Lecture-2

Measures of Dispersion
Learning Objectives

After careful study of this lecture, student will be able to do the following:

1. Find variability among the data.

2. Compare the efficiency of the methods using to calculate variability of data.

3. Recognize the limitations of the methods.

4. Determine uniformness of the data.

5. Apply the methods to real life problems.

Definition:
Measures of dispersion or variation measures the extent of variation or deviation of individual values
from central value. It helps us to measure variation among the data.
Batsman 1 49 50 55 54 𝐱̅ = 52
Batsman 2 10 68 90 40 𝐱̅ = 52
Which batsman is more consistent?
Types:
Different types of measures of dispersion or variation are:
1. The range
2. The inter-quartile range or quartile deviation
3. The mean deviation
4. The variance
5. The standard deviation
Absolute Measures of Variation: Absolute measures of variation are expressed in the same
statistical unit in which the original data are given.
Ex: Salary range between a manager and average salary of workers.
Relative Measures of Variation: A measure of relative variation is the ratio of a measure of
absolute variation to an average. It also called coefficient of variation.
Ex: The percentage of salary a manager gets more from the average salary of workers.
Absolute Measures of Variation
Range:
The range is the absolute difference between the largest value and the smallest value in the set of
data. Symbolically
1
Range R = L – S
Where L= Largest Value S= Smallest Value
Example: The following are the prices of shares of a company from Saturday to Thursday:
Day Sat Sun Mon Tue Wed Thu
Price(tk) 200 210 208 160 220 250

Solution:
Range R = L – S = 250 – 160 = 90tk
 In the frequency distribution, range is calculated by taking the difference between the lower limit
of the lowest class and upper limit of the highest class.
Example: Calculate the range of the following data
Profit(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of Companies 200 210 208 160 220

Solution:
Range R = L – S = 60 – 10 = 50 lakh
Limitation:
Range cannot tell us anything about the character in the distribution within two extreme
observations.
Data 1 6 46 46 46 46 46 46 R = 40
Data 2 6 6 6 6 46 46 46 R = 40
Data 3 6 10 15 25 36 39 46 R = 40

 In all the three series of data range is same (i.e., 40), but it does not mean that the distribution
of data are same.
Interquartile range or quartile deviation:
Interquartile range or quartile deviation represents the difference between the third quartile Q3 and
the first quartile Q1 . Symbolically
Q3 − Q1
Q. D = Q.D = Quartile deviation
2

𝟓𝟎%

Q1 Q3
Q.D

Range
2
 When quartile deviation is very small it describes small variation of the central 50% observations,
and a high quartile deviation means that the variation among central observations is large.
i ×N
− p.c.f
4
Quartiles Qi = L + ×h i = 1, 2, 3
f
𝐢 ×𝐍
Quartile class identified by 𝐐𝐢 = th observation.
𝟒

Example: The profits earned by 100 companies are given below:

Profits (lakhs) 20-30 30-40 40-50 50-60 60-70 70-80 80-90 90-100

No of Companies 4 8 18 30 15 10 8 7
i. Calculate the range within which middle 50% companies fall.
ii. Calculate quartile deviation.
Solution:
Profits (lakhs) No of Companies Cumulative frequency
20-30 4 4
30-40 8 12
40-50 18 30
50-60 30 60
60-70 15 75
70-80 10 85
80-90 8 93
90-100 7 100
N = 100
1 ×100
The first quartile Q1 = = 25th observation. 25th observation lies in 40 - 50.Quartile class is 40 -
4

50.
i ×N 1 ×100
− p.c.f − 12
4 4
By using Qi = L + × h, we get Q1 = 40 + × 10 = 47.22 lakhs
f 18
3 ×100
The third quartile Q3 = = 75 th observation; 75 th observation lies in 60 - 70.Quartile class is
4
3 ×100
− 60
4
60 - 70. So, Q3 = 60 + × 10 = 70 lakhs
15

