Measures of Central Tendency

Mean of Data Sets

Application of Mean in Real Life

The runs scored by the two opening batsmen of a team in ten successive matches of a
cricket series are listed in the table.

Player A 24 50 34 24 20 96 105 50 13 27

Player B 26 22 30 10 42 98 40 54 10 122

Using this data, we can compare the performances of the players for each individual
game. For example, player B performed better than player A in the first match, player A
then performed better than player B in the second match, etc.

This method, however, is not useful in trying to determine the overall performances of
the two players and comparing them. For this we need to calculate the average or mean
score of each player. The player having the better average or mean score has the better
overall performance.

In this lesson, we will learn how to find the mean of a data set.

Mean of a Data Set

Did You Know?

1. Arithmetic mean (AM), mean or average are all the same.

2. Mean is used in calculating average temperature, average mark, average score,

average age, etc. It is also used by the government to find the average individual
expense and income.

3. Mean cannot be determined graphically.

4. Mean is supposed to be the best measure of central tendency of a given data.

5. Mean can be determined for almost every kind of data.

Properties of Mean
Solved Examples

Easy

Example 1:

The amounts of money spent by Sajan during a particular week are listed in the
table.

Day Sunday Monday Tuesday Wednesday Thursday Friday Saturday

Money
spent 270 255 195 230 285 225 115
(in rupees)

Find the average amount of money spent by him per day.

Solution:
Example 2:

The average weight of the students in a class is 42 kg. If the total weight of the
students is 1554 kg, then find the total number of students in the class.

Solution:

Let the total number of students in the class be x.

Thus, there are 37 students in the class.

Medium

Example 1:

For what value of x is the mean of the data 28, 32, 41, x, x, 5, 40 equal to 31?

Solution:

Thus, for x = 35.5, the mean of the data 28, 32, 41, x, x, 5, 40 is 31.

Example 2:

The numbers of children in five families are 0, 2, 1, 3 and 4. Find the average
number of children. If two families having 6 and 5 children are included in this
data set, then what is the new mean or average?
Solution:

Thus, the average number of children for the five families in the initial data set is 2.

Two families are added to the initial set of families.

Thus, the average number of children for the seven families in the new data set is 3.

Example 3:

The mean of fifteen numbers is 7. If 3 is added to every number, then what will be
the new mean?

Solution:

Let be the fifteen numbers having the mean as 7 and x¯x¯ be the mean.

The new numbers are .

Let be the mean of the new numbers.

Thus, the mean of the new numbers is 10.

Hard

Example 1:

The average salary of five workers in a company is Rs 2500. When a new worker
joins the company, the average salary is increased by Rs 100. What is the salary
of the new worker?

Solution:

Let the salary of the new worker be Rs x.

Before the joining of the new worker, we have:

After the joining of the new worker, we have:

Number of workers = 5 + 1 = 6

Average salary = Rs (2500 + 100) = Rs 2600

Thus, the salary of the new worker is Rs 3100.

Example 2:

Find two numbers that lie between and .

Solution:

The given numbers are and .

Mean of the two numbers =

Now, we know that the mean of any two numbers lies between the numbers.

Hence, < <

Mean of and =

Hence, < <

And < < <

So, two numbers that lie between and are and .

Example 3:

If is the mean of the n observations , then prove that

Solution:

It is given that is the mean of the n observations .

Thus,

Now,

Thus, the given result is proved.

Mean Of Grouped Data Using The Direct Method

A cricket player played 7 matches and scored 88, 72, 90, 94, 56, 62, and 76 runs. What
is the average score or mean score of the player in these 7 matches?
We know that,

“The mean is the sum of all observations divided by the number of observations”.

We can use the following formula to find the mean of the given data.

Using this formula, the mean of scores obtained by the player

= 76.86

Thus, the average score of the player is 76.86. There are many situations where the
number of observations is very large and then it is not possible to use this formula to
find the mean of the given data.

Let us consider such a situation.

Let us solve some more examples to understand the concept better.

