UNIT FOUR:

MEASURE OF CENTRAL TENDENCY

At the end of this unit you should be able to:

1. determine or calculate the mean, mode and median for ungrouped data
2. determine or calculate the mean, mode and median for grouped data
3. outline the advantages and disadvantages of the mean, mode and median as measures of
central tendency for raw or summarized data

The single most important measure describing numerical information is the location of the center
of the data. The term “central tendency” refers to anyone of a number of different measures
including MEAN, MODE and MEDIAN, each being appropriate for certain descriptive purposes
and not others.

THE ARITHMETIC MEAN

This is probably the most widely used form of average. It is calculated by summing all the
observations in a data set and then dividing by the total number of observations. It is usually
denoted by x if taken from a sample and  when taken from a population.

THE MEAN FOR RAW DATA

The sample mean for raw data, not organized into a table is given by

x=
x ;
n

where n is the number of observations and  x (sigma x) is the sum of all the data values.
Example: The following are the ages of eight employees of a small firm. Find their mean age.
53 32 61 27 39 44 49 57

Solution:
53 + 32 + 61 +  + 49 + 57 362
x= = = 45.25yrs
8 8
 Practice Exercise

The following data shows the number of fruit produced for five months from a tree. Calculate the
mean

25 29 34 35 18
THE MEAN FOR UNGROUPED DATA

If the data is organized in a table, but not grouped into intervals, we call it ungrouped data. The
sample mean for ungrouped data is given by

x=
 xf
f
where f is the frequency and x is the variable.

Example: Below represent the ages of 20 students in a preschool. Calculate the mean.

Ages Frequency

1 2

2 4

3 7

4 5

5 2

Solution: To do this, we add another column xf to the table, where the variable age becomes ‘x’
and the frequency ‘f’

x f xf

1 2 2

2 4 8

3 7 21

4 5 20

5 2 10

20 61

 xf 61
x= = = 3.05 yrs
f 20
  Practice Exercise

Find the mean of the data in the table below showing the number of cars passing on a bridge for
25 days

No. of Cars Frequency

6 3
7 6
8 10
9 6

THE MEAN FOR GROUPED DATA

If the data is grouped into intervals in a table, we call it grouped data and we use the midpoint
values as a representative of x in the formula below.

x=
 xf
f
UCB + LCB
RECALL: Midpoint =
2

Example:
The speed to the nearest mile per hour, of 120 vehicles passing a check point were recorded and
grouped in the table below.

Speed Frequency

21-25 22

26-30 48

31-35 25

36-45 16

46-60 9

Find the average speed.

Solution:
We need to calculate the midpoints by first writing out the class boundaries.

Speed f Class Midpoint xf

Boundaries
x

21-25 22 20.5-25.5 23 506

26-30 48 25.5-30.5 28 1344

31-35 25 30.5-35.5 33 825

36-45 16 35.5-45.5 40.5 648

46-60 9 45.5-60.5 53 477

120 3800

x=
xf 3800
= = 31.67 mph
f 120

 Practice Exercise

The table below shows the time taken for 25 athletes13

to complete a race.

Time (sec) Frequency

4-6 2

7-9 3

10-12 7

13-15 8

16-18 5

Find the mean.

TRIMMED MEAN

This is used to omit outlier values which may lie at the beginning or the end of the data

STEPS: For a p% trimmed mean

1. Arrange the data in ascending order

p
2. Calculate n  ; where n is the total number of observations
100

3. Omit or trim the value in part 2) from the first and last numbers.

4. Calculate the mean of the remaining values.

Example: Find the 20% trimmed mean of the numbers below:

2, 6, 7, 5, 9, 6, 1, 2, 4, 5

Re-order: 1, 2, 2, 4, 5, 5, 6, 6, 7, 9

p 20
n = 10  =2
100 100

1, 2, 2, 4, 5, 5, 6, 6, 7, 9

x=
 x = 2 + 4 + 5 + 5 + 6 + 6 = 28 = 4.7
n 6 6

THE MODE

This is the value, which appears most frequently in the data set. This would suggest that data can
have no mode, one mode, two modes or any number of modes.

Example:
Find the mode for the data set below.
15, 16, 17, 20, 15, 14, 16, 15

Solution:
The mode of the distribution is 15.
 Example:
Below represent the ages of 20 students in a preschool. Find the mode.

