Measures of Location (Central Tendency)

1 Average: A value which represents the whole distribution is called average.

Averages are called measures of central tendency because averages tend to lie in the center
of the dist. Averages are also called measures of location because averages locate the center
of the dist.
2 Measures of Central Tendency: The methods which we use to measure the central
tendency are called measures of central tendency. These are also called averages which are:
1. Arithmetic mean 2. Geometric mean 3. Harmonic mean
4. Median 5. Mode
3 Arithmetic Mean: It is obtained by dividing the sum of items by their numbers. It is
denoted by x . It expresses the potential of the data.
Arithmetic Mean (For ungrouped data) Arithmetic Mean (For grouped data).
x = ∑ x i /n x = ∑ fx i /∑ f
4 Weighted Mean: If all values are not of equal importance then we assign then some
numerical values according to their importance called weights. If w1, w2, …, wn be the

weights of x1, x2, …, wn respectively then Weighted Mean = x w =

∑ w i xi .
∑ wi
5 Combined Mean: If data is divided into k subgroups, each having n1, n2, …, nk values along
∑ ni xi
with their means x 1, x 2, …, x k respectively then Combined mean = x c =
∑ ni
6 Properties of A.M:
1. The mean of the constant (all same values) will be the same constant. i.e. E(c) = c.
2. The sum of deviation taken from mean is zero. i.e. ∑ (x−x ) = 0.
3. Sum of squares of deviations from mean is minimum. i.e. ∑ (x−x )2 ≤ ∑ (x−a)2
4. Mean is affected by change of origin and scale. i. e. if x = ah+u then x = ah+u.

Q. 1. The marks obtained by 9 students are given below. Find A.M.

450, 320, 370, 460, 390, 360, 410, 480, 360
Sol:
xi (Marks)
450
320
370
460
390
360
410
480
360
3600 = ∑ x i

x = ∑ x i /n = 3600/9 = 400.
Q. 2. Find the A. M of the following distribution
 Weigh 65-84 85-104 105-124 125-144 145-164 165-184 185-204
t
f 9 10 17 10 5 4 5
Sol:
Weight f xi f xi
(Grams) (Mid point)
65-84 9 74.5 670.5
85-104 10 94.5 945.0
105-124 17 114.5 1946.5
125-144 10 134.5 1345.0
145-164 5 154.5 772.5
165-184 4 174.5 698.0
185-204 5 194.5 972.5
Totals 60 7350

x = ∑ fx i /∑ f = 7350.0/ 60 = 122.5 grams.

3 Weighted Mean: If all values are not of equal importance then we assign then some
1 numerical values according to their importance called weights. If w1, w2, …, wn be the

weights of x1, x2, …, wn respectively then Weighted Mean = x w =

∑ w i xi .
∑ wi
Q. 3. An examination candidate’s percentages are: English 73, French 82, Mathematics 57,
Science 62, and History 60. Find the candidate’s weighted mean if weights of 4, 3, 3, 1, 1
are allotted to the subjects respectively.

Sol:
Subject Marks Weights wi x i
(xi ) (wi)
English 73 4 292 ∑ w i xi = 831
= 69.25
French 82 3 246 x w =
Maths 57 3 171
∑ wi 12

Science 62 1 62
History 60 1 60
Total 12 831
3 Combined Mean: If data is divided into k subgroups, each having n1, n2, …, nk values along
2 ∑ ni xi
with their means x 1, x 2, …, x k respectively then Combined mean = x c =
∑ ni
Q. 4. The mean heights of three sections containing 40, 37 and 43 students are 62, 58 and
61 inches respectively. Find overall mean of 120 students.
Sol:
Section No. of Means ( ni x i
Students (ni ) x i)
A 40 62 2480
x
∑ ni xi = 7249
= 60.4 inches
B 37 58 2146 w = ∑ ni 120
C 43 61 2623
Total 120 7249

Geometric Mean: It is the nth root of the product of n non-negative values. It is suitable
averages for rates and ratios.
Geometric Mean for ungrouped data. G.M for grouped data.
G.M = √n x 1 . x 2 … x n = [ x 1 . x 2 … x n]1/n G.M = Antilog (∑ flog x i /∑ f )
G.M = Antilog (∑ log x i /n )
Q. 5. Find G. M of 45, 32, 37, 46, 39, 36, 41, 48, 36

Sol.

