Lesson 3

Measures of Central
Tendency
The Mean:

The sum of the values (positive , negative or zero) divided

by the number of values

Is called the Mean , Sample Mean , Arithmetic Mean and

average.

If 𝒙𝟏 , 𝒙𝟐 , … , 𝒙𝒏 are values, then the mean is:

𝒙𝟏 + 𝒙𝟐 + ⋯ + 𝒙𝒏 ∑𝒏𝒊%𝟏 𝒙𝒊
!=
𝒙 =
𝒏 𝒏
2
Example
Suppose that the following data represents the ages
(in year) of 3 persons :

x1 = 30, x2 = 35, x3 = 27.

Then, the mean is:

30 + 35 + 27 92
x= = = 30.67
3 3
 Mean for grouped data

∑ 𝑓𝑥
𝑥̅ =
∑𝑓

Where: 𝑥 and 𝑓 are the midpoints and frequencies

of a class, respectively.
 Mean for grouped data
1. Find the midpoint of each class.

2. Find the sum of the products of the

midpoints and the frequencies.

3. Find the sum of the frequencies

4. Find the mean of the frequency

distribution.
 Example
The table below gives the frequency distribution of the
daily commuting times (in minutes) from home to UT for
25 students. Calculate the mean of the daily commuting
times.
Daily commuting time (min) f x fx
0 to less than 10 4 5 20
10 to less than 20 9 15 135
20 to less than 30 6 25 150
30 to less than 40 4 35 140
40 to less than 50 2 45 90
Total 25 535

∑ "# $%$
𝑥̅ = = = 21.4 𝑚𝑖𝑛
∑" &$
Properties of arithmetic Mean
It is unique - there is only one answer.
Affected by extreme values (outliers)

Example.

The sample mean of 2,3,4 is 3.

The sample mean of 2,3,40 is 15.

The mean increased from 3 to 15 because 40 is an

extreme value.
The sum of the deviations of the observations from their
mean is always Zero
n

å (x - x ) = 0
i =1
i

Example: Find the sum of the deviations of the values 3, 4,

6, 8,14 from their mean

3 + 4 + 6 + 8 + 14 35
x= = =7
5 5
n

å (x - x ) = (3 - 7) + (4 - 7) + (6 - 7) + (8 - 7) + (14 - 7) = 0
i =1
i
The Median

The value which divides the data (after have been arranged)

into two equal halves, with half of the data being lower than

the median and half higher than the median.

Median Steps

If 𝒙𝟏 , 𝒙𝟐 , … , 𝒙𝒏 are the values, then the

median computed as follows:

1. Sort the values into ascending order.

2. If we have an odd number (n) of values, the

median is the middle value.

𝑴𝒆 = 𝒙𝟏(𝒏&𝟏)
𝟐
 3. If we have an even number of values, the
median is the mean of the two middle values.
1æ ö
M e = çç x n + x n ÷÷
2è 2 +1
2 ø

Example: Compute The sample median of (12, 24, 19, 20, 7) .

Solution
q Sort the values into ascending order.
7,12, 19, 20, 24
q Number of values is 5 is an odd the sample median is :
M e = x1 = x1 = x3 = 19
( n +1) ( 5+1)
2 2
Example
Compute The sample median of

(12, 24, 19, 20, 7 , 5) .

Solution
q Sort the values into ascending order.
5,7,12, 19, 20, 24
q Number of values is 6 is an even the sample median is :
1æ ö 1æ ö
M e = çç x n + x n ÷÷ = ç x 6 + x 6 ÷
2è 2 +1
2 ø 2 ç +1 ÷
è 2 2 ø