Range within which middle 50% companies fall = Q3 − Q1 = 70 − 47.22 = 22.78

Q3 − Q1 70− 47.22
Quartile deviationQ. D = = = 11.39 lakhs
2 2

Example: Based on the frequency distribution given below calculate quartile deviation.
Tax Paid(Lakh) 5-10 10-15 15-20 20-25 25-30 30-35 35-40
No of Managers 18 30 46 28 20 12 6
ANS: 𝐐𝟏 = 𝟏𝟑. 𝟔𝟕, 𝐐𝟑 = 𝟐𝟒. 𝟔𝟒, 𝐐. 𝐃 = 𝟓. 𝟒𝟖𝟓
Example: For the following data
Age (yr) 0-10 10-20 20-30 30-40 40-50 50-60 60-70
No of Members 6 5 8 15 7 6 3
3
i. Calculate the range within which middle 50% members fall.
ii. Calculate quartile deviation.
Limitation:
Quartile deviation ignores 50% items, i.e., the first 25% and the last 25%. Since it does not depend
upon every observation it is not regarded as good method of measuring variation.
Mean Deviation:
Mean deviation is an average of absolute deviation of each observation from the mean. It is obtained
by calculating the absolute deviation of each observation from the mean, and then averaging the
deviations by taking their mean.
Calculation of mean deviation (Ungrouped Data)
For ungrouped data
∑|xi − x̅|
M. D =
N
Example: Based on the frequency distribution given below calculate mean deviation.
Batsman 1 49 50 55 54
Solution:
Batsman 1
xi x̅ |xi − x̅|
49 3
50 2 |49-52|
55 208 3
= 52
54 4 2
∑|xi − x̅| = 10
∑|xi − x̅| 10
M. D = = = 2.5
N 4
Example: Based on the frequency distribution given below calculate mean deviation.
Batsman 2 10 68 90 40
Solution:
Batsman 2
xi x̅ |xi − x̅|
10 42
68 16
90 208 38
= 52
40 4 12
∑|xi − x̅| = 108
∑|xi − x̅| 108
M. D = = = 27
N 4

4
Calculation of mean deviation (Grouped Data)
For grouped data
∑ fi |xi − x̅|
M. D =
N
Where
∑ fi ui
x̅ = Arithmetic mean. (x̅ = A + × h)
N

xi = Mid values of each class.

N = The total frequency.
Example: Calculate mean deviation for the following data
Sales(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of days 3 6 11 3 2

Solution:

Sales Mid value xi No of ui fi ui x̅ |xi − x̅| fi |xi − x̅|

days fi ∑ fi ui
=A+ ×h
N
10-20 15 3 -2 -6 18 54
20-30 25 6 -1 -6 −5 8 48
35 + × 10
25
30-40 35 11 0 0 = 33 2 22
40-50 45 3 +1 +3 12 36
50-60 55 2 +2 +4 22 44
N = 25 ∑ fi ui = -5 ∑ fi |xi −
x̅|=204
∑ fi |xi −x̅| 204
M. D = = = 8.16 lakhs
N 25

Example: Calculate mean deviation for the following data

Marks 0-10 10-20 20-30 30-40 40-50 50-60 60-70
No of Students 6 5 8 15 7 6 3

Solution:

Marks Mid value xi fi ui fi ui x̅ |xi − x̅| fi |xi − x̅|

0-10 5 6 -3 -18 28.4 170.4
10-20 15 5 -2 -10 18.4 92
−8
20-30 25 8 -1 -8 35 + 8.4 67.2
50
30-40 35 15 0 0 × 10 1.6 24
40-50 45 7 +1 +7 = 33.4 11.6 81.2
50-60 55 6 +2 +12 21.6 129.6
60-70 65 3 +3 +9 31.6 94.8
N = 50 ∑ fi ui = -8 ∑ fi |xi − x̅|= 659.2

