Ex. No.

- 3 Measures of Central Tendency

- (Grouped and ungrouped data)
Arithmetic Mean, Geometric Mean, Harmonic Mean, Median, Mode

Raw data (or) Grouped data

Ungrouped data Discrete data Continuous data
Observations along with Class intervals along with frequencies
frequencies Exclusive Inclusive
x Frequency (f) Class Frequency (f) Class Frequency (f)
x1 f1 10-20 f1 10-19 f1
Observations only
x2 f2 20-30 f2 20-29 f2
x1, x2, x3,…, xn . . . . . .
. . . . . .
xn fn 90-100 fn 90-99 fn
Total f = N Total f= N Total f= N

Relationship between different averages:

i) In a symmetrical distribution, mean, median and mode will coincide.
i.e.) Mean = Median = Mode

ii) In an asymmetrical (skewed) distribution, these values will be different.

When positively skewed (skewed to the right) Mean > Median > Mode
When negatively skewed (skewed to the left) Mean < Median < Mode
iii) Mean – Mode = 3(Mean – Median)
iv) Mode = 3 Median – 2 Mean
v) If all the items in a distribution have the same value then, AM = GM = HM
vi) Generally, AM > GM > HM

15
 Formula:

S. Name of the Grouped data

Raw data
No. Measure Discrete data Continuous data
1 Arithmetic Population Mean, n
 fd 
Mean (AM) N fx i i A
 N 
C
X
i 1
(or) Mean i
i 1
N Where A = Assumed mean
(or) Average μ=
N Where mid x  A
(x ) d=
Sample Mean, N = Total frequency C
n
= f i N = f i
x
i 1
i
x= C = Class interval.
n
2 Geometric (x1, x2,…, xn)1/n  n   n 
Mean (GM)   f i log xi    f i log xi 
(or)
Anti log i 1  Anti log i 1 
n x 1 , x 2 ,…, x n (or)  N   N 
   
 n     
  log xi 
Antilog  i 1  Where x = mid value of
 n 
  class interval

3 Harmonic n N N
Mean (HM) n
1 n
fi n
fi
x
i 1
x
i 1
x
i 1
i i i

Where x = mid x
4 Median ( ~
x) Odd number  N  1
th
N 
 n  1
th   value  2  m
  item is the  2  L C
 2   f 
median  
Even number Where L = Lower limit of
the median class
The average of two
middle terms is the m = Cumulative frequency
median just before the median class
f = Frequency of the median
class
C = Class interval
N = Total frequency
5 Mode Maximum repeated Highest frequency of  f2 
value is the mode the item L C
 f1  f 2 
Where L = Lower limit of

16
 the modal class
f 1 = The frequency of the
class preceding the modal
class.
f 2 = The frequency of the
class succeeding the modal
class.
C = Class interval
(or)
 f1  f 0 
L C
 2 f1  f 0  f 2 
L => lower limit of modal
class
f 1 = frequency of modal
class
f 0 = frequency of before
modal class
f 2 = frequency of after
modal class

Example – (i) Arithmetic Mean (AM)

1. Raw data – Ungrouped data

The following data gives the yield of 5 paddy plants (gms/plant). Calculate average
paddy yield (gms/plant).
100 102 118 124 126
Solution:
n

x
i 1
i
Arithmetic Mean (AM) (or) Sample Mean (or) Average = x =
n
x1  x2  ...  xn 100  102  ...  126
= =
n 5
570
=  114 gms.
5

17
2. Grouped data – Discrete case
The following data gives the yield of 50 paddy plants (gms/plant). Calculate average
paddy yield(gms/plant).
Yield (gms) No. of paddy plants
(x) (f)
65 5
50 5
63 10
130 15
125 15
Total 50
Solution:
n n


i 1
f i xi fx
i 1
i i
Mean = x = n
=
f
N
i
i 1

f1 x1  f 2 x2  ....  f n xn
=
f1  f 2  ....  f n
n
Where N =  f i = f1+f2+….+fn = Total frequency
i 1

Yield (gms) No. of paddy plants

fx
(x) (f)
65 5 325
50 5 250
63 10 630
130 15 1950
125 15 1875
Total 50  fx = 5030
n

fx i i
5030
Mean = x = i 1
=  100.6 gm.
N 50
3. Grouped data – Continuous case
The following data gives the yield of 50 paddy plants (gms/plant). Calculate average
paddy yield(gms/plant).
Yield (gms) No. of paddy plants
(x) (f)
60 – 80 12

