50 + 𝑃10
𝑆𝑃 =
𝑃90 − 𝑃10
84− 2(59.23)+ 41.5
𝑆𝑃 =
84− 41.5
𝑺𝑷 =0.1656

KURTOSIS

𝑄𝐷
𝐾=
𝑃90 − 𝑃10
12.92
𝐾=
84− 41.5
𝑲 = 0.304

66
 Normal Curve
Blood pressure, height and weight, and even ages are just some of the natural occurring
phenomena in which a normal distribution can be used.

A Normal Distribution simply describes the proportionality of a given frequency.

.

It is generally represented by a bell shaped curve. The area under the curve represents
probability and since the probability of sure events (that DV value will fall between negative and
positive infinity) is always 1, the total area under all curves should always be equal to 1 or 100%.

Properties of a normal curve

 Points are symmetrically distributed.

 Asymptotic in both direction of the x – axis as the tail of the approaches ∞.
 Mean=Median=Mode
 Area is equal to 1 or 100%.

Areas Under normal curves

The preliminary step to find the area under the normal curve is to convert the given
variables into standardized thru applying this formula:
𝑋−𝑋̅
Z=
𝑆
where X: any given value of a particular variable
Z: standardized score
𝑋̅: mean
𝑆: standard deviation

In finding the area, we’ll need the help of the Z – Distribution Chart, it’s a chart in which
certain values of Z are given for us to find the curve much easier. It is located on the last page of
this module.

67
EXAMPLES

Example 3.6

a. Find the area under the normal curve between 𝑧1 = 0 and 𝑧2 = 2.4

Solution:

At 𝑧1 = 0 the area is 0
At 𝑧2 = 2.4 the area is 0.9918
Total Area = 𝑧1 + 𝑧2
Area = 0+0.9918
A=0.9918

Therefore the shaded part has an area of 0.9918.

b. Find the area under the normal curve between 𝑧1 = -1.3 and 𝑧2 = 0.

Solution:

At 𝑧1 = -1.3 the area is 0.9032

At 𝑧2 = 0 the area is 0
Total Area = 𝑧1 + 𝑧2
Area = 0.9032+0
A=0.9032

Therefore the shaded part has an area of 0.9032.

c. Find the area under the normal curve between 𝑧1 = -1.3 and = 𝑧2 = 2.4.

Solution:

At 𝑧1 = -1.3 the area is 0.9032

At 𝑧2 = 2.4 the area is 0.9918
Total Area = 𝑧1 + 𝑧2
Area = 0.9032+0.9918
A=1.895

Therefore the shaded part has an area of 1.895.

68
Example 3.7

If there were 5,000 PUPCET examinees, how many of them will get lower than 80 of the
score. If M = 84 and S = 5.

Solution:

S=5
M = 84
̅ = 80
X

𝑋 − 𝑋̅
𝑍=
𝑆
84 − 80
Z=
5
𝐙 = 𝟎. 𝟖

Where at Z = 0.8 the area is 0.2881.

Since we are after for the number of examinees, we are ought to multiply the area to the number
of examinees to get the total number of examinees that scored lower than 80.

Number of Examinees = (0.2881)(5000) = 1441 students

Example 3.8

If Joseph Balba plays DOTA at an average rate of 8 hours/week, determine the

probability that Joseph will play DOTA between 6 – 10 hours a week, with a Standard Deviation
of 2 hours.

Solution:

S=2
M=8
̅
X1 = 5.5 hours

𝑋−𝑋̅1
𝑍1 = 𝑆
5.5−8
𝑍1 = 2
𝐙𝟏 = −𝟏. 𝟐𝟓

S=2
M=8
̅ 2 = 10.5 hours
X

69
 𝑋−𝑋̅2
𝑍2 = 𝑆
10.5−8
𝑍2 = 2
𝐙𝟐 = 𝟏. 𝟐𝟓

Where at Z = 1.25 the area is 0.8944.

To get the probability simply multiply the area by 100%. So the probability that Joseph will play
DOTA between6 – 10 hours a week is 89.44%since we got the same value of Z it means that
joseph has the same percentage in either 6 or 10.

Example 3.9

Determine the probability that a CE board examinee, who took the board exam would get
a score higher than 85 if the average score is 83 and S = 3.

Solution:

M = 83
X = 85
S=3
𝑋−𝑀
𝑍= 𝑆
85−83
𝑍=
3
𝒁 = 𝟎. 𝟔𝟕

Where at Z = 0.67 the area is 0.2486.

Example 3.10

Determine the probability that a CE board examinee, who took the board exam would get a
score higher than 80 if the average score is 83 and S = 3.

Solution:

M = 80
S=3
X = 85
𝑋−𝑀
𝑍= 𝑆
80−83
Z= 3
Z = -1.0

Where at Z = 1.0 the area is 0.3413

70
Name:_________________________ Section:_______________ Date:______________

I. UNGROUPED DATA

A. A hen lays twelve eggs. Each egg was weighed and recorded as follows: 51, 53, 54,
56, 60, 61, 68, 69, 71, 74, 76 and 79 grams respectively. Find the range, quartile
deviation, mean absolute deviation, standard deviation, coefficient of variation,
coefficient of skewness and the coefficient of kurtosis.

B. Find the measures of variation of the first twelve odd numbers.

C. At the end of the semester, Raymundo Eugenio Panaligan Jr., a BSCE student got the
following grades. Compute for the measures of variation.

Subject Grade
Basic Economics 1.75
Basic Electrical Engineering 2.25
Construction Works IV 2.50
Buhay, Gawain at mga Sinulat ni Rizal 2.25
Integral Calculus 1.50
Team Sports – Volleyball 1.00
Logic 2.25
Sosyolohiya, Kultura at Pagpapamilya 2.00
Humanities 1.75
English III 1.75
Filipino III 2.00
Architectural Drafting III 2.25

71
II. GROUPED DATA

A. Shown below is the frequency distribution of the different areas of lot in La

Residencia de Calamba. Find the measures of variation.

Area (m2) Number of lots

250 – 259 10
240 – 249 30
230 – 239 50
220 – 229 60
210 – 219 80
200 – 209 90
190 – 199 55
180 – 189 45
170 – 179 85
160 – 169 70
150 – 159 25
140 – 149 70

B. Given below is the frequency distribution of diameter of balls in inches. The

number enclosed number enclosed in quantity represents the number of balls per the
diameter given. Find the measures of variation.

Diameter (in) Number of balls

8.40 – 8.44 5
8.35 – 8.39 3
8.30 – 8.34 2
8.25 – 8.29 10
8.20 – 8.24 15
8.15 – 8.19 12
8.10 – 8.14 6
8.05 – 8.09 3
8.00 – 8.04 2
7.95 – 7.99 8
7.90 – 7.94 4
7.85 – 7.89 7

72
III. NORMAL CURVES

A. Determine the probability that an examinee will have a percentage score between
85 and 90 if the mean score is 87 and a standard deviation of 5.
B. Determine the probability that an examinee will have a percentage score 88 if the
mean score is 87 and a standard deviation of 5.
C. Find the area:
a. Find the area under the normal curve between 𝑧1 = -1.51 and 𝑧2 = 0.
b. Find the area under the normal curve between 𝑧1 = 0 and 𝑧2 = 1.01.
D. If there were 1,124 board examinees in CE, how many of them will score higher
that 85 if the average is 83 and S = 3?
E. Using 83 % for the mean score and 3 as the Standard Deviation and N = 1,124 as
the number of examinees. How many of them will score lower than 80?

73