5
 ∑ fi |xi − x̅| 659.2
M. D = = = 13.184
N 50
Example: Calculate mean deviation for the following data
Class 0-6 6-12 12-18 18-24 24-30
No of days 8 10 12 9 5
ANS: 6.3
Limitations:
In calculation algebraic signs are ignored while taking the deviations of the items. If the signs of the
deviations are not ignored, the net sum of the deviations will be zero.
Variance:
Variance is the average of the squares of the deviations of the given values from their arithmetic
mean. It is denoted by σ2
Calculation of variance (Ungrouped Data)
For ungrouped data, variance
∑(xi − x̅)2
σ2 =
N
Example: Find variance from the weekly wages of 10 workers working in a factory.
1320 1310 1315 1322 1326 1340 1325 1321 1320 1331

Solution:
xi x̅ (xi − x̅) (xi − x̅)2
1320 -3 9
1310 -13 169
1315 -8 64
1322 13230 -1 1
= 1323
1326 10 +3 9
1340 +17 289
1325 +2 4
1321 -2 4
1320 -3 9
1331 +8 64
∑(xi − x̅)2 = 622
∑(xi − x̅)2 622
σ2 = = = 62.2 tk
N 10
Calculation of variance (Grouped Data)
For grouped data, variance
∑ fi (xi − x̅)2
σ2 =
N
2
2
∑ fi ui 2 ∑ fi ui
or σ =[ −( ) ] × h2
N N

6
Example: Calculate variance for the following data
Profit(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 6 4
Solution:
Profit Mid value xi fi ui fi ui fi ui 2

10-20 15 8 -2 -16 32
f1 =8, u1 =-2
20-30 25 12 -1 -12 12 8× (−2)2
30-40 35 20 0 0 0
40-50 45 6 +1 +6 6
50-60 55 4 +2 +8 16
N = 50 ∑ fi ui = -14 ∑ fi ui 2 = 66

2
2
∑ fi ui 2 ∑ fi ui 66 −14 2
σ =[ −( ) ] × h2 = [ − ( ) ] × 102 =
N N 50 50

= 1.2416 × 100 = 124.16 lakhs

Example: Calculate variance for the following data
Profit(Lakhs) 0-10 10-20 20-30 30-40 40-50
No of Companies 6 25 36 20 13
Solution:
Profit Mid value xi fi ui fi ui fi ui 2
0-10 5 6 -2 -12 24
10-20 15 25 -1 -25 25
20-30 25 36 0 0 0
30-40 35 20 +1 +20 20
40-50 45 13 +2 +26 52
N = 100 ∑ fi ui = 9 ∑ fi ui 2 = 121

2
2
∑ fi ui 2 ∑ fi ui 2
121 9 2
σ =[ −( ) ]×h =[ −( ) ] × 102 =
N N 100 100

= 1.2019 × 100 = 120.19 lakhs

Example: Calculate variance for the following data
Profit(Lakhs) 0-10 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 30 20 10
ANS: 192.155

7
Example: Calculate variance for the following data
Tax (Thousand) 5-10 10-15 15-20 20-25 25-30 30-35 35-40
No of Managers 18 30 46 28 20 12 6
ANS: 60.93
Standard Deviation:
Standard deviation is the positive square root of the average of the squares of the deviations of the
given values from their arithmetic mean. It is denoted by σ. That is
Standard deviation S.D or σ = √σ2 = √variance
Calculation of standard deviation (Ungrouped Data)
For ungrouped data, standard deviation

∑(xi − x̅)2
σ=√
N

Example: Find standard deviation from the weekly wages of 10 workers working in a factory.
1320 1310 1315 1322 1326 1340 1325 1321 1320 1331

Solution:
xi x̅ (xi − x̅) (xi − x̅)2
1320 -3 9
1310 -13 169
1315 -8 64
1322 13230 -1 1
= 1323
1326 10 +3 9
1340 +17 289
1325 +2 4
1321 -2 4
1320 -3 9
1331 +8 64
∑(xi − x̅)2 = 622