18
 80 – 100 13
100 – 120 10
120 – 140 10
140 – 160 5
Total 50
Solution:
 fd 
Mean = x = A   C
 N 
Where A = Assumed mean
mid x  A
d=
C
C = Class interval.
No. of paddy mid x  A
Yield (gms)
plants mid x d= fd
(x) C
(f)
60 – 80 12 70 –2 –24
80 – 100 13 90 –1 –13
100 – 120 10 110 0 0
120 – 140 10 130 1 10
140 – 160 5 150 2 10
Total 50 0 –17
 fd 
Mean = x = A   C
 N 
  17 
= 110     20 110  6.8  103.2 gm.
 50 

Example – (ii) Geometric Mean (GM)

1. Raw data – Ungrouped data

Find the geometric mean of the yield of Mangoes from 9 Mango Trees:
45 32 37 46 39 36 41 48 36
Solution:
Geometric Mean (GM) = n x1 x2 ......xn

= 9
45  32  37  46  39  36  41 48  36
But, obviously, it is a bit cumbersome to find the ninth root of a quantity. So we

19
 make use of logarithms, as shown below:
x log x
45 1.6532
32 1.5051
37 1.5682
46 1.6628
39 1.5911
36 1.5563
41 1.6128
48 1.6812
36 1.5563
14.3870
 n

  log xi 
Geometric Mean (GM) = Anti log i 1 
 n 
 
 
 14.3870 
= Anti log 
 9 
= Anti log1.5986 = 39.6826 = 40 (apprpx.)
Hint: Using calculator press (Shift + log) of 1.5986 buttons then get the Antilog.

2. Grouped data – Discrete case

The following data gives the yield of 50 paddy plants (gms/plant). Calculate
Geometric Mean.
Yield (gms) No. of paddy plants
(x) (f)
65 5
50 5
63 10
130 15
125 15
Total 50
Solution:
 n 
  f i log xi 
Geometric Mean (GM) = Anti log i 1 
 N 
 
 

20
 No. of paddy
Yield (gms)
plants log x f logx
(x)
(f)
65 5 1.8129 9.0646
50 5 1.6990 8.4949
63 10 1.7993 17.9934
130 15 2.1139 31.7092
125 15 2.0969 31.4537
Total 50 9.5221 98.7156
 n 
  f i log xi 
Geometric Mean (GM) = Anti log i 1 
 N 
 
 
 98.7156 
= Anti log  = Antilog (1.9743) = 94.2541
 50 
3. Grouped data – Continuous case
The following data gives the yield of 50 paddy plants (gms/plant). Calculate
Geometric Mean.
Yield (gms) No. of paddy plants
(x) (f)
60 – 80 12
80 – 100 13
100 – 120 10
120 – 140 10
140 – 160 5
Total 50
Solution:
 n 
  f i log xi 
Geometric Mean (GM) = Anti log i 1  where x = mid x
 N 
 
 
Yield (gms) No. of paddy plants
mid x log x f logx
(x) (f)
60 – 80 12 70 1.8451 22.1412
80 – 100 13 90 1.9542 25.4046
100 – 120 10 110 2.0414 20.4140
120 – 140 10 130 2.1139 21.1390
140 – 160 5 150 2.1761 10.8805

21
 Total 50 99.9793

 n 
  f i log xi 
Geometric Mean (GM) = Anti log i 1 
 N 
 
 
 99.9793 
= Anti log  = Antilog (1.9996) = 99.9080
 50 

Example – (iii) Harmonic Mean (HM)

1. Raw data – Ungrouped data

Daily income of 10 agricultural families in a village is given below:
85 70 15 75 500 8 45 250 40 36
Calculate Harmonic Mean.
Solution:
x 1/x
85 0.0118
70 0.0143
15 0.0667
75 0.0133
500 0.0020
8 0.1250
45 0.0222
250 0.0040
40 0.0250
36 0.0278
0.3121
n
Harmonic Mean (HM) = n
1
x
i 1 i

10
= = 32.0461
0.3121
2. Grouped data – Discrete case
The following data gives the yield of 50 paddy plants (gms/plant). Calculate

22
 Harmonic Mean.

Yield (gms) No. of paddy plants

(x) (f)
65 5
50 5
63 10
130 15
125 15
Total 50
Solution:
N
Harmonic Mean (HM) = n
fi
x
i 1 i

No. of paddy
Yield (gms)
plants f/x
(x)
(f)
65 5 0.0769
50 5 0.1000
63 10 0.1587
130 15 0.1154
125 15 0.1200
Total 50 0.5710
N
Harmonic Mean (HM) = n
fi
x
i 1 i

50
= = 87.5599
0.5710
3. Grouped data – Continuous case
The following data gives the yield of 50 paddy plants (gms/plant). Calculate
Harmonic Mean.
Yield (gms) No. of paddy plants
(x) (f)
60 – 80 12
80 – 100 13
100 – 120 10
120 – 140 10
140 – 160 5
Total 50

