Lecture Series on

Biostatistics

No. Biostat -8
Date:25.01.2009

MEASURES OF DISPERSION,
RELATIVE STANDING AND
SHAPE

Dr. Bijaya Bhusan Nanda,

M. Sc (Gold Medalist) Ph. D. (Stat.)
Topper Orissa Statistics & Economics Services, 1988
[email protected]
Arithmetic Mean

It is defined as the sum of observations divided

by the number of observations.
 CONTENTS
What is measures of dispersion?
Why measures of dispersion?
How measures of dispersions are calculated?
Range
Quartile deviation or semi inter-quartile range,
Mean deviation and
Standard deviation.
Methods for detecting outlier
Measure of Relative Standing
Measure of shape
 LEARNING OBJECTIVE

They will be able to:

describe the homogeneity or heterogeneity of
the distribution,
understand the reliability of the mean,
compare the distributions as regards the
variability.
describe the relative standing of the data and
also shape of the distribution.
What is measures of dispersion?
(Definition)
Central tendency measures do not reveal
the variability present in the data.

Dispersion is the scatteredness of the data

series around it average.

Dispersion is the extent to which values in

a distribution differ from the average of the
distribution.
Measures of dispersion are descriptive statistics
that describe how similar a set of scores are to
each other

The more similar the scores are to each other,

the lower the measure of dispersion will be.

The less similar the scores are to each other,

the higher the measure of dispersion will be

In general, the more spread out a distribution

is, the larger the measure of dispersion will be
 Why measures of dispersion? (Significance)

Determine the reliability of an average

Serve as a basis for the control of the

variability

To compare the variability of two or more

series and

Facilitate the use of other statistical

measures.
 Dispersion Example

Number of minutes 20 X:Mean Time 14.6

clients waited to see a
consulting doctor minutes
Consultant Doctor Y:Mean waiting time
X Y 14.6 minutes
05 15 15 16 What is the difference
12 03 12 18 in the two series?
04 19 15 14
37 11 13 17
06 34 11 15

X: High variability, Less consistency.

Y: Low variability, More Consistency
 Frequency curve of distribution of
three sets of data

A
B
 Characteristics of an Ideal Measure of Dispersion

1. It should be rigidly defined.

2. It should be easy to understand and easy to
calculate.
3. It should be based on all the observations of the
data.
4. It should be easily subjected to further
mathematical treatment.
5. It should be least affected by the sampling
fluctuation .
6. It should not be unduly affected by the extreme
values.
 How dispersions are measured?
Measure of dispersion:
Absolute: Measure the dispersion in the original unit of the
data.
Variability in 2 or more distrn can be compared provided
they are given in the same unit and have the same average.
Relative: Measure of dispersion is free from unit of
measurement of data.
It is the ratio of a measaure of absolute dispersion to the
average, from which absolute deviations are measured.
It is called as co-efficient of dispersion.
 METHODS OF MEASURING DISPERSION

Range
Quartile Deviation
Mean Deviation
Standard Deviation
How dispersions are measured? Contd.
The following measures of dispersion are used
to study the variation:
The range
The inter quartile range and quartile
deviation
The mean deviation or average deviation
The standard deviation
 How dispersions are measured? Contd.
Range:
The difference between the values of the two extreme items of a
series.
Example:
Age of a sample of 10 subjects from a population of 169subjects
are:

X1 X2 X3 X4 X5 X6 X7 X8 X9 X10
42 28 28 61 31 23 50 34 32 37
The youngest subject in the sample is
23years old and the oldest is 61 years, The
range: R=XL Xs
= 61-23 =38
Co-efficient of Range:
R= (XL - XS) / (XL + XS)
= (61 -23) / (61 + 23) =38 /84 = 0.452

Characteristics of Range
Simplest and most crude measure of dispersion
It is not based on all the observations.
Unduly affected by the extreme values and fluctuations of
sampling.
The range may increase with the size of the set of
observations though it can decrease
Gives an idea of the variability very quickly
 The Range
The range is defined as the difference between the
largest score in the set of data and the smallest score in
the set of data, XL XS

What is the range of the following data:

4 8 1 6 6 2 9 3 6 9

The largest score (XL) is 9; the smallest score (XS) is 1; the

range is XL - XS = 9 - 1 = 8
 Percentiles, Quartiles (Measure of Relative Standing)
and Interquartile Range
Descriptive measures that locate the relative position of an
observation in relation to the other observations are called
measures of relative standing.
They are quartiles, deciles and percentiles
The quartiles & the median divide the array into four equal parts,
deciles into ten equal groups, and percentiles into one hundred equal
groups.
Given a set of n observations X1, X2, . Xn, the pth percentile P is
the value of X such that p per cent of the observations are less than
and 100 p per cent of the observations are greater than P.
25th percentile = 1st Quartile i.e., Q1
50th percentile = 2nd Quartile i.e., Q2
75th percentile = 3rd Quartile i.e., Q3
 QL M QU
Figure 8.1 Locating of lower, mid and upper quartiles
Percentiles, Quartiles and Interquartile Range Contd.
n+1
Q1 = th ordered observation
4
2(n+1)
Q2 = th ordered observation
4
3(n+1)
Q3 = th ordered observation
4
Interquartile Range (IQR): The difference
between the 3rd and 1st quartile.
IQR = Q3 Q1
Semi Interquartile Range:= (Q3 Q1)/ 2
Coefficient of quartile deviation:
(Q3 Q1)/(Q3 + Q1)
Interquartile Range
Merits:
It is superior to range as a measure of dispersion.
A special utility in measuring variation in case of open end
distribution or one which the data may be ranked but measured
quantitatively.
Useful in erratic or badly skewed distribution.
The Quartile deviation is not affected by the presence of
extreme values.
Limitations:
As the value of quartile deviation dose not depend upon every
item of the series it cant be regarded as a good method of
measuring dispersion.
It is not capable of mathematical manipulation.
Its value is very much affected by sampling fluctuation.
 Another measure of relative standing is the z-score
for an observation (or standard score).
It describes how far individual item in a distribution
departs from the mean of the distribution.
Standard score gives us the number of standard
deviations, a particular observation lies below or above
the mean.
Standard xscore (or z -score) is defined as follows:
z-score=
For a population: X-

where X =the observation from the population
the population mean, = the population s.d
For a sample z-score= X-X
s
where X =the observation from the sample
X the sample mean, s = the sample s.d
 Mean deviation

The mean of the absolute deviations

xx
Mean deviation
n
 Mean Deviation

The mean deviation is an average of absolute

deviations of individual observations from the central
value of a series. Average deviation about mean
k

f i xi x
MDx i 1
n
k = Number of classes
xi= Mid point of the i-th class
fi= frequency of the i-th class
 Standard Deviation
Standard deviation is the positive square root
of the mean-square deviations of the
observations from their arithmetic mean.

Population Sample

i
x 2

s
i
x x 2

N N 1

SD variance
 The standard deviation
Measures the variation of observations from the mean

The most common measure of dispersion

Takes into account every observation

Measures the average deviation of observations from mean

Works with squares of residuals not absolute valueseasier to

use in further calculations
 The mean deviation
Measures the average distance of each
observation away from the mean of the data

Gives an equal weight to each observation

Generally more sensitive than the range or

interquartile range, since a change in any value
will affect it
 Mean Absolute Deviation (MAD) or Mean
Deviation (MD)
The average of difference of the values of items from some average
of the series (ignoring negative sign), i.e. the arithmetic mean of the
absolute differences of the values from their average .

Note:
1. MD is based on all values and hence cannot be calculated for open-
ended distributions.
2. It uses average but ignores signs and hence appears unmethodical.
3. MD is calculated from mean as well as from median for both
ungrouped data using direct method and for continuous
distribution using assumed mean method and short-cut-method.
4. The average used is either the arithmetic mean or median
Computation of Mean absolute Deviation
For individual series: X1, X2, Xn
|Xi -X|
M.A.D =
n
For discrete series: X1, X2, Xn & with
corresponding frequency f1, f2, fn
fi |Xi -X|
M.A.D =
fi
X: Mean of the data series.
Computation of Mean absolute Deviation:
For continuous grouped data: m1, m2, mn are the class mid
points with corresponding class frequency f1, f2, fn

fi|mi -X|
M.A.D =
fi
X: Mean of the data series.
Coeff. Of MAD: = (MAD /Average)
The average from which the Deviations are
calculated. It is a relative measure of dispersion
and is comparable to similar measure of other
series.
Example:
Find MAD of Confinement after delivery in the
following series.
Days of No. of Total days of Absolute fi|Xi - X|
Confinement patients confinement of each Deviation
( X) (f) group Xf from mean
|X - X |
6 5 30 1.61 8.05
7 4 28 0.61 2.44
8 4 32 1.61 6.44
9 3 27 2.61 7.83
10 2 20 3.61 7.22
Total 18 137 31.98

X = Mean days of confinement = 137 / 18 = 7.61

MAD=31.98 / 18=1.78, Coeff.of MAD= 1.78/7.61=0.233
Problem:
Find the MAD of weight and coefficient of MAD of
470 infants born in a hospital in one year from following
table.

Weight 2.0-2.4 2.5-2.9 3.0-3.4 3.5-3.9 4.0-4.4 4.5+

in Kg
No. of 17 97 187 135 28 6
infant
 Merits and Limitations of MAD
Simple to understand and easy to compute.
Based on all observations.
MAD is less affected by the extreme items than the Standard
deviation.
Greatest draw back is that the algebraic signs are ignored.
Not amenable to further mathematical treatment.
MAD gives us best result when deviation is taken from median.
But median is not satisfactory for large variability in the data. If
MAD is computed from mode, the value of the mode can not be
determined always.
 Standard deviation of a population

Every observation in the population is used.

x x
2

Standard deviation
n

Variance 2
The square of the population standard deviation is
called the variance.
33
 Variance

Variance is defined as the average of the

square deviations:

X 2

2

N
 Standard Deviation ()
It is the positive square root of the average of squares of
deviations of the observations from the mean. This is also called
root mean squared deviation () .
For individual series: x1, x2, xn

=

( xix )2
------------
n
=
n -( n )
xi2 xi 2

For discrete series: X1, X2, Xn & with

corresponding frequency f1, f2, fn

= fi ( xix )2
fixi2 fixi 2
------------
fi
=
fi
-( f )
i
 Standard Deviation () Contd.