∑(xi − x̅)2 622

σ=√ =√ = √62.2 = 7.89
N 10

Calculation of standard deviation (Grouped Data)

For grouped data, standard deviation

∑ fi (xi − x̅)2
σ=√
N

2
∑ fi ui 2 ∑ fi u
or σ=√ −( ) ×h
N N
8
Example: Calculate standard deviation for the following data
Profit(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 6 4
Solution:
Profit Mid value xi fi ui fi ui fi ui 2
10-20 15 8 -2 -16 32
20-30 25 12 -1 -12 12 f1 =8, u1 =-2
30-40 35 20 0 0 0 8× (−2)2
40-50 45 6 +1 +6 6
50-60 55 4 +2 +8 16
∑ fi ui = -14 2
∑ fi ui = 66
N = 50

2
∑ fi ui 2 ∑ fi ui 66 −14 2
σ=√ −( ) ×h=√ −( ) × 10 = 11.14 lakhs
N N 50 50

Example: Calculate standard deviation for the following data

Profit(Lakhs) 0-10 10-20 20-30 30-40 40-50
No of Companies 6 25 36 20 13
Solution:
Profit Mid value xi fi ui fi ui fi ui 2
0-10 5 6 -2 -12 24
10-20 15 25 -1 -25 25
20-30 25 36 0 0 0
30-40 35 20 +1 +20 20
40-50 45 13 +2 +25 52
∑ fi ui = 9 2
∑ fi ui = 121
N = 100
2
∑ fi ui 2 ∑ fi ui 121 9 2
σ=√ −( ) ×h= √ −( ) × 10 = 10.96 lakhs
N N 100 100

Example: An analysis of production rejects resulted in the following data

Reject amount 21-25 26-30 31-35 36-40 41-45 46-50 51-55
No of Operators 5 15 28 42 15 12 3
Calculate mean and standard deviation.
Solution: Using class boundaries we get
Reject Mid value xi fi ui fi ui fi ui 2
amount
20.5-25.5 23 5 -3 -15 45
25.5-30.5 28 15 -2 -30 60
30.5-35.5 33 28 -1 -28 28
35.5-40.5 38 42 0 0 0
40.5-45.5 43 15 +1 +15 15
45.5-50.5 48 12 +2 +24 48
50.5-55.5 53 3 +3 +9 27

9
 N = 120 ∑ fi ui = -25 ∑ fi ui 2 = 223
∑ fi ui −25
Mean:x̅ = A + × h = 38 + 120 × 10 = 36.96
N

∑ fi ui 2 ∑ fi ui 2 223 −25 2
Standard deviation:σ = √ −( ) × h = √120 − ( 120 ) × 5 = √1.858 − .043 × 5 = 6.375
N N

Example: Calculate standard deviation for the following data

Profit(Lakhs) 0-10 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 30 20 10
ANS: 13.862
Example: Calculate standard deviation for the following data
Tax (Thousand) 5-10 10-15 15-20 20-25 25-30 30-35 35-40
No of Managers 18 30 46 28 20 12 6
ANS: 7.806

 x̅ ± σ covers 68.27% observations.

 x̅ ± 2σ covers 95.45% observations.
 x̅ ± 3σ covers 99.73% observations.

Example: The breaking strength of 80 test pieces of a certain alloy is give in the following table,
the unit being given to the nearest pounds per square inch.
Breaking strength 44-46 46-48 48-50 50-52 52-54
No of pieces 3 24 27 21 5
Calculate the average breaking strength of the alloy and the standard deviation. Calculate the
percentage of observations lying between mean ± 2σ.
Solution:
Breaking strength Mid value xi fi ui fi ui fi ui 2
44-46 45 3 -2 -6 12
46-48 47 24 -1 -24 24
48-50 49 27 0 0 0
50-52 51 21 +1 +21 21