23
 Solution:
N
Harmonic Mean (HM) = n
where x = mid x
fi

i 1 x i

No. of paddy
Yield (gms)
plants mid x f/x
(x)
(f)
60 – 80 12 70 0.1714
80 – 100 13 90 0.1444
100 – 120 10 110 0.0909
120 – 140 10 130 0.0769
140 – 160 5 150 0.0333
Total 50 0.5170
N
Harmonic Mean (HM) = n
fi
x
i 1 i

50
= = 96.7046
0.5170

Example – (iv) Median

1. Raw data – Ungrouped data

i) Odd number of items given:
The following data gives the yield of Mangoes from 5 Mango Trees.
Calculate Median.
45 60 48 100 65
Solution:
First arrange the values in ascending order.
45 48 60 65 100

 n  1
th

If the data set contains odd number of items, say ‘n’ the value of   item
 2 
gives the median.

 n  1  5  1
th th

Median = ~
x=   item =   item = 3 value = 60 Mangoes
rd

 2   2 

24
 ii) Even number of items given:
The following data gives the yield of Mangoes from 6 Mango Trees.
Calculate Median.
45 60 48 100 86 65
Solution:
First arrange the values in ascending order.
45 48 60 65 86 100
If the data have even number of items, the median is the average of two middle
terms.
Median = ~
x = Average of two middle terms.
 60  65 
=  = 62.5
 2 
2. Grouped data – Discrete case
The following data gives the yield of Mangoes from 55 Mango Trees. Calculate
Median.
Yield of Mangoes No. of Mango Trees
(x) (f)
65 7
50 8
63 10
130 15
125 15
Total 55
Solution:

 N  1
th

Median = ~
x=   value
 2 
Where N = Total frequency.
First arrange the values in ascending order.
Yield of Mangoes No. of Mango Trees Cumulative
(x) (f) Frequency (CF)
50 8 8
63 10 18
65 7 25
125 15 40
130 15 55

25
 Total 55
 55  1 
th

Median = ~
x=  th
 value = 28 value
 2 
From the above table shows that all the items from 26 to 40 have their values
125. Since 28th item lies in this interval.  the value is 125. Median = 125.

3. Grouped data – Continuous case

The following data gives the yield of Mangoes from 150 Mango Trees. Calculate
Median.
Yield of Mangoes No. of Mango Trees
(x) (f)
60 – 80 22
80 – 100 38
100 – 120 45
120 – 140 35
140 – 160 20
Total 160
Solution:
N 
  m
x = L 2
Median = ~ C
 f 
 
Where L = Lower limit of the median class
m = Cumulative frequency just before the median class
f = Frequency of the median class
C = Class interval
N = Total frequency
Yield of Mangoes No. of Mango Trees Cumulative
(x) (f) Frequency (CF)
60 – 80 22 22
80 – 100 38 60 = m
L=100 – 120 45 = f 105
120 – 140 35 140
140 – 160 20 160

26
 Total 160
th th
N  160 
Median is the size of   item. (i.e.)   item = 80th item.
2  2 
This is lies between 100 – 120. Hence this is the median class of which lower limit
is L = 100, N = 160, m = 60, f = 45, C = 20.
N 
  m
x = L 2
Median = ~ C
 f 
 
 160 
  60 
x = 100   2
Median = ~   20 = 108.9
 45 
 

Example – (v) Mode

1. Raw data – Ungrouped data

Find the modal height (in cms.) from the heights of 20 seedlings.
60 65 64 58 69 72 64 64 65 60
61 67 64 63 67 64 68 63 64 66
Solution:
Here height 64" is repeated more number of times and hence modal
height (Mode) = 64".

2. Grouped data – Discrete case

The following data gives the heights of 50 seedlings (in inches). Calculate Mode.
Heights (in inches) No. of seedlings
(x) (f)
50 4
65 6
75 16
80 8
95 7
100 9

27
 Total 50
Solution:
Mode = 75.
Because it occurs maximum number of times (i.e.) 16 times in the frequency
distribution.
3. Grouped data – Continuous case

The following data gives the heights of 160 seedlings (in inches). Calculate Mode.

Heights (in inches) No. of seedlings

(x) (f)
60 – 80 22
80 – 100 f 1 = 38
L=100 – 120 f = 45
120 – 140 f 2 = 35
140 – 160 20
Total 160
Solution:

 f2 
Mode = L   C
 f1  f 2 
Where L = Lower limit of the modal class

f 1 = The frequency of the class preceding the modal class.

f 2 = The frequency of the class succeeding the modal class.

C = Class interval

Here the largest frequency is f = 45.

It is lies in the class interval 100 – 120 (i.e.) modal class.

