Coefficient of Standard Deviation

The standard deviation is the absolute measure of dispersion. Its relative measure is called the
standard coefficient of dispersion or coefficient of standard deviation. It is defined as:

S
Coefficient of Standard Deviation =
X́
Coefficient of Variation
The most important of all the relative measures of dispersion is the coefficient of variation.
This word is variation not variance. There is no such thing as coefficient of variance. The
coefficient of variation (C.V) is defined as:

S
Coefficient of Variation = × 100
X́
Thus C.V is the value of S when  X́  is assumed equal to 100. It is a pure number and the unit
of observation is not mentioned with its value. It is written in percentage form like 20% or
25%. When its value is 20%, it means that when the mean of the observations is assumed
equal to 100, their standard deviation will be 20. The C.V is used to compare the dispersion
in different sets of data particularly the data which differ in their means or differ in their units
of measurement. The wages of workers may be in dollars and the consumption of meat in
families may be in kilograms. The standard deviation of wages in dollars cannot be compared
with the standard deviation of amount of meat in kilograms. Both the standard deviations
need to be converted into a coefficient of variation for comparison. Suppose the value
of C.V for wages is 10% and the value of C.V for kilograms of meat is 25%. This means that
the wages of workers are consistent. Their wages are close to the overall average of their
wages. But the families consume meat in quite different quantities. Some families consume
very small quantities of meat and some others consume large quantities of meat. We say that
there is greater variation in their consumption of meat. The observations about the quantity of
meat are more dispersed or more variant. So C.V is unit less quantity.
 

Example:
Calculate the coefficient of standard deviation and coefficient of variation for the following
sample data: 2, 4, 8, 6, 10, and 12.

Solution:
2
X ( X − X́ )
2 ( 2−7 )2=¿25
4 9
8 1
6 1
10 9
12 25

X́ =
∑ X = 42 =7
n 6
 2
2 ∑ ( X − X́ ) 70
S= = =14
n−1 5

S= √ S2 =√ 14=3.7417
3.7417
Coefficient of Standard Deviation = =0.5345
7
3.7417
Coefficient of Variation = ×100=53.5 %
7

Q.1 The mean and standard deviation of marks obtained by 40 students of

a class in three subjects Mathematics, Science and Social Science are
given below

Which of the three subjects shows highest variation and which shows
lowest variation in marks?

Solution :

Mathematics :

Coefficient of variation (C.V) =  (σ/x̄) ⋅ 100%

x̄  =  56, σ  =  12

C.V  =  (12/56) ⋅ 100%

C.V  =  0.2142 ⋅ 100%

C.V  =  21.42%
Science :Coefficient of variation (C.V) =  (σ/x̄) ⋅ 100%

x̄  =  65, σ  =  14

C.V  =  (14/65) ⋅ 100%

C.V  =  0.2153 ⋅ 100%

C.V  =  21.53%

Social Science :

Coefficient of variation (C.V) =  (σ/x̄) ⋅ 100%

x̄  =  60, σ  =  10

C.V  =  (10/60) ⋅ 100%

C.V  =  0.1666 ⋅ 100%

C.V  =  16.66%

The highest variation is in the subject Science and lowest variation is in

the subject Social science
Q.2 The temperature of two cities A and B in a winter season are given
below.

Temperature A A2 Temperature B B2

18 324 11 121

20 400 14 196

22 484 15 225

24 576 17 289

26 676 18 324

∑ A=110 ∑ A 2=2460 ∑ B=75 ∑ B2=1155

Find which city is more consistent in temperature changes?

Solution :
 2
2
S=
1
n−1 {∑ X− 2 (∑ X )
n }

Temperature of city A :
Á=
∑ A = 110 =22
n 5
2
2
S=
1
n−1 {
∑A − 2 (∑ A )
n } {
=
1
5−1
2460−
110 2 40
5 }
= =10
4

S= √ S2 =√10=3.1623

3.1623
Coefficient of Variation = ×100=14.3741%
22

Temperature of city B :
B́=
∑ B = 75 =15
n 5
2
2
S=
1
n−1 {
∑B − 2 (∑ B )
n } {
=
1
5−1
1155−
75 2 30
5} = =7.5
4

S= √ S2 =√ 7.5=2.7386

2.7386
Coefficient of Variation = ×100=18.2574
15

Hence city A is more consistent.

Question:
The average marks scored by two students Sathya and Vidhya in 5 subjects are 460 and 480
with standard deviation 4.6 and 2.4 respectively. Who is more consistent in performance?