52-54 53 5 +2 +10 20
N = 80 ∑ fi ui = 1 ∑ fi ui 2 = 77
∑ fi ui 1
x̅ = A + × h = 49 + × 2 = 49.025
N 80

10
 2
∑ fi ui 2 ∑ fi ui 77 1 2
σ= √ −( ) ×h= √ −( ) ×2
N N 80 80

= 1.96
Now x̅ ± 2σ = 49.025 ± 2(1.96) = 45.105 to 52.945 = 45 to 53 (approx. ). We have to calculate the
percentage of items lying between 45 and 53. Since the numbers are equally distributed, then the
frequency at 45 be 1.5 and the frequency at 53 be 2.5.
Thus the total frequency between 45 and 53 is (1.5 + 24 + 27 + 21 + 2.5) = 76. The percentage is
76
× 100 = 95. Thus there are 95 percent observations lying between mean ± 2σ.
80

Relative Measures of Variation

Coefficient of Variance:
Measures of variance discussed above are absolute measures. One of the relative measure is
known as coefficient of variance. A coefficient of variance is computed as a percentage of the
standard deviation of the distribution to the mean of the same distribution. This measure represents
the spread of the distribution relative to the mean of the same distribution. Symbolically:
σ
C. V = × 100
x̅
Where σ =Standard deviation, x̅ = Arithmetic mean
Consider a statistic of height and weight of the 150 children:
Height Weight
Mean 40 inch 10 kg
S.D 5 inch 2 kg
C.V 12.5% 20%
Which one has more variability among the children, height or weight?
 The coefficient of variance helpful in comparing the relative variation in several data set
having different measure of unit.
Consider the blood pressures of a group of patient were measured at two levels:
Systolic (mm) Diastolic (mm)
Average 130 60
S.D 15 8
C.V 11.5% 13.3%
Which pressure shows greater variability among the patients?
 The coefficient of variance helpful in comparing the relative variation in several data set having
different means and different standard deviations.

11
Calculation of coefficient of variance (Ungrouped Data)
For ungrouped data, coefficient of variance
σ ∑(xi −x̅)2 ∑ xi
C. V = x̅ × 100; where σ=√ and x̅ =
N N

Example: Find coefficient of variance from the price of a company share during the last 10 months
in Dhaka stock exchange.
105 120 115 118 130 127 109 110 104 112
Solution:
xi x̅ (xi − x̅) (xi − x̅)2
105 -10 100
120 +5 25
115 0 0
118 +3 9
130 1150 +15 225
= 115
127 10 +12 144
109 -6 36
110 -5 25
104 -11 121
112 -3 9
∑(xi − x̅)2 = 694

∑(xi −x̅)2 694

Standard deviation σ = √ = √ 10 = √69.4 = 8.33 tk
N

σ 8.33
C. V = × 100 = × 100 = 7.24 %
x̅ 115
Example: Find coefficient of variance from the price of a company share during the last 10 months
in Chittagong stock exchange.
108 117 120 130 100 125 125 120 110 135
Solution:
xi x̅ (xi − x̅) (xi − x̅)2
108 -11 121
117 -2 4
120 +1 1
130 1190 +11 121
100 = 119 -19 361
10
125 +6 36
125 +6 36
120 +1 1
110 -9 81
135 +16 256
∑(xi − x̅)2 = 1018

12
 ∑(xi −x̅)2 1018
Standard deviation σ = √ =√ = √101.8 = 10.09 tk
N 10

σ 10.09
C. V = × 100 = × 100 = 10.09 %
x̅ 119
 Since the coefficient of variance of Dhaka is less, therefore it is safe to invest in Dhaka stock
exchange.
Calculation of coefficient of variance (Grouped Data)
For grouped data, coefficient of variance
σ
C. V = × 100
x̅
∑ fi ui 2 ∑ fi ui 2 ∑ fi ui
Where σ=√ −( ) × h and x̅ = A + ×h
N N N