Example 1:

The following table shows the various income brackets of the employees of a
company.
Income of 10000 − 15000 − 20000 − 25000 30000 35000 40000
employees (in 15000 20000 25000 − − − −
Rupees) 30000 35000 40000 45000

No. of employees 32 18 13 7 14 5 11

Find the average monthly income of each employee.

Solution:

Firstly, we will calculate the class marks of each class interval and then the product of
the class marks with the corresponding frequencies. By doing so, we obtain the
following table.
 Income of No. of Class xi × fi
employees employees: fi Mark: xi

(in Rupees)

10000 − 15000 32 12500 400000

15000 − 20000 18 17500 315000

20000 − 25000 13 22500 292500

25000 − 30000 7 27500 192500

30000 − 35000 14 32500 455000

35000 − 40000 5 37500 187500

40000 − 45000 11 42500 467500

Total (∑) 100 2310000

The mean can now be easily calculated using the formula.

Mean

Hence, the average income of the employees is Rs 23100.

Example 2:

The mean of the following frequency distribution is 62.8 and the sum of all the
frequencies is 50. Find the value of f1 and f2.

Class Interval Frequency

 0 − 20 5

20 − 40 f1

40 − 60 10

60 − 80 f2

80 − 100 7

100 − 120 8

Total 50

Solution:

Firstly, let us find the class marks of each class interval and then the product of class
marks with the corresponding frequencies for each class interval as shown in the
following table.

Class Interval Frequency: fi Class Mark: xi xi × fi

0 − 20 5 10 50

20 − 40 f1 30 30 f1

40 − 60 10 50 500

60 − 80 f2 70 70 f2

80 − 100 7 90 630

100 − 120 8 110 880

 30 + f1 + f2 = 50 2060 + 30 f1 + 70 f2

It is given that the sum of the frequencies is 50.

∴ 30 + f1 + f2 = 50

f1 + f2 = 20

f1 = 20 − f2 … (1)

The mean is given as 62.8.

∴ = 62.8

Using equation (1),

30(20 − f2) + 70 f2 = 1080

600 + 40 f2 = 1080

40 f2 = 1080 − 600 = 480

f2 =

On putting the value of f2 in equation (1), we obtain

f1 = 20 − f2 = 20 − 12 = 8
Thus, the values of f1 and f2 are 8 and 12 respectively.

Mean Of Grouped Data Using Assumed Mean Method

We know that direct method can be used to find the mean of any data given in grouped
form, but the calculation in direct method becomes very tough when the data is given in
the form of large numbers, because finding the product of xi and fi becomes difficult and
time consuming.

Therefore, we introduce assumed mean method to find the mean of grouped data.
This method is also known as shift of origin method. This is an easier method to find
the mean as it involves less calculation.

Let us solve more examples using the assumed mean method.

Example 1:

The following table shows the life time (in hours) of 20 bulbs manufactured by a
reputed company.

Life time (in hours) Number of bulbs

1000 − 2000 2

2000 − 3000 3

3000 − 4000 6

4000 − 5000 5

5000 − 6000 3
 6000 − 7000 1

Find the average life time of a bulb in hours.

Solution:

Firstly, we calculate the class mark of each class-interval and assume one of them as
the assumed mean. Here, we take a = 3500. The calculations of the deviations and the
product of the deviations with the corresponding frequencies have been represented in
the following table.

Life time Class Mark: xi Deviation di = xi − a fi di × fi

(in hours)

1000 − 2000 1500 −2000 2 −4000

2000 − 3000 2500 −1000 3 −3000

3000 − 4000 3500 0 6 0

4000 − 5000 4500 1000 5 5000

5000 − 6000 5500 2000 3 6000

6000 − 7000 6500 3000 1 3000

∑ fi = 20 ∑ difi = 7000

Using the formula,

= 3500 + 350
= 3850

Thus, the average lifetime of a bulb is 3850 h.

Example 2:

The following table shows the percentage of girls in the top 33 schools of Delhi.
Percentage of Girls Number of schools
15 − 25 5
25 − 35 6
35 − 45 10
45 − 55 5
55 − 65 4
65 − 75 2
75 − 85 1

Find the mean percentage of girls by using the assumed mean method.