( x3 + x4 ) (12 + 19 )
= =
2
= 15.5
2 12
Median from grouped data
The median of data organized into a frequency distribution
can be estimated by:
o Find the cumulative frequency
o Determine the rank of the median by dividing 𝑵/𝟐 or ∑𝒇/𝟐
o locate the class in which the median lies and then use the
following formula to calculate the median:
N
- å fm
L1 + ( 2 )´c
f median
𝑳𝟏 = lower class boundary
∑𝒇𝒎 = Sum of frequency of all class lower median class.
𝒇𝒎𝒆𝒅𝒊𝒂𝒏 = frequency of median class, 𝒄 = Class width (size)
Example
For the following frequency table, calculate the median

𝑪𝒍𝒂𝒔𝒔𝒆𝒔 Frequency (𝒇)

60-62 5

63-65 21

66-68 42

69-71 24

72-74 8

𝒕𝒐𝒕𝒂𝒍 𝟏𝟎𝟎
Solution
First find the accumulative frequency
𝑪𝒍𝒂𝒔𝒔𝒆𝒔 Frequency (𝒇) 𝑪𝒖𝒎𝒖𝒍𝒂𝒕𝒊𝒗𝒆 𝒇𝒓𝒆𝒒𝒖𝒆𝒏𝒄𝒚 Second, determine the
60-62
5 5
63-65
rank of the median with
21 26
66-68
42 68
divide the
69-71
24 92 ∑𝒇 𝟏𝟎𝟎
72-74 𝟐
= 𝟐
= 𝟓𝟎
8 100
𝒕𝒐𝒕𝒂𝒍 𝑵 = ∑𝒇 = 𝟏𝟎𝟎

Third, locate the class in which the median lies, which is (66-68)
Finally, use the formula to calculate the median:
𝑳𝟏 = 65.5, ∑𝒇𝒎 =26 𝒇𝒎𝒆𝒅𝒊𝒂𝒏 =42 𝒄 =3
Then the median is
N
- å fm 50 - 26 72
L1 + ( 2 ) ´ c = 65.5 + ( ) ´ 3 = 65.5 + = 67.21
f median 42 42
Properties of the Median

qExtreme values do not affect the median

q It is unique - there is only one answer.

qIt can be calculated from the open class

limits.
The Mode

The mode of a set of values is that which

occurs most frequently

Examples

The mode of the list (1, 2, 2, 3, 3, 3, 4) is 3.

The list (1, 2, 2, 3, 3, 5) has two modes 2 and 3.

No mode for the list (1, 6, 2, 7, 3, 5).

Mode from grouped data
First of all, we have to determine the modal class which is
that class corresponding to the largest frequency
and then, we can compute the mode by using the following
formula
𝚫𝟏
𝑳𝟏 + ×𝒄
𝚫 𝟏 &𝚫 𝟐

𝑳𝟏 = lower class boundary of the model class 𝒄 = Class width (size)

∆& = 𝑓' − 𝑓& , ∆( = 𝑓' − 𝑓(
𝒇𝒎: is the modal frequency (the highest frequency).

𝒇𝟏 : is the previous frequency of 𝒇𝒎

𝒇𝟐 :is the Subsequent frequency of 𝒇𝒎

Example
For the following frequency table, calculate the mode
𝑪𝒍𝒂𝒔𝒔𝒆𝒔 Frequency (𝒇) ∆& = 𝑓' − 𝑓& =42-18=24
60-62 5
63-65 18 𝒇𝟏
∆( = 𝑓' − 𝑓( =42-27=15
66-68 42 𝒇𝒎
69-71 27 𝒇𝟐 𝐿& =65.5
72-74 8
𝒕𝒐𝒕𝒂𝒍 𝟏𝟎𝟎 𝑐 =3

The mode is
𝚫𝟏 𝟐𝟒
𝑳𝟏 + ×𝒄 = 𝟔𝟓. 𝟓 + ×𝟑 = 67.34
𝚫 𝟏 &𝚫 𝟐 𝟐𝟒&𝟏𝟓
Mode properties
o It is not affected by extreme values

o Not necessarily unique - may be more than one answer

o When no values repeat in the data set, the mode is

every value and is useless.

o When there is more than one mode, it is difficult to

interpret and/or compare.

o It can be calculated from the open class limits