Marks Log xi
(xi )
45 1.65321
32 1.50515
37 1.56820 G. M = Antilog (∑ log x i /n )
46 1.66276
39 1.59106 = Antilog (14.38700/9) = 39.68
36 1.55630
41 1.61278
48 1.68124
36 1.55630
Total 14.38700

Q. 6. Find G. M

Weigh 65-84 85-104 105-124 125-144 145-164 165-184 185-204

t
f 9 10 17 10 5 4 5
Sol:
Weight f xi log xi f log xi G.M = Antilog (∑ flog x i /∑ f )
(Grams) (Mid point)
65-84 9 74.5 1.8722 16.8498 = Antilog (124.2483/60)
85-104 10 94.5 1.9754 19.7540
105-124 17 114.5 2.0589 35.0013 = 117.7 grams
125-144 10 134.5 2.1287 21.2870
145-164 5 154.5 2.1889 10.9445
165-184 4 174.5 2.2418 8.9672
185-204 5 194.5 2.2889 11.4445
Totals 60 124.2483

Harmonic Mean: It is the reciprocal of arithmetic mean of the reciprocals of the non-zero
n
values. H.M (for ungrouped data) = H.M = 1 H.M (for grouped data) = H.M =
∑( x)
∑f
∑ ( fx )
Q. 7. Find average speed if speed is 15 km/hr for first 30 km, 20 km/hr for second 30 km
and 25 km/hr for third 30 km.
 Sol: If distance remains same, then H. M is suitable for the average of speed.

Speed (xi ) 1/xi n

15 0.06667 H. M = 1
20 0.5000 ∑( x)
25 0.04000
Total 0.15667 = 3/ 0.15667 = 19.15 km/hr.

Q. 8. Find H. M

Weigh 65-84 85-104 105-124 125-144 145-164 165-184 185-204

t
f 9 10 17 10 5 4 5
Sol:
Weight f xi f / xi ∑f
(Grams (Mid point) G.M = H.M =
) ∑ ( fx )
65-84 9 74.5 0.12081
85-104 10 94.5 0.10582 = 60/ 0.53044
105-124 17 114.5 0.14847
125-144 10 134.5 0.07435 = 113.11 grams
145-164 5 154.5 0.03236
165-184 4 174.5 0.02292
185-204 5 194.5 0.02571
Totals 60 0.53044

7 Median: It is the most middle value of the arranged data.

Median for ungrouped data and discrete Median for grouped data.
grouped data without classes. h n
Med = l + ( - c), where
f 2
n+1 l = lower class boundary of middle class,
Med = ( )th value in an array.
2 h = class interval of middle class.
f = frequency of middle class.
c = preceding cumulative frequency of middle
class.
8 Mode: It is the most frequent value of the data. It can also be calculated for qualitative data.
It is the average which can take more than one values. A dist. having only one mode is
called unimodal. A dist. having two values of mode is called bimodal.
Mode for ungrouped data and discrete Mode for grouped data.
grouped data without classes. f m −f 1
Mode = l + , where
(f ¿ ¿ m−f 1)+(f m −f 2)× h ¿
Mode = Most frequent value of the data. l = Lower class boundary of model class,
 h = Class interval of model class.
fm = Maximum frequency.
f1 = Preceding frequency of fm.
f2 = Frequency next to fm.
9 Quantiles: These are the vales which divide the arranged data into different equal parts.
Quartiles: These are the vales which divide the arranged data into four equal parts.
Quartiles for ungrouped data and discrete Quartiles for grouped data.
grouped data without classes. h n
n+1 Q1 = l + ( – c)
f 4
Q1 = ( )th value in an array.
4 h 3n
n+1 Q3 = l + ( – c)
f 4
Q3 = 3( )th value in an array.
4
1 Deciles: These are the vales which divide the arranged data into ten equal parts.
0 Deciles for ungrouped data and discrete Deciles for grouped data.
grouped data without classes. h n
n+1 D1 = l + ( – c)
f 10
D1 = ( )th value in an array.
10 h 7n
n+1 D7 = l + ( – c)
f 10
D7 = 7( )th value in an array.
10
1 Percentiles: These are the vales which divide the arranged data into hindered equal parts.
1 Percentiles for ungrouped data and discrete Percentiles for grouped data.
grouped data without classes. h 60 n
n+1 P 60 = l + ( – c)
f 100
P60 = 60( )th value in an array.
100

Q. 1. Find median, Q1, Q3 from the following data.

12, 6, 15, 9, 4, 8, 7, 19, 11, 25, 22
Sol:
Arranging the data

No. 1 2 3 4 5 6 7 8 9 1 11
0
Values: 4 6 7 8 9 11 12 1 19 2 25
5 2

n+1
Med = th value in an array
2
11+1
= th = 6th value in an array
2
= 11
 n+1
Q1 = th value in an array
4
11+1
=( )th = 3rd value in an array
4
=7

n+1
Q3 = 3( )th value in an array
4
11+1
= 3( )th = 9th value in an array
4
= 19
Q. 2. Find median, Q1 and Q3 from the following data.
12, 15, 9, 4, 7, 19, 25, 22, 30, 28
Sol:
Arranging the data

No. 1 2 3 4 5 6 7 8 9 10
Values: 4 7 9 12 15 19 22 25 28 30

n+1
Med = th value in an array
2
10+1
= th = 5.5th value in an array
2
= 5th value + 0.5(6th – 5th value)
= 15 + 0.5(19-15) = 15+2 = 17

n+1
Q1 = th value in an array
4
10+1
=( )th = 2.75th value in an array
4
= 2nd value + 0.75(3rd – 2nd value)
= 7 + 0.75(9-2) = 7+1.5 = 8.5

n+1
Q3 = 3( )th value in an array
4
10+1
= 3( )th = 8.25th value in an array
4
= 8th value + 0.25(9th – 8th)
= 25 + 0.25(28-25) = 25+0.75 = 25.75