Solution:

Firstly, we calculate the class mark of each class-interval and assume one of them as
the assumed mean. Here, we take a = 50. The calculations of the deviations and the
product of the deviations with the corresponding frequencies have been represented in
the following table.

Percentage of girls Class Mark xi Deviation Frequency di × fi

di = xi − a fi

15-25 20 −30 5 −150

25-35 30 −20 6 −120

35-45 40 −10 10 −100

45-55 50 0 5 0
 55-65 60 10 4 40

65-75 70 20 2 40

75-85 80 30 1 30

∑ fi = 33 ∑ difi = −260

Using the formula, , we obtain

Thus, the mean of the given data is 42.12 i.e., the mean percentage of girls in the 33
schools of Delhi is 42.12.

Mean Of Grouped Data Using Step Deviation Method

In the assumed mean method, we assume the mean as a from the class-marks and we
use the following formula to find the actual mean.

Where, di is the deviation of a from xi.

When the data is given in the form of large numbers, then sometimes it is difficult and
even lengthy to find the mean by using the assumed mean method. In such cases, we
follow another method called step deviation method or shift of origin and scale
method. Using this method, we can further reduce the calculation.

Let us solve one more example to understand the step deviation method better.

Example 1:

Calculate the mean of the following data using step deviation method.
Class-interval 0 − 20 20 − 40 40 − 60 60 −80 80 −100 100 −120 120 − 140

Frequency 12 22 16 13 17 8 12

Solution:

Let us assume a = 50

Let us calculate the deviations of class marks from the assumed mean a. The
calculations are shown in the following table.

Class- Frequency Class di = xi − a fi × ui

interval Mark xi
fi

0 − 20 12 10 −40 −2 −24

20 − 40 22 30 −20 −1 −22

40 − 60 16 50 = a 0 0 0

60 − 80 13 70 20 1 13

80 − 100 17 90 40 2 34

100 − 120 8 110 60 3 24

120 − 140 12 130 80 4 48

Total
∑ fi = 100 ∑uifi=
73

Highest common factor of all the di’s = h = 20

Now, using the formula , we obtain

 Thus, the mean of the given data is 64.6.

Medians of Data Sets Having Odd or Even Number of Terms

Median as the Measure of Central Tendency

Let us consider the group of half dozen individuals shown in the picture. There are five
children standing with a very tall man.

You can see that the distribution of height in this group is unbalanced or asymmetrical
because one individual is much taller than the others. When we calculate the mean
height of the five children, the value so obtained will be close to the actual height of
each child.

However, when we calculate the mean height of the six persons (including the really tall
man), the value so obtained will give the impression that each individual in the group is
quite tall. So, in this case, the mean will not be an appropriate measure of central
tendency. In situations such as this, we use median as the measure of central tendency.

In this lesson, we will study about median and the method to calculate the same for any
given data.

Method to Find Median

Median can be defined as follows:

Median is the value of the middlemost observation when the data is arranged in
increasing or decreasing order.

The method to find median can be summarized as follows:

Step 1: Arrange the data in increasing or decreasing order.

Step 2: Let n be the number of observations. Here, two cases arise.

Case 1: When n is even, the median of the observations is given by the formula

Median = Mean of the and observations

Case 2: When n is odd, the median of the observations is given by the formula

Median = Value of the observation

Did You Know?

1. Median is used to measure the distribution of earnings, to calculate the poverty line,
etc.

2. Median is independent of the range of the series as it is the middle value of a data.
So, it is not affected by extreme values or end values.

3. The median of a data is incapable of further algebraic or mathematical treatment. For

example, if we have the median of two or more groups, then we cannot find the median
of the bigger group formed by combining the given groups.

4. Median is affected by the fluctuation in data as it depends only on one item, i.e., the
middle term.
Know Your Scientist

Antoine Augustin Cournot

Antoine Augustin Cournot (1801−1877) was a French economist, philosopher and
mathematician. The term median was introduced by him in 1843. He used this term for
the value that divides a probability distribution into two equal parts or halves.