The lower limit of the modal class is L = 100, f 1 = 38, f 2 = 35, f = 45, C = 20.

 35 
Mode = 20    20 = 109.6.
 38  35 

28
Exercise – 1(b) Measures of Central Tendency – (Grouped and ungrouped data)

1. The given data stands for the yield (in kgs.) of Wheat from 10 equal plots.
60 40 50 45 60 55 65 50 65 55
Calculate all the measures of central tendency and interpret the results (Verify the results
using MS Excel functions).
2. The following data stands for heights (in cms.) of 20 seedlings.
60 65 64 58 69 72 64 64 65 60
61 67 64 63 67 64 68 63 64 66
Calculate the Arithmetic Mean, Geometric Mean and Harmonic Mean and also check the
relationship between the above measures (Verify the results using MS Excel functions).
3. Calculate the mean, median and mode for the following data of Diameter at Breast Height
(DBH) of Teak plantation and also check the symmetry.
[Link] 1 2 3 4 5 6 7 8 9 10 11 12
DBH (cm) 23.5 22.4 27.6 29.0 21.5 31.0 28.9 24.2 23.6 24.5 22.0 26.8

2. Compute the mean number of flowers per plant for the following data.
No. of Flowers 0 1 2 3 4 5 6
No. of Plants 5 10 12 16 8 7 2

3. The following table gives the weight of 31 ear-heads in a sample survey.

Weight (lbs) 130 135 140 145 146 148 149 150 157
No. of ear-heads 3 4 6 6 3 5 2 1 1
Calculate the Arithmetic Mean, Geometric Mean and Harmonic Mean and also check the
relationship between the above measures.
4. Find the mean breadth of leaf of banyan tree given the following distribution.
Breadth of leaf (in cms.) 2–4 4–6 6–8 8 – 10 10 – 12 12 – 14
No. of leaves 7 10 19 15 9 3

29
5. Find the Mean, Mode and Median for the following table relating to the number of grains
per wheat blade.
No. of grains 20 – 24 24 – 28 28 – 32 32 – 36 36 – 40 40 – 44 44 – 48
No. of wheat ears 6 10 25 35 14 5 8

6. The following is the distribution of heights of 85 bamboo plants.

Height (cms.) 30 – 32 33 – 35 36 – 38 39 – 41 42 – 44 45 – 47
No. of plants 8 13 20 29 10 5
Find the Mean, Mode and Median heights of the bamboo plant.
7. The frequency distribution below gives the cost of production of sugarcane in different
holdings. Obtain the Arithmetic Mean, Median and Mode.
Class 2–6 6 – 10 10 – 14 14 – 18 18 – 22 22 – 26 26 – 30 30 – 34
Frequency 1 9 21 47 52 36 19 3

8. Calculate the mode for the following distribution of wages of farm workers in a village.
Daily Wages
2–4 4–6 6–8 8 – 10 10 – 12 12 – 14 14 – 16 16 – 18
(’0s)
No. of Farm
29 43 75 135 90 60 35 33
Workers

9. Find all the measures of central tendency from the heights of trees given in the following
table and interpret the results.
Height Frequency
Below 7 feet 26
Below 14 feet 57
Below 21 feet 92
Below 28 feet 134
Below 35 feet 216
Below 42 feet 287
Below 49 feet 341
Below 56 feet 360

30
 Ex. No. – 4 (a) Measures of Dispersion
- (Grouped and ungrouped data)
Range, Quartile Deviation, Mean Deviation, Standard Deviation, Variance and
Coefficient of Variation
Formula:

S. Name of the Grouped data

Raw data
No. Measure Discrete Continuous
1 Range Largest value – Smallest value = L – S
2 Quartile Q3  Q1
Deviation (QD) 2
where

 n 1
th
 N  1
th
N 
Q1=   value Q1=   value  4  m
 4   4  Q1 = L   C
 f 
 n 1  N  1  
th th

Q3= 3  value Q3= 3  value

 4   4   3N 
 4  m
n=No. of observations N = Total frequency Q3 = L   C
 f 
 
3 Mean Deviation xx  f xA
(MD)
n N
Where x = Mean Where f = Frequency A = Mean (or) Median (or) Mode
N = No. of observations N = Total Frequency
4 Standard  x  2
n

 (x  fd 2   fd 
2
 fx 2   fx 
2
 x)2  x2 
=  C 
i
Deviation (SD) i 1 n
 
n n N  N  N  N 
In case of sample, Where
replace n as (n-1) f = Frequency
n
 x  2 N = f = Total Frequency
 (x
i 1
i  x)2
=  x2 
n
n 1 n 1 C = Class interval
mid x  A
d= , A = Assumed
C
mean
5 Variance Square of Standard Deviation = (SD)2
6 Coefficient of CV (%) = (SD / Mean) x 100
Variation (CV)

