Measures of Dispersion

Although arithmetic mean is a concise method of presentation

of a statistical data yet it is inadequate for several reasons,
for example, it gives no indication of its reliability.
A mean weight derived from a sample of 1200 will usually be
more reliable than a mean weight derived from 4 or 5
weights.
However, not only number of observations will affect the
reliability of the mean but also the variability of the
individual observations. For example, a mean weight of 20
children selected from a group with weights between 45 and
50 kg will be more reliable than the mean weight of 20
children selected from a group with weight varying between
35 to 70 kg. 1
As mean doesn’t in itself gives a clear picture of a distribution,
therefore, an other type of measure which helps to describe more
clearly the shape of the distribution is dispersion (or variability).
This variability among the individual observations is the essence of
statistical data. It indicates how the observations are spread out
from the average.

1. The spread in the sample observations may be of great interest to

estimate spread in the population.
2. The spread of a distribution may be of interest insofar as it aids in
gauging the precision with which a sample mean estimates the
corresponding population mean.

A measure of central tendency along with a measure of dispersion

gives an adequate description of statistical data. 2
 Measures of Dispersion
The Scatter of the values about their center is called Dispersion and
Measures which are used to find the amount of scatter about the center
are called Measures of Dispersion.
Measures of variation measure the variation present among the values in
a data set with a single number so measures of variation are summary
measures of the spread of values in the data

3
 Types of Measures of Dispersion
There are two main types of measures of dispersion:
1. Absolute Measure of Dispersion
2. Relative Measure of Dispersion
1. Absolute Measure of Dispersion
The absolute measure of dispersion measures the variation present among
the observations in the unit of the variable or square of the unit of the
variable.
2. Relative Measure of Dispersion
The relative measure of dispersion measures the variation present among
the observations relative to their average. It is expressed in the form of
ratio, or percentage. It is independent of the unit of measurement.

4
 Measures of Dispersion
The commonly used measures of absolute dispersion are:
1. Range
2. Quartile Deviation
3. Mean (Average) Deviation
4. Variance and Standard Deviation

Their corresponding measures of relative dispersion are:

1. Coefficient of Range/Coefficient of dispersion
2. Coefficient of Quartile Deviation
3. Coefficient of Mean (Average) Deviation
4. Coefficient of Variation (CV)

5
Measures of Spread
❖Distance Based Measures of Spread
• The range
• The Semi interquartile range
❖Centre Based Measures of Spread
• The mean deviation
• The variance
• The standard deviation

6
Distance Based Measures of Spread
Range
Range. The difference between the largest and the smallest
observations:

X Max = X m , X min = X 0
Range
• Coefficient = Xm − X0
of Range.

Xm − X0
Coefficient of Range =
Xm + X0

7
Range
Example: The following data set shows the weekly TV viewing
times, in hours. Find Range and Coefficient of Range
25 41 27 32 43 66 35 31 15 5
34 26 32 38 16 30 38 30 20 21

X m = 66, X 0 = 5
Range = X m − X 0 = 66 − 5 = 61
X m − X 0 66 − 5
Coefficient of Range = = = 0.86
X m + X 0 66 + 5

8
Disadvantages of the Range
• Ignores the way in which data are distributed

7 8 9 10 11 12 7 8 9 10 11 12
Range = 12 - 7 = 5 Range = 12 - 7 = 5

• Sensitive to outliers
1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,3,3,3,3,4,5
Range = 5 - 1 = 4

1,1,1,1,1,1,1,1,1,1,1,2,2,2,2,2,2,2,2,3,3,3,3,4,120
Range = 120 - 1 = 119
9
Interquartile Range

The difference between upper quartile and lower quartile

Q3 = Upper Quartile, Q1 = Lower Quartile

I .Q.R = Q3 − Q1

10
Semi Interquartile Range or Quartile Deviation

Half of the difference between upper quartile and lower

quartile

Q3 = Upper Quartile, Q1 = Lower Quartile

Q3 − Q1
Q.D =
2
Q3 − Q1
Coefficient of Q.D =
Q3 + Q1

11
Quartile Deviations. Find IQR,Q.D and Coefficient of Q.D

5 15 16 20 21 25 26 27 30 30
31 32 32 34 35 37 38 41 43 66
1(20+1)
LOCATION of Q1 = th observation in the data
4
=5.25th observation
VALUE of Q1 = 5th obs. + 0.25{6th obs.-5th obs.}
= 21 + 0.25{25-21} = 22.0 Hours

