Chapter One Advanced Business

Statistics
Moments, Skewness & Kurtosis

Moments
The concept and procedure of moments are popularly used to describe the characteristics of a
frequency distribution. They represent a convenient and unifying method for summarizing
many of the most commonly used descriptive statistical measures such as central tendency,
variation, Skewness and Kurtosis. The moment contribution of frequency distribution is
measured by the product of the class frequency and the corresponding deviation from the
origin. The Greek letter µ (read as mu) is generally used to denote the moments.
Moments are two kinds i) moment about mean (central moment) and
ii) moment about arbitrary point

If X1, X2, X3 ........ Xn are the N value assumed by the variate X we can define the r th moment
of variable X about the mean (X) is given by

∑(X-X) r
µr = For ungrouped data
N
∑f (X-X) r
µr = For grouped data
N
And the rth moment about any origin A is given by

∑(X-A) r
µr / = For ungrouped data
N
∑f (X-A) r
µr / = For grouped data
N
For different values of r we shall get different moments.

If r = 1, we get ∑(X- X )
1st moment about mean, µ1 = = 0 [ ∑(X-X) = 0]
N
If r = 2, we get
∑(X- X )2
2nd moment about mean, µ2 = = б2 = variance
N
If r = 3, we get
∑(X- X )3
3rd moment about mean, µ3 = = Skewness
N
Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 1
Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis

∑(X- X )4
4th moment about mean , µ4 = = Kurtosis
N

∑ ( X i −A )
1st moment about the origin µ1/ =
N

∑(X-A)2
nd /
2 moment about the origin µ2 = and so one.
N

Relation between Moments

Let X1, X2, X3 ........ Xn be the set of values with frequencies f 1, f2, f3, ...... fn respectively. If
A be an arbitrary value about which moments are taken, we have
∑f (X-A) ∑f X – A ∑f
µ1/ = = =X –A
N N

∑f (X-A)2
µ2/ = and so one
N

∑f (X- X ) ∑fX NX
Now, µ1 = = - = 0 remember that µ1 always zero
N N N

∑f (X- X )2
µ2 =
N

The second, third and fourth central moments can be expressed in terms of the raw moments
as follows:

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 2

Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis

Skewness
The term skewness refers to lack of symmetry or departure from symmetry i,e. when a
distribution is not symmetrical (or is asymmetrical) it is called a skewed distribution. It is
known as the shape characteristics of a distribution. The measure of skewness tells us
whether the dispersal of items from an average is symmetrical or asymmetrical. Thus,
skewness measures the degree of asymmetry or degree of departure from symmetry.

A distribution in which the values of mean, median and mode coincide is known as
symmetrical distribution. Conversely, when the values of mean, median and mode are not
equal the distribution is known as asymmetrical or skewed. In moderately skewed or
asymmetrical distribution, a very important relationship exists among mean, median and
mode. The relation is
Mode = 3 Median – 2 Mean
In a moderately skewed distribution, the median lies between the mode and the arithmetic
mean, approximately 2/3rd distance from the mode and 1/3rd from the mean. In a moderately
asymmetrical distribution Mode < Median < Mean, if the tail of such a distribution is
towards right. When the tail of such a distribution is towards left then Mode > Median>
Mean. It should be noted that in both the cases, median lies in between the mode and the
mean. If the value of mean is greater than the mode, skewness is said to be positive. On the
other hand, if the value of mode greater than mean, skewness is said to be negative.

The following diagrams would clarify the relative positions of the mean, median and mode
for frequency distribution which are moderately asymmetrical.

Bell–shaped frequency curve is characteristics

by the fact that it has a maximum values at the
centre and the class frequencies decreases to
zero symmetrically on both side of the
maximum.
X=m=z

Symmetrical Distribution

In a skewed frequency curve, the tail of the curve

to one side of the central maximum is longer than
the other. If the longer tail occurs to the right the
curve is said to be positive skewed. In a positive
skewed distribution mean is greater than the
mode and the median lies somewhere in between
mean and mode. A positive skewed distribution
z m x
contain some values that are much larger than the
Positive skewed frequency
majority of the other observations
Distribution

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 3

Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis

In a negative skewed distribution mode is greater

than the mean. The mean is pulled towards the
low-valued item into the left. If the longer tail
occurs to the left the curve is said to be negative
skewed. A negative skewed distribution contains
x m z some values that are much smaller than the
Negative skewed Distribution majority observations.