Page 125

4.25, 4.26, 4.27, 4.28, 4.29 and 4.30

QUANTILES
Median:

It is such a value which divides the data set into two equal parts.

Minimum Median Maximum

50% 50%

Quartiles:
It is such a value which divides the data set into 4 four equal parts.

Minimum 1 Q1 2 Q2 3 Q3 4 Maximum
Median
25% 75%
50% 50%
75% 25%

Q 1=¿ 1st Quartile

Q2=¿ 2nd Quartile = Median
Q 3=¿ 3rd Quartile

How to calculate Quartiles: Use the following steps for calculating Quartiles es for small data sets.
For large data sets, we use frequency distribution to find quartiles.
• Step 1: Sort the data in ascending order (from smallest to largest)

• Step 2: Calculate 𝑖𝑡ℎ= i ( n4 )where i is the particular quartile you wish to calculate and n is the
sample size. i.e.
n
Q 1=
4
Q 2=2 ( n4 )= n2 =median
3n
Q 3=
4
• Step 3: If 𝑖 is an integer, the q𝑡ℎ Quartile is the mean of the data values in positions 𝑖 and 𝑖+1. If 𝑖 is
not an integer, then round up to the next integer and use the value in this position.

Example: Use the following set of stock prices (in dollars): 10, 7, 20, 12, 5, 15, 9, 18, 4, 12,
8, 14 Find the 1st Quartile, 3rd Quartile and median.
Solution:
 First sort the data in ascending order:
4 5 7 8 9 10 12 12 14 15 18 20
1st 2nd 3rd 4th 5th 6th 7th 8th 9th 10th 11th 12th

 There are 12 scores so, n = 12.

 To find
n 12
Q 1= = =3 , Where 3 is an integer value so
4 4
3 rd value+ 4 th value 7 +8
Q 1= = =7.5
2 2
Q1=7.5
 To find
3 n 3 ×12
Q 3= = =9, Where 3 is an integer value so
4 4
9 th value+10 th value 14+15
Q 3= = =14.5
2 2

 To find median

n 12
Q 2=median= = =6, Where 6 is an integer value so
2 2

6 th value+7 th value 10+12

Q 2=median= = =11
2 2

DESILES
It is such a value which divides the data set into 10 ten equal parts.

1 2 3 4 5 Median 6 7 8 9 10
Minimum D1 D2 D3 D4 D5 D6 D7 D8 D9 Maximum
10% 90%
20% 80%
30% 70% .
40% 60% .

50% 50% .
60% 40% .
70% 30% .
 80% 20% .
90% 10% .

 There are 9 deciles which divide data set into 10 equal parts.
 From minimum value to D1 be first divide and less than D1 to minimum value is 10%
of data set and greater than D1to maximum value is 90% of the data set. And same for
all deciles i.e. D2 , D3 , D3, D4 , D5=median, D6 , D7 , D8 , D9 shown in the given
figure.
How to calculate Deciles: Use the following steps for calculating Deciles for small data sets. For
large data sets, we use frequency distribution to find deciles.
• Step 1: Sort the data in ascending order (from smallest to largest)

• Step 2: Calculate 𝑖𝑡ℎ= i ( 10n )where i is the particular Decile you wish to calculate and n is the
sample size. i.e.
n 2n 3n 4n 5n n 6n 7n 8n
D 1= D 2= D 3= D4 = D 5= = D 6= D 7= D 8=
10 10 10 10 10 2 10 10 10

9n
D 9=
10

• Step 3: If 𝑖 is an integer, the d𝑡ℎ Decile is the mean of the data values in positions 𝑖 and 𝑖+1. If 𝑖 is
not an integer, then round up to the next integer and use the value in this position.

Example: Use the following set of weights of 15 apples (in grams): 2.0, 2.7, 2.4, 2.9, 4.7,
4.5, 3.5, 3.7, 4.6, 4.9, 1.9, 2.5, 3.0, 4.1, and 4.6. Find Q1 , D3 , D7 ,Q3 ∧D9.
Solution:
 First sort the data in ascending order:
1.9 2.0 2.4 2.5 2.7 2.9 3.0 3.5 3.7 4.1 4.5 4.6 4.6 4.7 4.9
5t 10t
1st 2nd 3rd 4th 6th 7th 8th 9th 11th 12th 13th 14th 15th
h h

 There are 15 scores so, n = 15.