31
Example – (i) Range:

1. Raw data – Ungrouped data

The following are the weights in gms. of 9 frogs. Calculate range.
80 100 85 90 110 120 150 135 140
Solution:
Range = Largest value – Smallest value = L – S
The minimum weight in the above series is 80 g. and the maximum, 150 g.
Range = 150 – 80 = 70 g.
More commonly, the range of the data is indicated as 80 – 150 g.
2. Grouped data – Discrete case
The following data gives the weights of 50 frogs in gms. Calculate range.
Weight (x) No. of frogs (f)
85 5
90 5
110 10
140 15
125 15
Total 50
Solution:
Range = Largest value – Smallest value = L – S
Range = 140 – 85 = 55 g.
3. Grouped data – Continuous case
The following data gives the weights of 50 frogs in gms. Calculate range.
Weight (x) No. of frogs (f)
60 – 80 12
80 – 100 13
100 – 120 10
120 – 140 10
140 – 160 5
Total 50
Solution:
Range = Largest value – Smallest value = L – S
Range = 160 – 60 = 100 g.

32
Example – (ii) Quartile Deviation:

1. Raw data – Ungrouped data

The following are the heights in cms. of 5 seedlings. Calculate Quartile deviation.
8 3 5 10 7
Solution:
First arrange the values in ascending order.
3 5 7 8 10
Here n = 5

 n 1  5  1
th th

Q1 =   value =   value
 4   4 
= 1.5th value
= 1st value + (0.5) (2nd value – 1st value)
= 3 + (0.5) (5 – 3) = 3 + 1 = 4

 n 1  5  1
th th

Q3 = 3  value = 3   value
 4   4 
= 3(1.5)th value = 4.5th value
= 4th value + (0.5) (5th value – 4th value)
= 8 + (0.5) (10 – 8) = 8 + 1 = 9
Q3  Q1
Quartile Deviation =
2
94
= = 2.5.
2
2. Grouped data – Discrete case
The following data gives the heights in cms. of 60 seedlings in gms. Calculate
Quartile deviation.
Height No. of Seedlings
(x) (f)
1 3
2 11
3 20
4 14
5 8
6 4
Total 60

33
 Solution:
Height No. of Seedlings Cumulative
(x) (f) Frequency (CF)
1 3 3
2 11 14
3 20 34
4 14 48
5 8 56
6 4 60
Total 60

Here N = 60

 N  1  60  1 
th th
th
Q1 =   value =   value = 15.25 value falling frequency
 4   4 
= 15th value + (0.25) (16th value – 15th value)
= 3 + (0.25) (3 – 3) = 3 + 0 = 3

 N  1  60  1 
th th
th
Q3 = 3  value = 3   value = 45.75 value
 4   4 
= 45th value + (0.75) (46th value – 45th value)
= 4 + (0.75) (4 – 4) = 4 + 0 = 4
Q3  Q1
Quartile Deviation =
2
43
= = 0.5
2
3. Grouped data – Continuous case
The following data gives the heights of 50 plants in cms. Calculate Quartile
deviation.
Height (cms) No. of plants
(x) (f)
0 – 20 7
20 – 40 13
40 – 60 20
60 – 80 6
80 – 100 4
Total 50
Solution:

34
 Height (cms) No. of plants Cumulative
(x) (f) Frequency (CF)
0 – 20 7 7
20 – 40 13 20
40 – 60 20 40
60 – 80 6 46
80 – 100 4 50
Total 50
th th
N   50 
Find the size of   item. (i.e.)   item = 12.5th item.
4 4
Q1 class is lies between 20 – 40.
N 
 4  m
Q1 = L   C
 f 
 
L = 20, N = 50, m = 7, f = 13, C = 20.
 50 
 4  7
Q1 = 20     20 = 28.46
 13 
 
th th
 3N  150 
Find the size of   item. (i.e.)   item = 37.5th item.
 4   4 
Q3 class is lies between 40 – 60.
 3N 
 4  m
Q3 = L   C
 f 
 
L = 40, N = 50, m = 20, f = 20, C = 20.
 3(50) 
 4  20 
Q3 = 40     20 = 57.5
 20 
 