In the field of economic analysis, he developed the concept of functions and probability.
He introduced the demand curve to show the relationship between price and demand
for any given item. He is best remembered for his theory of strategic behaviour of
competitors in a market having only two players, i.e., in a duopoly.
Solving Problems Based on Finding the Median of a Given Data

Know More

Advantages of median

1. Median is better suited for non-symmetrical distributions as it is not much affected by

very low and high values. Non-symmetrical distribution means the data is distributed in
such a way that the values toward one end are much higher or lower than the values
toward the other end. For example, 1, 2, 3, 4, 25, 30, 50, 60 is a non-symmetrical
distribution.

2. Knowing the median test score is important to people who want to know whether they
belong to the ‘better half of the population’ or not.

Mode can be defined as:

“The observation which occurs the maximum number of times is called mode”.
Or “the observation with maximum frequency is called mode”.

Example 2:
Find the mode of the following marks obtained by 15 students.
2, 5, 1, 0, 8, 11, 8, 12, 19, 18, 13, 10, 9, 8, 1
Solution:
We arrange the given data as follows:
0, 1, 1, 2, 5, 8, 8, 8, 9, 10, 11, 12, 13, 18, 19
We observe that 8 occurs most often. So, the mode is 8.
Solved Examples

Easy

Example 1:

Find the median of these observations: 324, 250, 234, 324, 250, 196, 189, 250, 313,
227.

Solution:

On writing the observations in ascending order, we have the following sequence.

189, 196, 227, 234, 250, 250, 250, 313, 324, 324

Here, the number of observations (n) is 10, which is an even number.

∴ Median = Mean of the and observations

⇒ Median = Mean of the 5th and 6th observations

Here, the 5th and 6th observations are the same value, i.e., 250.

∴ Median = 250

Medium

Example 1:

The minimum temperatures (in °C) for fifteen days in a city are recorded as
follows:

4.5, 4.7, 3.9, 5.2, 5.0, 4.2, 4.6, 4.2, 4.2, 4.5, 5.7, 2.3, 6.0, 3.5, 4.0

Find the median of the minimum temperatures.

Solution:

On arranging the data in ascending order, we obtain the following sequence.

2.3, 3.5, 3.9, 4.0, 4.2, 4.2, 4.2, 4.5, 4.5, 4.6, 4.7, 5.0, 5.2, 5.7, 6.0

Here, the number of observations (n) is 15, which is an odd number.

∴ Median = observation

⇒ Median = observation

Here, the 8th observation is 4.5.

Thus, the median of the minimum temperatures for the fifteen days was 4.5°C.

Example 2:

The marks obtained (out of 50) by fifteen students are 27, 31, 29, 35, 30, 42, 45, 41,
37, 32, 28, 36, 44, 34 and 43. Find the median. If the marks 27 and 44 are replaced
by 25 and 46, then what will be the new median?

Solution:

The given marks can be arranged in ascending order as follows:

27, 28, 29, 30, 31, 32, 34, 35, 36, 37, 41, 42, 43, 44, 45

Here, the number of observations (n) is 15, which is an odd number.

∴ Median = observation

= observation

= 8th observation

= 35
After replacing 27 and 44 by 25 and 46, the marks are arranged in ascending order as
follows:

25, 28, 29, 30, 31, 32, 34, 35, 36, 37, 41, 42, 43, 45, 46

∴ New median = observation

= observation

= 8th observation

= 35

Hard

Example 1:

The following observations are arranged in ascending order.

11, 17, 20, 25, 39, 2y, 3y + 1, 69, 95, 112, 135, 1204

If the median of the data is 53, then find the value of y.

Solution:

The observations in ascending order are given as follows:

11, 17, 20, 25, 39, 2y, 3y + 1, 69, 95, 112, 135, 1204

Here, the number of observations (n) is 12, which is even.

∴ Median = Mean of and observations

It is given that the median of the observations is 53.

∴ 53 = Mean of and observations.

⇒ 53 = Mean of and observations

⇒ 53 = Mean of and observations

The 6th and 7th observations are 2y and 3y + 1 respectively.

