Descriptive Statistics

Moments , skewness and kurtosis

Moments
• Moments are statistical measures that give certain characteristics of the
distribution.
• Shape
• Position
• Variability of a distribution
• Most common moments are
• First Moment: Measure of the central location. (MEAN)
• Second Moment: Measure of dispersion/spread.(VARIANCE)
• Third Moment: Measure of asymmetry.
• Fourth Moment: Measure of outliers/tailedness.
• The third moment is called skewness, and the fourth moment is known as
kurtosis.
Types of moments
1. Moments about origin
2. Moments about mean, and
3. Moments about arbitrary point,
Moments about Origin
Moments about origin
Moments about Arbitrary Point
When actual mean is in fraction, moments are first calculated about an
arbitrary point and then converted to moments about the actual mean.
When deviations are taken from arbitrary point, the formula’s are:
Moments about Arbitrary Point
Moments about Arbitrary Point
Moments around mean
Moments around mean
Moments
• Moments can be classified in raw and central moment.
• Raw moments are measured about any arbitrary point A (say). If A is taken to
be zero then raw moments are called moments about origin.
• When A is taken to be Arithmetic mean we get central moments.
• The first raw moment about origin is mean whereas the first central
moment is zero.
• The second raw and central moments are mean square deviation and
variance, respectively.
• The third and fourth moments are useful in measuring skewness and
kurtosis
Example 1/1
Find first four moments of 6,9,11,12,17 about mean
Solution
Mean =11
First moment= 0
Second Moment= 13.2
Third moment= 16.8
Fourth moment= 387.6
Example 2/5
• Calculate the first four moments about origin for the following
frequency distribution

xi 10 15 20 25 30
f 2 5 4 9 5
Solution
xi 10 15 20 25 30
f 2 5 4 9 5

xi f fx fx2 fx3 fx4

10 2 20 200 2000 20000
15 5 75 1125 16875 253125
20 4 80 1600 32000 640000
25 9 225 5625 140625 3515625
30 5 150 4500 135000 4050000
25 550 13050 326500 8478750
Second Third Fourth
First Moment moment moment moment
22 522 13060 339150
Example 3/7
• Calculate the first four moments about the point A=35 for the
following frequency distribution

Class 10-20 20-30 30-40 40-50 50-60

Interval
Frequency 15 20 30 10 5
Solution

Moments
First -3.75
Second 137.5
Third -1125
Fourth 43750
Example 4/9
• The first four moments of a distribution about the point A=5 are
2,20,40 and 50. Find the central moments
Solution
Example 5/10
Solution
Example 6/11
Example 6/11
 Example 7/15

The first four moments of a distribution about the point A=3 are
-2,10,-25 and 50. Find the central moments and the moments
around origin and the value 5
Example 8/14
Example 8/14
Skewness
• Skewness means ‘lack of symmetry’.
• We study skewness to have an idea about the shape of the curve
drawn from the given data
• When the data set is not a symmetrical distribution, it is called a
skewed distribution and such a distribution could either be positively
skewed or negatively skewed.
Types of Skewness
Positive Skewness:
• In a distribution that is Positively Skewed, the tail is more pronounced on the right side.
• also called the right-skewed distribution
• It assumes a skewness value of more than zero.
• Since the skewness of the given distribution
is on the right, the mean value is greater than
the median and moves towards the right, and
the mode occurs at the highest frequency
of the distribution.
• In this distribution,
Mean > Median > Mode.
Types of Skewness
Negative Skewness:
• In a distribution that is Negatively Skewed, the tail is more pronounced on the left side.
• also called the left-skewed distribution
• It assumes a skewness value of less than zero.
• Since the skewness of the given distribution
is on the left, the mean value is less than
the median and moves towards the left, and
the mode occurs at the highest frequency
of the distribution.
• In this distribution,
Mean < Median < Mode.
Types of Skewness
Zero Skewness:
• A symmetrical distribution has zero skewness
• The spread of the frequencies is the same on both sides of
the centre point of the curve.
• It assumes a skewness value of zero.
• In this distribution,
Mean = Median = Mode.
Measures of Skewness
• Karl-Pearson’s coefficient of skewness
• Bowley’s coefficient of skewness
• Kelly’s coefficient of skewness
• Coefficient of skewness based on moments
Karl-Pearson’s coefficient of skewness
• According to Karl-Person the absolute measure of skewness
= Mean – Mode.
• The median is always the middle value, and the mean and mode are the extremes, Karl-Pearson
coefficient of skewness captures the horizontal distance between mean and mode.
(𝑀ⅇan − Modⅇ)
=
𝑆⋅𝐷
• The above formula gives you Pearson's first coefficient.
• Division by the standard deviation will help you scale down the difference between mode and
mean.
• This will scale down their values in a range of -1 to 1.
• Substituting the relationship Mode=3Median-2Mean, in Pearson’s first coefficient gives us
Pearson’s second coefficient and the formula for skewness:
3(𝑀ⅇan − Mⅇdian)
𝑆⋅𝐷
Example 1
Calculate Karl – Pearson’ s coefficient of skewness for the
following data.
25, 15, 23, 40, 27, 25, 23, 25, 20
Example 1
Example 2
Example2
Example 3
Example 3
Interpretation of Karl-Pearson’s coefficient of skewness
If this value is between:
1. -0.5 and 0.5, the distribution of the value is almost symmetrical
2. -1 and -0.5, the data is negatively skewed, and if it is between 0.5 to
1, the data is positively skewed. The skewness is moderate.
3. If the skewness is lower than -1 (negatively skewed) or greater than 1
(positively skewed), the data is highly skewed.
Bowley’s coefficient of skewness
• Bowley's skewness is another name for the quartile skewness coefficient.
• Bowley's coefficient of skewness is based on the quartile deviation, which is
a measure of the spread of a distribution around its median.
• In a symmetrical distribution, the quartiles are equidistant from the value of
the median; i.e., Median – Q1 = Q3 – Median. but in skewed distributions it
may not happen.
• Hence, Bowley's skewness is calculated using the following formula:

• In Karl- Pearson’s method of measuring skewness the whole of the series is

needed. Prof. Bowley has suggested a formula based on relative position of
quartiles.
Interpretation of Bowley's coefficient of skewness
• Bowley's coefficient of skewness ranges from -1 to +1.
• A value of zero indicates a perfectly symmetrical distribution, while
negative values indicate a negatively skewed distribution and positive
values indicate a positively skewed distribution.
• The magnitude of the coefficient indicates the degree of skewness,
with larger values indicating greater skewness.
• Interpretation of Bowley's coefficient of skewness depends on the
context of the data.
• For instance, if you're analyzing the returns of a portfolio over time, positive
skewness might imply that there are occasional large spikes in the portfolio
value due to significant gains from certain investments.
Limitations of Bowley’s Coefficient of Skewness
• One of the limitations of Bowley's coefficient of skewness is that it is
sensitive to outliers.
• Outliers are values that are significantly higher or lower than the rest
of the data and can skew the distribution.
• Therefore, it is important to check for outliers before using Bowley's
coefficient of skewness.
Example 4
Example 4
Example 5
Find the Bowley’ s coefficient of skewness for the following series.
2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22
Example 5
Example 6
Example 6
Example 7 (Practice)
Example 7
Kelly’s Measure of Skewness
• is one of several ways to measure skewness in a data distribution.
• Bowley’s skewness is based on the middle 50 percent of the observations in a
data set. It leaves 25 percent of the observations in each tail of the distribution.
• Kelly suggested that leaving out fifty percent of data to calculate skewness too
extreme and suggested a measure of skewness which is based on middle 80
percent of the observations of data set.
Interpretation
Example 8
Example 8

The distribution is
negatively skewed
Moment coefficient of skewness
• The Measure of skewness based on moments is denoted by β1 and is given by

• Also called Pearson’s 𝛽1 − 𝑐𝑜𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡

• For a symmetrical distribution, the third moment about the mean is zero. Hence 𝛽1 =0
• Greater the value of 𝛽1 , more skewed is the distribution.
• However, 𝛽1 as a measure of skewness has a limitation as it does not tell us about the
direction of skewness. Therefore another measure of skewness –Pearson’s
𝛾1 𝑐𝑜𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡 𝑖𝑠 defined as follows
𝜇3
𝛾1 = 𝛽1 = 3
𝜇2
• This measure tells us the direction of skewness
Example 9
The first three central moments are 0,8.76 and -2.91. Find the moment coefficient
of skewness
Example 9
Kurtosis
• Kurtosis is another measure of the shape of a distribution
• Whereas skewness measures the lack of symmetry of the frequency
curve of a distribution, kurtosis is measures the peakedness or
flatness of a distribution.
• Kurtosis is the fourth moment, which measures the presence of
outliers in the distribution i.e., it gives the graph of either heavily-
tailed or lightly-tailed due to the presence of outliers.
• If the graph has a shorter tail and a flat top, then Kurtosis is said to be
high.
• If the graph has a higher peak and lower tail, then the kurtosis is said
to be low.
Types of Kurtosis(depending upon the shape of their peak. )
• Mesokurtic
• Leptokurtic
• Platykurtic
Mesokurtic
• Normal Kurtosis
• When kurtosis is equal to 3, the distribution is mesokurtic.
• This means the kurtosis is the same as the normal distriburion; it is mesokurtic
(medium peak).
• The kurtosis of a mesokurtic distribution is neither high nor low; rather, it is
considered to be a baseline for the two other classifications.
Platykurtic
• Negative Kurtosis
• Negative excess values of kurtosis (<3) indicate that the distribution is flat and has
thin tails. Platykurtic distributions have negative kurtosis values.
• A platykurtic distribution is flatter (less peaked) when compared with the normal
distribution, with fewer values in its lighter and thinner tails.
Leptokurtic
Positive Kurtosis
• Positive excess values of kurtosis (> 3) indicate that distribution is peaked
and possesses thick tails. Leptokurtic distributions have positive kurtosis
values.
• A leptokurtic distribution has a higher peak (thin bell) and fatter and heavy
tails than a normal distribution.
Measure of kurtosis
Pearson’s 𝛽2 − 𝑐𝑜𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡 also called moment coefficient of kurtosis

Where 𝜇2 𝑎𝑛𝑑 𝜇4 are second and fourth moments about the mean
• Value of 𝛽2 measures the degree of peakedness
• As 𝛽2 =3 represents normal distribution, kurtosis is also given by
𝛾2 = 𝛽2 − 3
• Value of 𝛾2 is positive for a leptokurtic curve, negative for
platykurtic and zero for mesokurtic curve
Example
Example
Example10
Using the data (12 13 54 56 25), determine the type of kurtosis
present.
A. Mesokurtic distribution
B. Platykurtic distribution
C. Leptokurtic distribution
Example 10