These curves are highly skewed. A curve for

distribution of income among persons in a
country would always give a positive J – shaped
curve, as there are only few persons having very
high incomes.

J – Shaped frequency
Distribution

So, Skewness is a measure that indicates whether a distribution is symmetrical or tails off is
one direction or another. It shows the direction of the scattered ness of the items.

Measures of Skewness
A suitable measure of skewness is
Mean - Mode
Skewness, Skp =
Standard deviation

This is known as Pearson’s measure of skewness when mode is ill defined, the above formula
has to be modified. In such a case the following formula is used
3 (Mean – Median)
Skp = [ Mode = 3 median – 2 mean]
Standard deviation

The value of this co-efficient would be zero in a symmetrical distribution. If mean greater
than mode co-efficient of skewness would be positive, otherwise negative. In practice, the
value of this co-efficient usually lies between ± 1.

Concept of Moments applied to Skewness

The concept of moments about the mean helps in understanding a frequency distribution in
all its feature.

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 4

Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis
Skewness in terms of moments is defined as the ratio of the third moment about the
mean (µ3) to the variance (µ2).

Another statistical parameter introduced by Karl Pearson, is β1 which determine whether a

frequency distribution is symmetrical or not i,e. β1 is used as a measure of skewness.
μ3 2

β 1=
μ2 3

In a symmetrical distribution, β1 shall be zero. However, the co-efficient of β1 as a measure of

skewness has a serious limitation. β1 as a measure of skewness cannot tell us about the
direction of skewness i,e. whether it is positive or negative. Because, µ 3 is the sum of the
cubes of the deviation from the mean and it may be positive or negative but µ 32 is always
positive. Also, µ2 is always positive.

Hence β1 is always positive. For this shortcoming, R.H. Fisher introduced the notion
μ3 2 μ3
γ 1 =√ β 1 = =
μ2 3 σ3
If γ 1 = 0 The distribution is normal
γ 1 > 0 The distribution is positive skewed
γ 1 < 0 The distribution is negative skewed
γ 1 = 0 There is no skewed in the distribution

Note: It is advisable to use γ 1 as a measure of skewness

Kurtosis
Kurtosis is the degree of peaked ness of a distribution, usually taken relative to a normal
distribution. The measure of kurtosis exhibits the extent to which the curve is more peaked or
more flat topped than the normal curve. Thus, the concept of kurtosis helps us in studying the
peaked ness of the distribution.

From the standpoint of kurtosis, the normal curve is a curve which is neither too peaked nor
too flat-topped is called mesokurtic. When the curve of a distribution is relatively high peak
is called leptokurtic, a curve which is flat-topped is platykurtic

 Leptokurtic:
Sharply peaked with
fat tails, and less
variable.
 Mesokurtic:
Medium peaked
Dr. Md. Monimul Haque, Professor, Department of Finance, R.U.  Platykurtic: Flattest 5
peak and highly
dispersed.
Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis

Different types of Kurtosis

The most important measure of kurtosis is β2 defined as

μ4 μ4
β 2= =
μ σ4
22
Where, µ4 and µ2 forth and 2nd moment about the mean.

This measure is a pure number and in always positive. For the normal distribution β 2 = 3. As
β 2 = 3 in a normal curve, therefore if β 2 is greater than 3, the curve is more peaked than the

normal curve and is known as leptokurtic and if, β 2 < 3, the curve is flatter at the top than the
normal and is known as platykurtic.
R. A. Fisher has introduced another notation
μ4
γ 2 =β 2−3= −3
μ 2
2

As γ 2 is zero in case of normal distribution, if γ 2 > 0 i,e. positive it indicates that distribution
is leptokurtic If γ 2 < 0 i,e. negative it indicates that the distribution is platykurtic.