12
 2(20 + 1)
LOCATION of Q2 = th observation in the data
4
= 10.50th observation
VALUE of Q 2 = 10th obs. + 0.50{11th obs.-10th obs.}
= 30 + 0.50{31- 30} = 30.5 Hours
3(20 + 1)
LOCATION of Q = th observation in the data
3 4
= 15.75th observation
VALUE of Q3 = 15th obs. + 0.75{16th obs. -15th obs.}
= 35 + 0.75{37 - 35} = 36.5 Hours

13
Q1 = 22.0 Hours, Q3 = 36.5 Hours
I.Q.R=Q3 − Q1 = 36.5 − 22.0 = 14.50
Q3 − Q1 36.5 − 22.0
Q.D = = = 7.25
2 2
Q3 − Q1 36.5 − 22.0
Coefficient of Q.D = = = 0.12
Q3 + Q1 36.5 + 22.0

14
Centre Based Measures of Spread
• Several statistics use the centre of the data as a point of reference
and reflect how data is clustered around it

• Of these, average deviation, variance and the standard deviation are

the most widely used
All are based on the arithmetic mean.

15
Mean Deviation: is defined as the arithmetic mean of
the absolute deviation of observations from
mean/Median/Mode.
M .D from Mean M.D from Median

M .Dmean =
 X −X
M .Dmedian =
 X − Median
n n
M .D M .D
Coefficient of M .D = Coefficient of M .D =
X Median
M.D from Mode

M .Dmod e =
 X − Mode
n
M .D
Coefficient of M .D =
Mode 16
 X − X
Find M.D and Coefficient X cm
4 +6
of M.D. From mean
6 +4
9 +1
• The M.D of scores is 12 2
M .D =
 X −X
13 3
n
16 6
M .D
Coefficient of M .D = 60 22
X

X=
60
= 10 X  X −X
6

M .D =
 X − X 22
= = 3.67
n 6
M .D 3.67
Coeff . of M .D = = = 0.367
X 10 17
 X − Median
Find M.D and Coefficient X cm
4 +6.5
of M.D. from Median
6 +4.5
n +1
Median = th value = 3.5th value 9 +1.5
2
12 1.5
Median = 3rd value + 0.5(4th value − 3rd value)
13 2.5
median = 9 + 0.5(12 − 9) = 10.5 16 5.5
20
• The M.D of scores is  X − Median

M .DMedian =
 X − Median
=
20
− = 3.33
n 6
M .D 3.33
Coefficient of M .D = = = 0.317
Median 10.5
18
 X − Mode
Find M.D and Coefficient X cm
4 +5
of M.D. from Mode
9 0
Mode = 9 9 0
12 3
• The M.D of scores is 13 4
16 7
19
 X − Mode

M .DMode=
 X − Mode
=
19
− = 3.17
n 6
M .D 3.17
Coefficient of M .D = = = 0.352
Mode 9
19
 The Mean (absolute) Deviation
Problem:-Sum of deviations from X (X − X ) X −X

mean is always 0 ( Due to canceling 8 3 3

sign problem) regardless of the
spread of values in the data. Hence 5 0 0
deviation of values from mean can 2 -3 3
not be used as a measure of spread
in the data 0 6
15
X = =5
3
Solution:-[1]:-Take Absolute
deviations instead of deviation and M .D =
 X −X 6
= =2
calculate mean n 3
M .D 2
absolute deviations Coeff . of M .D = = = 0.4
X 5
20
Variance: is defined as the arithmetic mean of the
Squared deviation of observations from mean it is
denoted by S 2

( Biased Estimate Variance)

  (  ) 
2
( X − X ) 2
1 X
S =
2

n
or S =
2

n
 X −
2

n


 
(Unbiased Estimate Variance)