 To find
n 15
Q 1= = =3.75, Where 3.75 is a decimal value so we round up (3.75) ~ 4
4 4
Q1=4 rth value=2.5
Q 1=2.5
 To find
3 n 3 ×15
Q 3= = =11.25, Where 11.25 is a decimal value so we round up (11.25) ~ 12
4 4
Q3=12 th value=4.6

 To find
 3 n 3 ×15
D 3= = =4.5, Where 4.5 is a decimal value so we round up (4.5) ~ 5
10 10

D 3=5 th value=2.7
 To find
7 n 7 ×15
D 7= = =10.5 , Where 10.5 is a decimal value so we round up (10.5) ~ 11
10 10

D7=11 th value=4.5
 To find

9 n 9 ×15
D 9= = =13.5, Where 13.5 is a decimal value so we round up (13.5) ~ 14
10 10

D9=14 thvalue=4.7

PERCENTILES
It is such a value which divides the data set into 100 ten equal parts.

1 2….. 10… 25… Median 60… 75… 98 99 100

Minimum P1 P2… P10… P25… P50… P60… P75… P98 P99 Maximum
1% 99%
2% 98%
10% 90% .
25% 75% .

50% 50% .
60% 40% .
75% 25% .

98% 2% .
99% 1% .

 There are 99 percentiles which divide data set into 100 equal parts.
 From minimum value to P1 be first divide and less than P1 to minimum value is 1%
of data set and greater than P1to maximum value is 99% of the data set. And same for
all Percentiles i.e. P2 , P3 , P4 , P5, … P10,…, P25,… P50=Q2=D5 =MEDIAN ,… ,
P55,… , P60, …, P98 , P 99 as shown in the given figure.
  If we calculate percentiles it include all quantiles such as
1. P10=D 1 P20=D2 P30=D 3 …….. P90=D 9
2. P25=Q1
3. P50=D 5=Q 2=median
4. P75=Q3
How to calculate Percentiles: Use the following steps for calculating percentiles for small data sets.
For large data sets, we use frequency distribution to find percentiles.
• Step 1: Sort the data in ascending order (from smallest to largest)

• Step 2: Calculate 𝑖𝑡ℎ= i ( 100n )where i is the particular Percentile you wish to calculate and n is the
sample size. i.e.
n 2n 3n 4n 10 n n
P 1= P 2= P 3= P4 = …….. P10= = =D 1 …
100 100 100 100 100 10
25 n n 50 n n 75 n 3 n
P25= = =Q 1 …… P50= = =median …… P75= = =Q 3 …….
100 4 100 2 100 4

99 n
P99=
100

• Step 3: If 𝑖 is an integer, the p𝑡ℎ Percentile is the mean of the data values in positions 𝑖 and 𝑖+1. If 𝑖
is not an integer, then round up to the next integer and use the value in this position.

INTERPRETATION OF PERCENTILES
If you give NTS test for admission then you got your result card with percentile let
suppose 85%.Which means 85% of students got less than your score in a test and 15%
greater than your score in a test.
Page 84
3.42,
3.43
Weight (milligrams) No of seeds CF Class Boudaries
LCB UCB
10-24.9 16 16 9.05 24.95
25-39.9 68 16+68=84 24.95 39.95
40-54.9 204 84+204=288 39.95 54.95
55-69.9 233 288+233=521 54.95 69.95
70-84.9 240 521+240=761 69.95 84.95
85-99.9 655 761+655=1416 84.95 99.95
100-114.9 803 1416+803=2219 99.95 114.95
115-129.9 294 2219+294=2513 114.95 129.95
130-144.9 21 2513+21=2534 129.95 144.95
145-159.9 4 2534+4=2538 144.95 159.95

h n
Q 1=l +
f 4 (
−C )
n 2538
h = 84.95-69.95=15 = =634.5
4 4
 15 2538
Q 1=69.95+
240 4( −521 )
Q 1=77.0437

h 3n
Q3=l+
f 4 (−C )
3(n) 3 (2538)
= =1903 h = 114.95-99.95= 15
4 4
15 3(2538)
Q3=99.95+
803 ( 4
−1416 )
Q 3=109.0565

h 3n
D 3=l+ (
f 10
−C )
3 ( n ) 3 ( 2538 )
= =761.4 h = 99.95-84.95 = 15
10 10
15 3 ( 2538 )
D3=84.95+ (
655 10
−761)
D 3=84.95916

h 45 n
P9 5=l+ (
f 100
−C )
95(n) 95(2538)
h = 129.95-114.95 =15 = =2411.1
100 100

15 95(2538)
P95=114 .95+
294 100( −2219 )
P95=124.751