Example: Calculate standard deviation and coefficient of variance for the following data
Profit(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 6 4
Solution:
Profit Mid value xi fi ui fi ui fi ui 2

10-20 15 8 -2 -16 32
20-30 25 12 -1 -12 12
30-40 35 20 0 0 0
40-50 45 6 +1 +6 6
50-60 55 4 +2 +8 16
N = 50 ∑ fi ui = -14 ∑ fi ui 2 = 66

∑ fi ui −14
Meanx̅ = A + × h = 35 + × 10 = 32.2 lakh
N 50

∑ fi ui 2 ∑ fi ui 2 66 −14 2
Standard deviationσ = √ −( ) × h = √50 − ( 50 ) × 10 = 11.14 lakh
N N

σ 11.14
C. V = × 100 = × 100 = 34.6 %
x̅ 32.2
Example: Calculate standard deviation and coefficient of variance for the following data
Profit(Lakhs) 0-10 10-20 20-30 30-40 40-50
No of Companies 6 25 36 20 13

Solution:
Profit Mid value xi fi ui fi ui fi ui 2
0-10 5 6 -2 -12 24
10-20 15 25 -1 -25 25
20-30 25 36 0 0 0
13
 30-40 35 20 +1 +20 20
40-50 45 13 +2 +25 52
N = 100 ∑ fi ui = 9 ∑ fi ui 2 = 121
∑ udi 9
Mean:x̅ = A + × h = 25 + 100 × 10 = 25.9 lakh
N

∑ udi 2 ∑ fi ui 2 121 9 2
Standard deviation:σ = √ −( ) × h = √100 − (100) × 10 = 10.96 lakh
N N

σ 10.96
C. V = × 100 = × 100 = 42.32 %
x̅ 25.9
Example: An analysis of production rejects resulted in the following data
Reject amount 21-25 26-30 31-35 36-40 41-45 46-50 51-55
No of Operators 5 15 28 42 15 12 3
Calculate standard deviation and coefficient of variance.
Solution: Using class boundaries we get
Reject amount Mid value xi fi ui fi ui fi ui 2

20.5-25.5 23 5 -3 -15 45
25.5-30.5 28 15 -2 -30 60
30.5-35.5 33 28 -1 -28 28
35.5-40.5 38 42 0 0 0
40.5-45.5 43 15 +1 +15 15
45.5-50.5 48 12 +2 +24 48
50.5-55.5 53 3 +3 +9 27
N = 120 ∑ fi ui = -25 ∑ fi ui 2 = 223
∑ fi ui −25
Mean:x̅ = A + × h = 38 + 120 × 10 = 36.96
N

∑ fi ui 2 ∑ fi u 2 223 −25 2
Standard deviation:σ = √ −( ) × h = √120 − ( 120 ) × 5 = √1.858 − .043 × 5 = 6.375
N N

σ 6.375
C. V = × 100 = × 100 = 17.25 %
x̅ 36.96
For Practice
1. Calculate standard deviation and coefficient of variance for the following data
Profit 0-10 10-20 20-30 30-40 40-50 50-60
No of Companies 8 12 20 30 20 10
ANS: 𝐱̅ = 𝟑𝟐. 𝟐, 𝛔 = 𝟏𝟑. 𝟖𝟔𝟐, 𝐂. 𝐕 = 𝟒𝟑. 𝟎𝟓%
2. Calculate standard deviation and coefficient of variance for the following data
Tax (Thou) 5-10 10-15 15-20 20-25 25-30 30-35 35-40
No of Managers 18 30 46 28 20 12 6
ANS: 𝐱̅ = 𝟏𝟕. 𝟔, 𝛔 = 𝟕. 𝟖𝟎𝟔, 𝐂. 𝐕 = 𝟒𝟒. 𝟑𝟓%
3. Calculate standard deviation and coefficient of variance for the following data