Q3  Q1
Quartile Deviation =
2
57.5  28.46
= = 14.52.
2

35
Example – (iii) Mean Deviation:

1. Raw data – Ungrouped data

The following are the heights in cms. of 5 seedlings. Calculate Mean deviation.
3 5 7 8 10
Solution:
n

x  x2  ...  xn x
i 1
i
Mean = x = 1 =
n n
33
=  6.6
5
x 3 5 7 8 10 33
(x  x) 3 – 6.6 5 – 6.6 7 – 6.6 8 – 6.6 10 – 6.6
xx 3.6 1.6 0.4 1.4 3.4 10.4
xx 10.4
Mean Deviation = ==  2.08
n 5
2. Grouped data – Discrete case
The following data gives the heights in cms. of 60 seedlings in gms. Calculate Mean
deviation.
Height (x) No. of Seedlings (f)
1 3
2 11
3 20
4 14
5 8
6 4
Total 60
Solution:
Height (x) No. of Seedlings (f) fx xx f xx
1 3 3 2.42 7.26
2 11 22 1.42 15.62
3 20 60 0.42 8.40
4 14 56 0.58 8.12
5 8 40 1.58 12.64
6 4 24 2.58 10.32
Total 60 205 62.36

36
 n n

fx i i fx
i 1
i i
205
Mean = x = i 1
n
= =  3.42.
f
N 60
i
i 1

 f xx 62.36
Mean Deviation = =  1.039
N 60

3. Grouped data – Continuous case

The following data gives the heights of 50 plants in cms. Calculate Mean deviation.
Height (cms) No. of plants
(x) (f)
0 – 20 7
20 – 40 13
40 – 60 20
60 – 80 6
80 – 100 4
Total 50
Solution:
d=
Height (cms) No. of plants
mid x mid x  A fd xx f xx
(x) (f)
C
0 – 20 7 10 –2 –14 34.8 243.6
20 – 40 13 30 –1 –13 14.8 172.4
40 – 60 20 50 0 0 5.2 104.0
60 – 80 6 70 1 6 25.2 151.2
80 – 100 4 90 2 8 45.2 180.8
Total 50 872
 fd 
Mean = x = A   C
 N 
  13 
Mean = x = 50     20 = 44.8
 50 
 f xx 872
Mean Deviation = =  17.44
N 50

37
Example – (iv) Standard Deviation:

1. Raw data – Ungrouped data

The following are the weights in gms. of 5 frogs. Calculate Standard Deviation and
Variance.
100 102 118 124 128
Solution:
x 100 102 118 124 128 572
(x  x)2 207.36 153.76 12.96 92.16 184.96 651.2
n

x
i 1
i
Mean = x =
n
572
=  114.4
5
n

 (x i  x)2
Standard deviation =  = i 1

n
651.2
= = 11.4123
5
n

 (x
i 1
i  x)2
651.2
Sample Standard deviation = S = = = 12.7593
n 1 4
n

 (x i  x)2
Variance = (SD)2 = 2 = i 1
= (11.4123)2 = 130.2406
n

2. Grouped data – Discrete case

The following data gives the heights in cms. of 50 seedlings. Calculate Standard
deviation and Variance.
Height (x) No. of Seedlings (f)
3 4
4 6
5 15
6 15
7 10
Total 50
Solution:

38
 Height (x) No. of Seedlings (f) fx fx2
3 4 12 36
4 6 24 96
5 15 75 375
6 15 90 543
7 10 70 490
Total 50 271 1537
n n

fx i i fx
i 1
i i
271
Mean = x = i 1
n
= =  5.42
f
N 50
i
i 1

 fx 2   fx 
2

Standard deviation =  =  
N  N 
2
1537  271
=    1.1677
50  50 
Variance = (SD)2 = 2 = (1.1677)2 = 1.3635

3. Grouped data – Continuous case

The following data gives the heights in cms. of 50 seedlings. Calculate Standard
deviation and Variance.
Height No. of Seedlings
(x) (f)
2.5 – 3.5 4
3.5 – 4.5 6
4.5 – 5.5 15
5.5 – 6.5 15
6.5 – 7.5 10
Total 50
Solution:
Height (cms) No. of Seedlings mid x  A
mid x d= fd fd2
(x) (f) C
2.5 – 3.5 4 3 –2 –8 16
3.5 – 4.5 6 4 –1 –6 6
4.5 – 5.5 15 5 0 0 0
5.5 – 6.5 15 6 1 15 15
6.5 – 7.5 10 7 2 20 40
Total 50 21 77

39
  fd 2   fd 
2

Standard deviation =  = C   
N  N 
2
77  21 
= 1  = 1.1677
50  50 

Variance = (SD)2 = 2 = (1.1677)2 = 1.3635

Exercise – 4 (a) Measures of Dispersion - (Grouped and ungrouped data)

1. The following data based on number of seeds germinated out of 20 in each of the ten petty
dishes.
15 13 10 17 8 12 14 11 13 15
Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation
(Also verify the results using MS Excel functions)
2. The country’s food grains output (in million tons) for 20 years from 1987 – 2007 in Tamil
Nadu is given below.
75 74 80 81 85 86 84 81 90 87
92 94 95 93 98 96 94 99 109 110
Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation
(Also verify the results using MS Excel functions)
3. The numbers of seeds in 65 seed cases from a new variety of sweet pea were as follows.
No. of seeds No. of seed cases of sweet pea
(x) (f)
2 1
4 5
6 15
8 27