Ages Frequency

1 2
2 4
3 7
4 5
5 2

Solution: To find the mode of ungrouped data, we look for the data entry with the highest
frequency. Therefore the mode of the distribution is 3 yrs., since it occur the most.

 Practice Exercise

14 Find the mode of the data sets below:

a) 23, 11, 56, 23, 778, 7, 34, 26

b)
No. of Cars Frequency
6 3
7 6
8 10
9 6
Mode for Grouped Data

As we saw in the section on data, grouped data is divided into classes. We have defined mode as
the element which has the highest frequency in a given data set. In grouped data, we calculate from
the mode using the formula below.

 f1 − f 0 
Mode = L +    c
 2 f1 − f 0 − f 2 

where

• L is the lower class limit of the modal class

• f1 is the frequency of the modal class
• f0 is the frequency of the class before the modal class in the frequency table
• f2 is the frequency of the class after the modal class in the frequency table
• c is the class width of the modal class

Example: Find the mode of the data set below showing the height in cm of 100 potted plants.

Height Frequency
60 − 63 5
63− 66 18
66 − 69 42
69 − 72 27
72 − 75 8

Solution: We first begin by location the modal class which is the class or interval with the
highest frequency. The modal class is highlighted in the table below. f1 is always the highest
frequency in the table. Therefore, in our example, f1 is 42.

Height Frequency
60 − 63 5
63− 66 18
66 − 69 42
69 − 72 27
72 − 75 8

L = 66 f 0 = 18 c=3
f 1 = 42 f 2 = 27

 42 − 18 
Mode = 66 +    3 = 67.85
 2(42) − 18 − 27 
Example 2: The table below shows the time taken in minutes by 100 athletes to complete a race.
Find the mode.

Time Frequency

13-15 12
16-18 17
19-21 23
22-24 18
25-27 16
28-30 14

Solution 2: We first set up the boundaries

Time Class Boundaries Frequency

13-15 12.5-15.5 12
16-18 15.5-18.5 17
19-21 18.5-21.5 23
22-24 21.5-24.5 18
25-27 24.5-27.5 16
28-30 27.5-30.5 14

L = 18 .5 f 0 = 17 c=3
f 1 = 23 f 2 = 18

 23 −17 
Mode = 18 .5 +  3

 2(23) − 17 − 18 

 6
= 18.5 +    3
11
 

= 18.5 +1.636

= 20.1

Note: Always make sure that the variable is in class boundaries before finding the
values of L and c.

 Practice Exercise
The table below show the weight of 100 steel produced in a factory, in pounds. Calculate the
mode.

Weight Frequency
36-40 12
41-45 23
46-50 34
51-55 21
56-60 10

THE MEDIAN FOR RAW DATA

The median, denoted by ~ x , is the value that lies exactly

15 in the center of the distribution,
provided that the distribution is arranged in ascending numerical order

When n is odd
If the number of observations is odd, we find the median by following the following steps:
1. Rearrange the data in ascending order.
th
 n +1
2. The median is the   term
 2 
Example 1:
Find the median of the data set below:
2, 7, 3, 8, 10, 3, 5
Solution 1:
Rearranging we get,
2, 3, 3, 5, 7,8,10

Since there are 7 data entries, it means that n = 7 . The median is the hence given by
 7 +1 8
  = = 4 term
th

 2  2
Therefore the median is 5.
2, 3, 3, 5 , 7,8,10

When n is even
If the number of observations is even, the median value lies between the two center values. We
find the median by following the following steps:
1. Rearrange the data in ascending order.
th
 n +1
2. The median is the average of the two terms around the   value.
 2 

Example 2:
Find the median of the data set below:
13, 14, 16, 10, 20, 23

Solution 2:
Rearranging we get,
10, 13, 14, 16, 20, 23

Since there are 6 data entries, it means that n = 6 . The median is the hence given by
 6 +1 7
  = = 3.5
 2  2
Therefore the median lies half way between the third and fourth term. To find the median, we
take the average of the two middle terms, 14 and 16.
10, 13, 14, 16, 20, 23

The median is therefore

 14 + 16  30
 = = 15
 2  2

 Practice Exercise

Find the median for the following data sets

a) 12, 15, 08, 22, 29, 11, 28,10, 19, 32

b) 77, 83, 11, 23, 109, 92, 84, 65, 88, 33, 73, 54, 22

3.8 THE MEDIAN FOR GROUPED DATA

For data organized into class intervals, we calculate the median using the formula

𝑛+1
−𝑚
𝑥̃ = 𝑙 + ( 2 )×𝑐
𝑓

where:

l is the lower limit of the median class

n is total number of observations
m is the cumulative frequency of the interval before median class
f is the frequency of the median class
c is the class width of the median class
𝑛+1
We locate the median class by first calculating the value of and using the cumulative
2
frequencies.
Example 1: Find the median of the data set below showing the height in cm of 100 potted
plants.

