CHAPTER IV

MEASURES OF DISPERSION

1
MEASURES OF DISPERSION

• Two facts:
• The distribution may have similar
averages, but the degree of
scatterdness in the individual values
is different.
• The distribution may have different
averages, but the variation among
the values may be quite less

2
 Production of Teff (In Metric Tones Per
hectare) in three fields.
Year Field’A’(X1) Field Field`C’(X3)
`B’(x2)
1984 8 6 2
1985 8 13 8
1986 8 8 30
1987 8 13 28
1988 8 15 10
1989 8 11 2
1990 8 7 0
1991 8 6 0
1992 8 0 0
1993 8 1 0
X1 = 80 X2 = 80 X3 = 80 3
4
 Year
Firms
Yassem Variatio Tianes Variation WinnerC Variatio
n ap n
X1=24 X2=34 X3=168

1984 6 -18 16 -18 150 -18

1885 10 -14 20 -14 154 -14
1986 14 -10 24 -10 158 -10
1987 18 -6 28 -6 162 -6
1988 22 -2 32 -2 166 -2
1989 26 +2 36 +2 170 +2
1990 30 +6 40 +6 174 +6
1991 34 +10 44 +10 178 +10
1992 38 +14 48 +41 182 +14
1993 42 +18 52 +18 186 +18
the average production of the firm’s Yassem, Tianes, and WinnerCap is
x1 = =0 x2 = =0 x3 = = 05
24,000 computers, 34,000 computers, and 168000 computers
Types of Measures of Dispersion
1. Distance Measures/Positional Measures
2. Measures of deviations
We can use
Numerical methods
(i) Range
(ii) Quartile deviation,
(iii) Mean deviation
(iv) Standard deviation.
Graphical Methods
(v) Normal Distribution Curve (Lorenz Curve)

6
 The range
• Simply the difference between the largest and
smallest values in a set of data
• Useful for: daily temperature fluctuations or share
price movement
• Is considered primitive as it considers only the
extreme values which may not be useful
indicators of the bulk of the population.
• The formula is:
Range = largest observation - smallest
observation
For ensuring comparability, relative measure of
range, known as coefficient of range is used.

7
 Interquartile range
• Measures the range of the middle 50% of the
values only
• Is defined as the difference between the upper
and lower quartiles
Inter-quartile range = upper quartile - lower
quartile
= Q3 - Q1

8
 QUARTILE DEVIATION
• Is the average absolute difference
between the third (upper) quartile
and the first (lower) quartile of the
frequency distribution.

9
10
11
 COEFFICIENT OF QUARTILE DEVIATION
• The coefficient of quartile deviation
(sometimes called the quartile coefficient
of dispersion) allows you to compare
dispersion for two or more sets of data.
The formula is:

If one set of data has a larger coefficient

of quartile deviation than another set,
then that data set’s interquartile
dispersion is greater.
12
 The mean deviation
• `average deviation’ is the absolute
average of the deviations taken from
a measure of central Tendency.
• 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.
13
 Mean deviation
 The mean of the absolute
deviations

14
• Example 2 Calculate the mean deviation
from
 Arithmetic mean, Mode and ,
Median
 Marks (out of 25) 7, 4, 10, 9, 15, 12, 7, 9,
7. If the marks are all doubled and taken
out of 50 will the variation in marks
increase? Given reasons.

15
16
 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 values—easier to use in further
calculations

17
 Standard deviation of a population δ

• Every observation in the population

is used.
• The square of the population
standard deviation is called the
variance.
 x  x 
2

Stan dard deviation δ 

N

Variance δ 2
18
 Standard deviation of a sample ---s

• In practice, most populations are

very large and it is more common to
calculate the sample standard
deviation.
 x  x 
2

Sample stan dard deviation s 

n 1

• Where: (n-1) is the number of observations in the sample

19
To calculate standard deviation

1. Calculate the mean x

2. Calculate the residual for each x x x

3. Square the residuals ( x  x )2

4. Calculate the sum of the squares


 x x 
2

 x  x 
2
5. Divide the sum in Step 4 by (n- 1)
N

6. Take the square root of quantity in Step 5  x  x 

2

20
• Example 1 Find the standard
deviations of the following.
14 15 17 22 23 25 24 16
18 26

Solution
• Computation of standard deviation and
coefficient of standard deviation.