40
 10 10
12 5
14 2
Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation
4. The following data gives the number of eggs laid by 60 hens in a two-week period.
No. of eggs No. of hens
(x) (f)
5 3
6 7
7 9
8 10
9 13
10 9
11 8
12 1
Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation

5. The following data gives the yield of milk per day (in liters) of 70 dairy animals.
Yield of milk per No. of dairy
day (in liters) animals
(x) (f)
0–2 6
2–4 10
4–6 14
6–8 18
8 – 10 11
10 – 12 7
12 – 14 4
Total 70

41
 Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation

6. The following frequency distribution is the height of tomato plants in F3 generation (i.e.)
the third generation of tomato crosses.
Tomato Plant
No. of plants
Height (in c.m.)
(f)
(x)
30 – 35 3
35 – 40 5
40 – 45 9
45 – 50 14
50 – 55 17
55 – 60 12
60 – 65 10
65 – 70 6
70 – 75 2
Calculate the following.
1) Range 2) Quartile Deviation 3) Mean Deviation 4) Standard Deviation
5) Variance 6) Coefficient of Variation

7. Below are the yield of two varieties in Ragi kg./plot in 10 trial plots. Find out which
variety gives more consistent yield.
Variety - I 85 68 50 30 70 95 60 76 24 19
Variety - II 99 75 80 94 80 89 69 85 65 40
Calculate Coefficient of Variation.

42
8. The following table gives the grain yield of rice in kg./plot and the no. of randomly
selected plants in two different districts. Find out which district gives more consistent
yield?
Grain yield (x) 0 – 10 10 – 20 20 – 30 30 – 40 40 – 50 50 – 60 60 – 70 70 – 80 80 – 90
No. of plants (f)
District I 3 7 12 17 22 20 14 4 1
No. of plants
District II 1 4 14 20 22 17 12 7 3
No. of plants
Calculate Coefficient of Variation.

9. Information regarding the price movements of the shares of three companies is given
below.
Company Average Price (in Rs.) S.D. (in Rs)
A 18.00 5.40
B 22.50 4.50
C 24.0 6.00
Which company’s share is more stable in price?

10. Prices of rice (in Rs./kg) in five towns of two districts are given below.
District A 10 12 19 13 16
District B 11 18 17 15 14
Find in which district the prices are more stable?

43
Ex. No. – 4 (b) Skewness and Kurtosis
- (Ungrouped and Grouped data)

Formula:
Skewness

1. Karl Person’s first coefficient of Skewness (using mean, mode, SD) = Mean  Mode
SD
2. Karl Person’s second coefficient of Skewness (using mean, median, SD) =
3( Mean  Median )
. Karl Person’s coefficient of Skewness lies between –3 to 3.
SD
3. Bowley’s measure of Skewness (or) Quartile measure of skewness =
Q3  Q1  2Median = Q3  Q1  2Q2 .
Q3  Q1 Q3  Q1

Bowley’s measure of Skewness lies between –1 to 1.

Measure of Skewness based on the moments, 1=  3

2
4.
 23

Where  2 and  3 are called second and third order central moments. The
second central moment is nothing but the variance.

( x  x ) 2 ( x  x ) 3
Raw data  2  , 3 
n 1 n 1
 f (x  x)2  f (x  x)3
Discrete and Continuous data  2  , 3 
N N

Kurtosis
4
Kurtosis is measured by Pearson’s coefficient, 2 =
 22

( x  x ) 2 ( x  x ) 4
Where Raw data  2  , 4 
n 1 n 1
 f (x  x)2  f (x  x)4
Discrete and Continuous data  2  , 4 
N N

44
Example Skewness and Kurtosis

The soil sample is taken in 7 districts of Tamil Nadu. Calculate the measure of skewness and
kurtosis for the following data.

District 1 2 3 4 5 6 7
Nutrient content (%) 12 15 20 25 30 40 50
No. of plots 10 25 40 70 32 13 10
Solution:
i) Calculation of Skewness :
Nutrient content No. of plots
cf fx fx2
(x) (f)
12 10 10 120 1440
15 25 35 375 5625
20 40 75 800 16000
25 70 145 1750 13750
30 32 177 960 28800
40 13 190 520 20800
50 10 200 500 25000
Total 200 5025 141415
n

fx
i 1
i i
Arithmetic Mean = x =
N
5025
=  25.13
200

 N 1
th

Median =   value
 2 
 200  1 
th

=  value  25
 2 

By inspection of the given data, Mode = 25.