Height Frequency
60 − 63 5
63− 66 18
66 − 69 42
69 − 72 27
72 − 75 8

Solution 1: We begin by adding an additional column to the table to calculate the cumulative
frequencies.

Height Frequency Cumulative Frequency

60 − 63 5 5
63− 66 18 23
66 − 69 42 65
69 − 72 27 92
72 − 75 8 100

𝑛+1 101
We then locate the median class by calculating 2
= 2 = 50.50

l = 66 m = 23 c=3
n = 100 f = 42

𝟏𝟎𝟎 + 𝟏
− 𝟐𝟑
̃ = 𝟔𝟔 + ( 𝟐
𝒙 ) × 𝟑 = 𝟔𝟕. 𝟗𝟔
𝟒𝟐

Example 2: The table below shows the time taken in minutes by 100 athletes to complete a race.
Find the median.

Time Frequency

13-15 12
16-18 17
19-21 23
22-24 18
25-27 16
28-30 14
Solution 2: We need to set up the class boundaries and calculate the cumulative frequencies.

Time Class Boundaries Frequency Cumulative Frequency

13-15 12.5-15.5 12 12
16-18 15.5-18.5 17 29
19-21 18.5-21.5 23 52
22-24 21.5-24.5 18 70
25-27 24.5-27.5 16 86
28-30 27.5-30.5 14 100
𝑛+1 100+1
We then locate the median class by calculating 2
= 2 = 50.5

l = 18.5 m = 29 c=3
n = 100 f = 23
𝟏𝟎𝟏
−𝟐𝟗
𝟐
̃ = 𝟏𝟖. 𝟓 + (
𝒙 ) × 𝟑 = 𝟐𝟏. 3
𝟐𝟑

 Practice Exercise
17
The table below show the weight of 100 steel produced in a factory, in pounds. Calculate the
median.
Weight Frequency
36-40 12
41-45 23
46-50 34
51-55 21
56-60 10

COMPARING THE MEAN, MODE AND MEDIAN

Below are a few notes on the measures of central tendency covered in this unit

1. The arithmetic mean is affected by extreme values (Outliers).

2. The arithmetic mean can be used in other statistical calculations.
 3. The mean and median may not be a number of the data set.
4. The mode is always a number of the data set.
5. There may be more than one mode in a distribution of data.
6. Mode is best used in business planning for identifying those products in greatest demand.
7. The median is the preferred average when the data is skewed.

1. If the mean of the following numbers is 8, find the value of y.

3, 5, 4y, 8, 2, 8

2. The following are the ages (in years) of all eight employees of a small company:
53, 32, 61, 27, 39, 44, 49, 57
Find
a) the mean age of these employees
b) the median
c) the mode

3. Use the table below to find the mean and the modal score.

Score (x) Frequency

4 4
5 10
6 5
7 6
8 2
9 5

4. The distribution below records the overtime hours worked by employees of the Marketing
Agency last month

Overtime Frequency
Hours
 1–6 2
7 – 12 5
13 – 18 10
19 – 24 6
25 – 30 3
31 - 36 6

a) What is the lower class boundary of the interval 13 – 18?

b) What is the upper class boundary of the interval 25 – 30?
c) What is the midpoint of the interval 31 – 36?
d) What is the width of the class boundaries?
e) What is the mean number of overtime hours worked by employees?
f) What is the median?
g) What is the mode?

5. Data on the amount of time they spent per day on their phones. The results are displayed in
the table below.
Time, minutes Frequency

0t 5 5

5  t  10 20

10  t  20 32

20  t  30 23

30  t  40 12

40  t  60 8

Calculate estimates of
a) The mean time spent per day on these mobile phones.
b) the mode
c) The median