21
x

14 -6 36
15 -5 25
17 -3 9
22 2 4
23 3 9

 x  x 
25 5 25 2

24 4 16 Stan dard deviation δ 

N
16 -4 16
18 -2 4
26 6 36
x = 200

22
• Group Discrete and Continuous
Series: When deviations are
measured from Actual arithmetic
mean:
• Standard deviation from a population

23
 • The standard deviation is the absolute measure of
dispersion. Its relative measure is called the
standard coefficient of dispersion or coefficient of
standard deviation.

• A Distribution is consistent and less variable, if its

coefficient of standard deviation is low.

24
 COEFFICIENT OF VARIATION
• The relative measure of standard deviation
• Is the percentage variation in the mean the
standard deviation (Coefficient of Standard
Deviation) being treated as the total variation in
the mean.
• It is used to measure the consistency and
variability or uniformity of two or more
distributions.
• Lower value of the coefficient of variation
indicates higher consistency, more uniformity,
and lower variability.

25
 VARIANCE
• It is the square of standard deviation (2).
• The variance is “The mean of the squared
deviations about the mean of a series”
Thus symbolically variance may be
expressed as:

26
 COMBINED STANDARD DEVIATION
• Is a single standard deviation representing two or
more distributions.

 and number of observation for each

population

27
Example: From the analysis of monthly
wages paid to employees in two service
organizations X and Y, the following results
were obtained
Firm X Firm Y

Number of Employees 550 650

Average monthly wage Br 5000 Br 4500

Variance of the distribution of Br 900 Br 1600
wages

i. Which organization pays a larger amount as monthly

wages?
ii. In which organization is there greater variability in
individual wages of all the wage earners taken
together? 28
Solution:
i. For finding out which
organization X or Y pays larger amount of
monthly wages, we have to compare the
total wages:
• Total wage bill paid monthly by X and Y is

• Organization Y pays a larger amount as

monthly wages as compared to
organization X.

29
• For calculating the combined
variance, we will first calculate the
combined mean
• Combined Mean

• Combined Standard Deviation

30
31
 Measures of Shape
• Skewness
 Absence of symmetry
 Extreme values in one side of a
distribution
• Kurtosis
 Peakedness of a distribution
• Box Plots
 Graphic display of a distribution
 Reveals skewness
32
 Skewness

Mean Mode Mean Mean

Mode
Median
Median Mode Median

Negatively Symmetric Positively

Skewed (Not Skewed) Skewed

Slide 3-33
• µ1 = First moment is mean

• µ2 = Second moment is the variance

• µ3 = Third moment about mean

• µ4 = Forth moment about mean

34
• Measure of Skewness:

• Coefficient of skewness

• If S < 0, the distribution is negatively

skewed (skewed to the left).
• If S = 0, the distribution is symmetric
(not skewed).
• If S > 0, the distribution is positively
skewed (skewed to the right).

35
 Coefficient of Skewness
 23
1
 2
26  3
29

M
d1 26 M
d2 26 M
d3 26
 1
12.3  2
12.3  3
12.3


3 1  M 
d1 
3 2  M d2  
3 3  M d3 
S 1

 S 2

 S 3


1 2 3

323  26 326  26 329  26

  
12.3 12.3 12.3
 0.73 0 0.73
Slide 3-36
 KURTOSIS
• Peakedness of a distribution
– Leptokurtic: high and thin
– Mesokurtic: normal in shape
– Platykurtic: flat and spread out

Leptokurtic

Mesokurti
c Platykurtic

Slide 3-37
 Measures of Kurtosis

β2 = µ4/µ22
• µ4 = Forth moment about mean

• µ2 = Second moment about mean

• Interpretation
 If β2 < 3 Curve is Leptokurtic
 If β2 = 3 Curve is Mesokurtic
 If β2 > 3 Curve is PlatyKurtic
38
 Further Moments of the
Distribution
• There are further statistics that describe the
shape of the distribution, using formulae that
are similar to those of the mean and variance
• 1st moment - Mean (describes central value)
• 2nd moment - Variance (describes dispersion)
• 3rd moment - Skewness (describes
asymmetry)
• 4th moment - Kurtosis (describes peakedness)

39
 Skewness:
Skewness: BoxBox Plots,
Plots, and
and
Coefficient
Coefficient of
of Skewness
Skewness
S<0 S=0 S>0

Negatively Symmetric Positively

Skewed (Not Skewed) Skewed
Slide 3-40
41