For continuous grouped series with class

midpoints : m1, m2, mn & with
corresponding frequency f1, f2, fn

= fi ( mix )2
fimi2 fimi 2
------------
fi
=
fi
-( f )
i
Variance: It is the square of the s.d
Coefficient of Variation (CV): Corresponding
Relative measure of dispersion.

CV = ------- 100
X
 Characteristics of Standard Deviation:
SD is very satisfactory and most widely used
measure of dispersion
Amenable for mathematical manipulation
It is independent of origin, but not of scale
If SD is small, there is a high probability for
getting a value close to the mean and if it is large,
the value is father away from the mean
Does not ignore the algebraic signs and it is less
affected by fluctuations of sampling
SD can be calculated by :
Direct method
Assumed mean method.
Step deviation method.
 It is the average of the distances of the observed
values from the mean value for a set of data
Basic rule --More spread will yield a larger SD

Uses of the standard deviation

The standard deviation enables us to determine,
with a great deal of accuracy, where the values
of a frequency distribution are located in relation
to the mean.
Chebyshevs Theorem

For any data set with the mean and the

standard deviation s at least 75% of the
values will fall within the 2 interval and at
least 89% of the values will fall within the 3
interval of the mean
TABLE: Calculation of the standard deviation ()
Weights of 265 male students at the university of Washington
Class-Interval f d fd fd2 (d2) (fd)2
(Weight) = - (i)
n2
90-99 1 -5 -5 25 n
100-109 1 -4 -4 16 931 (99)2
110-119 9 -3 -27 81 = - (10)
265 265
120-129 30 -2 -60 120
130-139 42 -1 -42 42
140-149 66 0 0 0 (3.5132 0.1396) (10)
=
150-159 47 1 47 47
160-169 39 2 78 156 = (1.8367) (10)
170-179 15 3 45 135 18.37 or 18.4
=
180-189 11 4 44 176
190-199 1 5 5 25 d = (Xi A)/i n = fi
200-209 3 6 18 108 .A = 144.5, i = 10
n =265 d= 99 d2 = 931
 Means, standard deviation, and coefficients of variation of the age
distributions of four groups of mothers who gave birth to one or
more children in the city of minneapol in: 1931 to 1935. Interprete
the data
CLASSIFICATION X CV
Resident married 28.2 6.0 21.3
Non-resident married 29.5 6.0 20.3
Resident unmarried 23.4 5.8 24.8
Non-resident unmarried 21.7 3.7 17.1

Example: Suppose that each day laboratory technician A completes

40 analyses with a standard deviation of 5. Technician B completes
160 analyses per day with a standard deviation of 15. Which
employee shows less variability?
 Uses of Standard deviation
Uses of the standard deviation
The standard deviation enables us to determine, with
a great deal of accuracy, where the values of a
frequency distribution are located in relation to the
mean. We can do this according to a theorem
devised by the Russian mathematician P.L.
Chebyshev (1821-1894).
 Coefficient of Variation

A coefficient of variation is computed as a

ratio of the standard deviation of the
distribution to the mean of the same
distribution.
sx
CV
x
 Coefficient of variation

Is a measure of relative variability used to:

measure changes that have occurred in a
population over time
compare variability of two populations that are
expressed in different units of measurement
expressed as a percentage rather than in terms of
the units of the particular data

43
 Measure of Shape
The fourth important numerical characteristic of a
data set is its shape: Skewness and kurtosis.
Skewness
Skewness characterizes the degree of asymmetry of
a distribution around its mean. For a sample data,
the skewness is defined by the formula:

xi x
n 3
n
Skewness
(n 1)( n 2) i 1 s

where n = the number of observations in the sample,

xi= ith observation in the sample, s= standard deviation of
the sample, x = sample mean
 Measure of Shape

Figure 8.2 +ve or Right-skewed Figure 8.3 ve Left-skewed distribution

distribution
Kurtosis:
Kurtosis characterizes the relative peakedness or flatness of
a distribution compared with the bell-shaped distribution
(normal distribution).
Kurtosis of a sample data set is calculated by the formula:

n(n 1) n
xi x
4
3(n 1) 2
Kurtosis
(n 1)( n 2)( n 3) i 1 s
(n 2)( n 3)

Positive kurtosis indicates a relatively peaked distribution.

Negative kurtosis indicates a relatively flat distribution.
The distributions with positive and negative kurtosis
are depicted in Figure 8.4 , where the distribution with
null kurtosis is normal distribution.
 REFERENCE
1. Mathematical Statistics- S.P Gupta
2. Statistics for management- Richard I. Levin,
David S. Rubin
3. Biostatistics A foundation for Analysis in the
Health Sciences.
THANK YOU