It is to be noted that bigger the value of

βalignl¿2¿¿¿ in a frequency distribution, the greater is its
departure from normality. β 1 and β 2 are statistical parameter which measure whether a given
distribution is normal or not. β 1 and β 2 are measures of symmetry and normality
respectively. If β 1 = 0 the distribution is symmetrical and if β 2 = 3, the distribution is normal.
Note: It may be noted that it is easier to interpret kurtosis by calculating β2 instead of
γ2

Problem:
The first four central moments of a distribution are 0, 16, -36 and 120. Comment on the
skewness and kurtosis of the distribution.
Solution:
We are given µ1 = 0, µ2 = 16, µ3 = -36 and µ4 = 120
For commenting on the skewness we need to calculate γ1
µ3 -36
γ1 = = = - 0.5625
б 3
4 3

The distribution is negative skewed

µ4

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 6

Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis
γ2 = β2 – 3 = -3
2
µ2

= 120/162 - 3
= - 2.53
Since the value of γ2 < 0 i,e. negative it indicates that the distribution is platykurtic.

Differences Between Skewness and Kurtosis

Skewness, in basic terms, implies off-center, so does in statistics, it means lack of symmetry.
With the help of skewness, one can identify the shape of the distribution of data. Kurtosis, on
the other hand, refers to the pointedness of a peak in the distribution curve. The main
difference between skewness and kurtosis is that the former talks of the degree of symmetry,
whereas the latter talks of the degree of peakedness, in the frequency distribution.

Data can be distributed in many ways, like spread out more on left or on the right or evenly
spread. When the data is scattered uniformly at the central point, it called as Normal
Distribution. It is perfectly symmetric, bell-shaped curve, i.e. both the sides are equal, and so
it is not skewed. Here all the three mean, median and mode lie at one point.

Skewness and Kurtosis are the two important characteristics of distribution that are studied in
descriptive statistics. To further comprehend the understanding of these two concepts, let’s
take a look at the article given below.

Key Differences Between Skewness and Kurtosis

The points presented to you explain the fundamental differences between skewness and
kurtosis:

1. The characteristic of a frequency distribution that ascertains its symmetry about the
mean is called skewness. On the other hand, Kurtosis means the relative pointedness
of the standard bell curve, defined by the frequency distribution.
2. Skewness is a measure of the degree of lopsidedness in the frequency distribution.
Conversely, kurtosis is a measure of degree of tailedness in the frequency distribution.
3. Skewness is an indicator of lack of symmetry, i.e. both left and right sides of the
curve are unequal, with respect to the central point. As against this, kurtosis is a

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 7

Chapter One Advanced Business
Statistics
Moments, Skewness & Kurtosis
measure of data, that is either peaked or flat, with respect to the probability
distribution.
4. Skewness shows how much and in which direction, the values deviate from the mean?
In contrast, kurtosis explain how tall and sharp the central peak is?

Conclusion
For a normal distribution, the value of skewness and kurtosis statistic is zero. The crux of the
distribution is that in skewness the plot of the probability distribution is stretched to either
side. On the other hand, kurtosis identifies the way; values are grouped around the central
point on the frequency distribution.

1. Calculate Sample Skewness, Sample Kurtosis from the following grouped data
Class Frequency
2-4 3
4-6 4
6-8 2
8 - 10 1

Solution:
Mean x =∑fx/∑f
=52/10 = 2.2
Sample Standard deviation S = √∑(x-ˉx)2 /n-1=√26/24
=√1.0833
=1.0408
Skewness = ∑(x-ˉx)3 /(n-1)⋅S3
=1.2/24(1.0408)3
=1.2/24*1.1276
=0.0443

Kurtosis = ∑(x-ˉx)4/(n-1)*S4
=67.76/24*(1.0408)4
=67.76/24*1.1736
=2.4057

Dr. Md. Monimul Haque, Professor, Department of Finance, R.U. 8