So,

Median of Grouped Data Given in Discrete Form Using Cumulative Frequency

Table

The middle value obtained after arranging a data in ascending or descending order is
known as median of the data.

The median of a data having an odd number of terms is simply the value of the middle
observation whereas the median of a data having an even number of terms is the mean
of the two middle observations of the data.

However, there are conditions where a grouped data is provided. In such cases, the
above mentioned method cannot be directly applied to find the median of a data.
The method used in such cases is explained below with the help of an example.

The following table represents the salaries of 150 workers of a company.

Salary (in Rs) 8000 12000 16000 20000 24000

Number of workers 25 40 30 50 5

Let us find the median salary of the workers for the given information.

First, we have to find the cumulative frequency of the data.

The cumulative frequency (c.f.) for a class is the total of the frequencies above or
below it.

The cumulative frequency of each class in the above table is calculated as follows:
 Salary (in Rs)
Number of workers (f ) Cumulative frequency (c.f.)
(x)
8000 25 25
12000 40 40 + 25 = 65
16000 30 30 + 65 = 95
20000 50 50 + 95 = 145
24000 5 5 + 145 = 150
∑f = 150

Now, we can see that the 75th observation occurs in the cumulative frequency 95 whose
corresponding salary is Rs 16000.

The median salary of the above data is Rs 16000.

Let us try to solve some more problems to understand the concept better.

Example 1:
The following table shows the heights of 53 students of a class. What is the median
height of the class?

Height (in cm) 120 130 140 150 160

Number of students 4 8 17 20 4

Solution:

Height (in cm) (x) Number of students (f ) Cumulative frequency (c.f.)

120 4 4
130 8 8 + 4 = 12
140 17 17 + 12 = 29
150 20 20 + 29 = 49
160 4 4 + 49 = 53
∑f = 53
Now, we can see that the 27th observation occurs in the cumulative frequency 29 whose
corresponding height is 140 cm.

The median height of the class is 140 cm.

Example2:
What is the median of the given data?
x f
5 3
10 7
15 4
20 11
25 2
35 15
40 12
50 4

Solution:
x f c.f.
5 3 3
10 7 7 + 3 = 10
15 4 4 + 10 = 14
20 11 11 + 14 = 25
25 2 2 + 25 = 27
35 15 15 + 27 = 42
40 12 12 + 42 = 54
50 4 4 + 54 = 58
∑f = 58

Now, we can see that the 29th observation occurs in the cumulative frequency 42,
whose corresponding variable x is 35.

The median of the above data is 35.

Quartile Deviation

The range and quartile deviation are measures of dispersion that depend on the values
of the variables at a particular position in the distribution. The range is based on
extreme values in the distribution. It does not consider the deviation among the values.
In order to study the variation among the values, the measure of inter-quartile range is
used.

Inter-Quartile Range = Third Quartile − First Quartile = Q3 − Q1

Quartile deviation is the half of the difference between third quartile, Q3 and first
quartile, Q1 of the series.

Quartile deviation gives half of the range of middle 50% observations. Quartile deviation
is also known as semi-inter-quartile range.

Calculation of quartile deviation

Here, L = lower limit of the quartile class

f = frequency of the quartile class

h = class interval of quartile class

c.f. = total of all the frequencies below the quartile class

N = total frequency, ∑f∑f

Solved Examples

Example 1:

Find the quartile deviation for the following data.

15, 65, 30, 70, 50, 25, 40, 75, 45, 60

Solution:

First, arrange the observations in ascending order, as shown below:

15, 25, 30, 40, 45, 50, 60, 65, 70, 75

Here, number of observations, n = 10

= Value of 2.75th observation

= Value of 2nd observation + 0.75(Value of 3rd observation − Value of 2nd observation)

= 25 + 0.75(30 − 25)

= 25 + 0.75 × 5

= 28.75

= Value of 8.25th observation

= Value of 8th observation + 0.25(Value of 9th observation − Value of 8th observation)

= 65 + 0.25(70 − 65)

= 65 + 0.25 × 5

= 66.25

Example 2:

Find the quartile deviation for the following data.