14
 Wages 10-20 20-30 30-40 40-50 50-60 60-70 70-80 80-90
No of Workers 1 2 4 13 21 9 6 4
ANS: 𝐱̅ = 𝟓𝟓. 𝟑𝟑, 𝛔 = 𝟏𝟒. 𝟖𝟑, 𝐂. 𝐕 = 𝟐𝟔. 𝟖%
4. Calculate standard deviation and coefficient of variance for the following data
Profits 20-30 30-40 40-50 50-60 60-70 70-80 80-90 90-100
No of Companies 4 8 18 30 15 10 8 7
ANS:𝐱̅ = 𝟓𝟗. 𝟏, 𝛔 = 𝟏𝟕. 𝟓𝟔, 𝐂. 𝐕 = 𝟐𝟗. 𝟕𝟏%
5. Calculate standard deviation and coefficient of variance for the following data
Weights 210-215 215-220 220-225 225-230 230-235 235-240 240-245 245-250
No of Boys 8 13 16 29 14 10 7 3
ANS:𝐱̅ = 𝟐𝟐𝟕. 𝟓𝟓, 𝛔 = 𝟖. 𝟕𝟑𝟐, 𝐂. 𝐕 = 𝟑. 𝟖𝟒%
6. Calculate standard deviation and coefficient of variance for the following data
Turnover(Lakh) 5-10 10-15 15-20 20-25 25-30 30-35 35-40
No of Companies 8 18 42 62 30 10 4
ANS:𝐱̅ = 𝟐𝟏. 𝟑𝟓, 𝛔 = 𝟔. 𝟑𝟕𝟓, 𝐂. 𝐕 = 𝟐𝟗. 𝟖𝟔%
Empirical Relation between Measures of variation

𝟐
Quartile Deviation (Q.D) = 𝟑 Standard Deviation (𝛔)

𝟒
Mean Deviation (M.D) = Standard Deviation (𝛔)
𝟓

𝟓
Quartile Deviation (Q.D) = 𝟔 Mean Deviation (M.D) (𝝈)

Example: Calculate standard deviation and then calculate mean deviation using empirical relation
for the following data
Profit(Lakhs) 10-20 20-30 30-40 40-50 50-60
No of 8 12 20 6 4
Companies
Solution:
Profit Mid value xi fi ui fi ui fi ui 2
10-20 15 8 -2 -16 32
20-30 25 12 -1 -12 12
30-40 35 20 0 0 0
40-50 45 6 +1 +6 6
50-60 55 4 +2 +8 16
N = 50 ∑ fi ui = -14 ∑ fi ui 2 = 66

15
 ∑ fi ui 2 ∑ fi ui 2 66 −14 2
Standard deviation:σ = √ −( ) × h = √50 − ( 50 ) × 10 = 11.14 lakh
N N
4 4
Mean deviation:M. D = × σ = 5 × 11.14 = 8.912 lakh
5

Example: Calculate mean deviation and then calculate quartile deviation using empirical relation
for the following data
Marks 0-10 10-20 20-30 30-40 40- 50- 60-70
50 60
No of Students 6 5 8 15 7 6 3
Solution:
Marks Mid value xi fi ui fi ui x̅ |xi − x̅| fi |xi − x̅|
0-10 5 6 -3 -18 28.4 170.4
10-20 15 5 -2 -10 18.4 92
20-30 25 8 -1 -8 −8 8.4 67.2
30-40 35 15 0 0 35 + 1.6 24
50
40-50 45 7 +1 +7 × 10 11.6 81.2
= 33.4
50-60 55 6 +2 +12 21.6 129.6
60-70 65 3 +3 +9 31.6 94.6
N = ∑ fi ui = -8 ∑ fi |xi − x̅|=
50 658.4

∑ fi |xi − x̅| 658.4

M. D = = = 13.168
N 50
5 5
Quartile deviationQ. D = 6 × M. D = 6 × 13.168 = 10.97

16