  (  ) 
2
(X − X ) 2
1  X
S 2
=
n −1
or S =
2

n −1 
 X −
2

n


 
21
Q. Find Variance of the X ( X − X )2
given data, s2 4 36
6 16
X 60 9 1
X= = = 10 12 4
n 6
13 9

S =
2  ( X − X ) 102
2

= = 17
16 36

n 6 60 102
X
S =
2  ( X − X ) 2

=
102
= 20.4
( X − X ) 2

n −1 5

22
Q. Find Variance of the
X cm X2
given data, s2
4 16
X 60 6 36
X = = = 10
n 6 9 81
 (  X) 
2
1
  = 17 12 144
S =
2
X −
2

n n  13 169
 
1 (60) 2  16 256
S =  702 −
2
 = 17 cm 2

6 6  60 702
1 
 (  X)
2
 X X 2
S =
2

n −1 
 X −
2

n


 
1  (60) 2
 n=6
S =  702 −
2
 = 20.4
5 6 
23
Standard Deviation: is defined as the Positive square root of
the arithmetic mean of the Squared deviation of
observations from mean it is denoted by
S
( Biased Estimate S .D )

  (  ) 
2
( X − X ) 2
1 X
S=
n
or S =
n
 X −
2

n 

 
(Unbiased Estimate S .D )

(X − X )  (  ) 
2
2
1  X
S=
n −1
or S =
n −1 
 X −
2

n 

 
24
 Q. Find S.D of the given X ( X − X )2
data, s 4 36
6 16
X 60
X= = = 10
9 1

n 6 12 4

(X − X )
13 9
2
102
S= = = 4.123 16 36

n 6 60 102
X ( X − X ) 2
S=
(X − X ) 2

=
102
= 4.517
n −1 5

25
Q. Find S.D and Coefficient
X cm X2
Variation of the given data, s2
4 16
X 60
X = = = 10 6 36
n 6
9 81
 (  X) 
2
1
S=
n
 X −
2

n


12 144

  13 169
16 256
1 (60) 2 
S=  702 − = 17 = 4.123cm
6 6  60 702

1 
 (  X)
2
 X X 2

S=
n −1   X −
2

n


 
n=6
1 (60) 2
S=  702 − = 20.4 = 4.517
5 6 
26
 Coefficient of Variation (CV)
• Always in percentage (%)
• Shows relative variability, that is, variability relative to the
magnitude of the data i.e variation relative to mean
• Can be used to compare two or more sets of data measured
in different units or same units but different average size

S
C.V =   .100%
X
27
Coefficient of Variation (CV)

X = 10
S = 4.123
 4.123 
CV =   100%=41.23%
 10 

28
Comparing Coefficient of Variation
Mr. Ali
AverageMarks out of 60 = X 1 =53
Standard deviation=S1 = 5
 S1  5 Mr. Ali is
CVALI =   100% = 100% = 9.43%
 X1  53 more
Consistent in
Mr.Zain performance
AverageMarks out of 80 = X 1 =72
Standard deviation=S1 = 10
 S1  10
CVALI =   100% = 100% = 13.88%
 X1  72
29
 Comparing Coefficient
of Variation
• Stock A:
o Average price last year = $50
o Standard deviation = $5

s $5
 
C V A =    100% =  100% = 10%
x  $50 Both stocks
have the same
• Stock B:
standard
o Average price last year = $100 deviation, but
o Standard deviation = $5 stock B is less
variable relative
to its price
s $5
C VB =    100% =  100% = 5%
x  $100
 Coefficient of Variation
Summary statistics for WEIGHT and HEIGHT (both ratio variables) of Pakistani adults in different units:
Weight Height Weight Height
Mean 160 pounds 66 inches SD 30 pounds 4 inches
72.6 kilograms 5.5 feet 13.6 kilograms 0.33 feet
0.08 tons 168 centimeters 0.015 tons 10.2 centimeters

Which variable [WEIGHT or HEIGHT] has greater dispersion? [No meaningful answer can be given]
Which variable has greater dispersion relative to its average, e.g., greater Coefficient of Dispersion (SD relative
to mean)?

 S1  30 13.6 0.015
CVWeight =  100% = = = = 18.7%
 X1  160 72.6 0.08
 S1  4 0.33 10.2
CVHeight =  100% = = = = 6.1%
 X1  66 5.5 168

Note that the Coefficient of Variation is a pure number, not expressed in any units and is the same whatever
units the variable is measured in.
Choosing Appropriate
Measure of Variability
• If data are symmetric, with no serious outliers, use range and
standard deviation.
• If data are skewed, and/or have serious outliers, use IQR.
• If comparing variation across two data sets, use coefficient of
variation (C.V)

32