Q. 3. Find median, Q1, Q3, D7, P65 and mode from the following data which shows the
number of heads when five coins were tossed 165 times.
No. of heads 0 1 2 3 4 5 6
Frequency 15 2 30 40 30 20 10
 0

Sol: It is grouped data without classes. Here x (number of heads) is discrete, therefore, we
solve it as:

x f Cf n+1 165+1
Med = th value in an array = ( )th value
0 15 15 2 2
1 20 35 = 84th value (it lies in 105 cf value) = 3
2 30 65 n+1 165+1
Q1 = th value in an array = ( )th value
3 40 105 4 4
4 30 135 = 42th value (it lies in 65 cf value) = 2
5 20 155 n+1 165+1
Q3 = 3( )th value in an array = 3( )th value
6 10 165 4 4
= 126th value (it lies in 135 cf value) = 4
n+1 165+1
D7 = 7( )th value in an array = 7( )th value
10 10
= 116.2th value (it lies in 135 cf value) = 4
n+1 165+1
P65 = 65( )th value in an array = 65( )th value
100 100
= 107.9th value (it lies in 135 cf value) = 4
Mode = most frequent value (x with maximum frequency) = 3

Q. 4. Find median, Q1, Q3, D8, P45 and mode from the following data

Marks 30-39 40-49 50-59 60-69 70-79 80-89 90-99

f 8 87 190 304 211 85 20

Marks f Cf C-B n
Med = Marks obtained by th student.
30-39 8 8 29.5-39.5 2
40-49 87 95 39.5-49.5 905
= Marks obtained by th = 452.5 th
50-59 190 285 49.5-59.5 2
60-69 304 589 59.5-69.5 student which lies in class (59.5-69.5)
70-79 211 800 69.5-79.5 h n
Med = l + ( - c)
80-89 85 885 79.5-89.5 f 2
90-99 20 905 89.5-99.5 10
= 59.5+ (452.5- 285) = 65 marks
304
n 905
Q1 = Marks obtained by th student= Marks obtained by th = 226.25th
4 4
student which lies in class (49.5-59.5)

h n 10
Q1 = l + ( - c) = 49.5 + (226.25- 95) = 56 marks
f 4 190
 3n 3(905)
Q3 = Marks obtained by th student = Marks obtained by th = 678.75th
4 4
student which lies in class (69.5-79.5)

h 3n 10
Q3 = l + ( - c) = 69.5 + (678.75- 589) = 74 marks
f 4 211

8n 8(905)
D8 = Marks obtained by th student = Marks obtained by th = 724th
10 10
student which lies in class (69.5-79.5)

h 8n 10
D8 = l + ( - c) = 69.5 + (724- 589) = 76 marks
f 10 211

45 n 45(905)
P45 = Marks obtained by th student = Marks obtained by th = 407.25th
100 100
student which lies in class (59.5-69.5)

h 45 n 10
P45 = l + ( - c) = 59.5 + (407.25-285) = 65.93 marks
f 100 211

For mode, select fm = maximum frequency which is 304. Hence model class is (59.5-69.5) f1
is its preceding value which is 190. f2 is next to fm which is 211.

f m −f 1
Mode = l +
(f ¿ ¿ m−f 1)+(f m −f 2)× h ¿

304−190
= 59.5 + ×10
(304−190)+(304−211)

14(10)
= 59.5 + = 59.5 + 1.31 = 60.81 marks
14 +93

Q. 5. Find median, Q1, Q3, O5, D3, P55 and mode from the following data

Weight (x) 60 61 62 63 64 65 66
f 10 40 70 90 60 30 20

Sol: It is grouped data without classes but x (weight) is continuous variable, therefore, for
median, quantiles and mode, we have to make the classes first.

Take the half of the difference of first two values (61-60)/2 = 0.5. Subtracting it from each
value of x, get lower class boundary. Adding it to each value of x, get upper class boundary
of that group.
 Weigh f Cf C-B
t
60 10 10 59.5-60.5
61 40 50 60.5-61.5
62 70 120 61.5-62.5
63 90 210 62.5-63.5
64 60 270 63.5-64.5
65 30 300 64.5-65.5
66 20 320 65.5-66.5

Solve it now as we solved the Q. 4.

Q. 6. Find Mode of the following data.

(i) 25, 15, 18, 30, 20, 20, 12, 9, 16, 15 (ii) 12, 23, 25, 15, 20, 34, 21, 18
(iii) 15, 23, 25, 15, 20, 34, 21, 18, 15

Sol: (i) 15, 20 (Both are most frequent as both appear two times)
(ii) No mode (No value is being repeated)
(iii) 15 (most frequent which appears three times)