Age of workers 25 35 45 55 65
 Number of workers 8 12 20 16 4

Solution:

Here, the data is in ascending order. First, prepare the table with cumulative
frequencies(less than type).

Age of workers(xi) Number of workers(fi) Cumulative frequency

25 8 8
35 12 20 ← Q1
45 20 40
55 16 56 ← Q3
65 4 60
Total N = 60

Here, N = 60

Example 3:

Compute the quartile deviation for the following data.

C.I. 10-19 20-29 30-39 40-49 50-59

Frequency 3 4 6 5 2
Solution:

In the given data, the classes are discontinuous. First, convert the classes into
continuous classes and prepare the table with cumulative frequencies(less than type).
 C.I. Continuous classes Frequency Cumulative frequency
10-19 9.5-19.5 3 3
20-29 19.5-29.5 4 7 ← Q1
30-39 29.5-39.5 6 13
40-49 39.5-49.5 5 18 ← Q3
50-59 49.5-59.5 2 20
Total N = 20

Mode Of A Data Set

Bhangra’s is a very popular shop that sells watches of foreign brands in Delhi’s posh
Connaught Place market. The owner of the shop decided to stock the brand whose
watches were selling the most. He decided to look at the previous month’s sales, which
is listed as
Brand Number of watches sold
Alpha 17
 Townzen 23
Tag Heuim 7
Twatch 13

Based on this information, the owner decided to stop keeping Tag Heuim watches
because very few people buy them. He also decided to keep more varieties of Townzen
watches because most people were buying this brand.

In this data set, the highest occurring event (23) corresponds to Townzen watches and
is known as the mode of this data set. Just like mean and range, mode is another
measure of central tendency of a group of data. It can be defined as

The value of a set of data that occurs most often is called the mode of the
data.

Here, the data set did not contain too many terms and could thus be easily arranged in
ascending order. However, in case of very large data, it is not always easy to arrange it
in ascending or descending order. Therefore, in such cases, it is better to arrange the
data set in the form of a table with tally marks.

A collection of data can have more than one mode. The data sets having one mode or
two modes or more than 2 modes are said to have uni-mode or bi-mode or multi-
mode.

Let us now look at some more examples to understand this concept better.

Example 1:

Find the mode of the following numbers.

2, 6, 7, 5, 4, 2, 6, 7, 9, 7, 8, 3, 2, 11

Solution:

The given set of numbers can be arranged in ascending order as

2, 2, 2, 3, 4, 5, 6, 6, 7, 7, 7, 8, 9, 11

Here, 7 and 2 occur most often (3 times). Therefore, both 7 and 2 are the modes of the
given set of numbers.

Example 2:
Find the mode of the following data set.

1000, 200, 700, 500, 600, 160, 270, 300, 360, 950

Solution:

The increasing order of the given numbers is

160, 200, 270, 300, 360, 500, 600, 700, 950, 1000

Here, every number is occurring only once.

Thus, the given data has no mode.

Note: The above example shows that the mode of a data may or may not be unique.
Also, there are some data sets which do not have any mode.

Example 3:

Determine whether the data 35, 30, 32, 35, 40, 30, 25, 30, 22, 30 has uni-mode,
bi-mode or multi-mode.

Solution:
From the data, we observe that 30 repeats maximum times (4 times). Thus, the mode of
this data is 30. Since there is only one mode of this data, so the given data has uni-
mode.

Example 4:
Find the type of mode of the data 25, 23, 23, 25, 27, 26, 23, 24, 23, 25, 28, 25.

Solution:
From the data, we observe that 23 and 25 repeats maximum times (4 times). Thus, the
mode of this data is 23 and 25. Since there are two modes of this data, so this data has
bi-mode.

Example 5:
Which type of mode is represented by the data as shown below?
Solution:
From the frequency table, we observe that 16, 24 and 32 repeats maximum times (9
times). Thus, the mode of this data is 16, 24, and 32. Since there are three modes of
this data, so this data has multi-mode.