45
  fx 2   fx 
2

Standard Deviation = SD = S = 
N  N 
 
2
141415  5025 
=   = 75.8094 = 8.71
200  200 

a) Karl Pearson’s coefficient of skewness,

Mean  Mode 25.13  25.0

i) Sk = =  0.0149
SD 8.71
3( Mean  Median ) 3(25.13  25)
ii) Sk = =  0.0448
SD 8.71

It may be concluded that the distribution of nutrient content almost symmetrical.

 32
b) Measure of Skewness based on the moments = 1=
 23
Where  2 and  3 are called second and third order central moments. The
second central moment is nothing but the variance.

( x  x ) 2 ( x  x ) 3
Raw data  2  , 3 
n 1 n 1
 f (x  x)2  f (x  x)3
Discrete and Continuous data  2  , 3 
N N

Nutrient No. of (x  x)
content plots ( x  x )2 (x  x)3 f (x  x) 2 f (x  x)3
( x  25.13)
(x) (f)
12 10 -13.13 172.3969 -2263.5713 1723.9690 -22635.7130
15 25 -10.13 102.6169 -1039.5092 2565.4225 -25987.7299
20 40 -5.13 26.3169 -135.0057 1052.6760 -5400.2279
25 70 -0.13 0.0169 -0.0022 1.1830 -0.1538
30 32 4.87 23.7169 115.5013 758.9408 3696.0417
40 13 14.87 221.1169 3288.0083 2874.5197 42744.1079
50 10 24.87 618.5169 15382.5153 6185.1690 153825.1530
Total 200 16.09 1164.6983 15347.9365 15161.8800 146241.4781

46
  f (x  x)2 15161.8800
2  =  75.8094
N 200
 f (x  x)3 146241.4781
3  =  731.2074
N 200
 32
Measure of Skewness based on the moments, 1= 3
2

(731.2074) 2
 1= = 1.23
(75.8094) 3

ii) Calculation of Kurtosis :

4
Kurtosis is measured by Pearson’s coefficient, 2 =
 22

( x  x ) 2 ( x  x ) 4
Where Raw data  2  , 4 
n 1 n 1
 f (x  x)2  f (x  x)4
Discrete and Continuous data  2  , 4 
N N

Nutrient No. of (x  x)
content plots ( x  x )2 (x  x) 4 f (x  x) 2 f (x  x) 4
( x  25.13)
(x) (f)
12 10 -13.13 172.3969 29720.6911 1723.9690 297206.9113
15 25 -10.13 102.6169 10530.2282 2565.4225 263255.7041
20 40 -5.13 26.3169 692.5792 1052.6760 27703.1690
25 70 -0.13 0.0169 0.0003 1.1830 0.0200
30 32 4.87 23.7169 562.4913 758.9408 17999.7231
40 13 14.87 221.1169 48892.6835 2874.5197 635604.8851
50 10 24.87 618.5169 382563.1556 6185.1690 3825631.5559
Total 200 16.09 1164.6983 472961.8292 15161.8800 5067401.9684

 f (x  x)2 15161.8800
2  =  75.8094
N 200

47
  f (x  x)4 5067401.9684
4  =  25337.0098
N 200

4
Kurtosis =
 22

25337.0098
=  4.4087
(75.8094) 2

2  3

 The curve is leaping curve i.e.) Lepto kurtic.

Exercise – 4 (b) Skewness and Kurtosis

1. The nutrients on soil available NPK (kgha-1) after the harvest of Bt Cotton sample
collected from 8 locations of Coimbatore district is given below:
Soil available NPK (kgha-1)
Nitrogen Phosphorus Potassium
232 15.3 340
223 13.0 328
238 16.2 348
235 17.1 356
228 14.2 338
230 14.5 342
240 17.9 360
243 18.9 368
By estimating the skewness and kurtosis discuss the properties of available Nitrogen
in soil of Coimbatore district.

48
2. The following data gives the yield of milk per day (in litres) of 70 dairy animals.
Yield of milk per No. of dairy
day (in litres) animals
(x) (f)
2 6
4 10
6 14
8 18
10 11
12 7
14 4
Total 70
Discuss the distribution of the yield of milk per day (in litres) using skewness and
kurtosis.

3. The farm income obtained from 250 farmers in 8 revenue villages (in Rs.) of Salem
District.
Farm Income (Rs.) No. of farmers
(x) (f)
Below 100 10
100 – 139 16
140 – 179 39
180 – 219 48
220 – 259 60
260 – 299 46

300 – 339 22

340 and above 9

Total 250
Discuss the nature of the distribution of farm income are normally distributed or not
using the measures of skewness and kurtosis.

49