You are on page 1of 16

Lesson 4

Measures of dispersion
Range
Variance
Standard Deviation
Coefficient of Variation
Introduction
o The variation or dispersion in a set of data refers to how spread
out the observations are from each other.

The variation is small when the observations are close together.


There is no variation if the observations are the same.

There are various methods that can be used to measure the


dispersion of a dataset, each with its own set of advantages and
disadvantages.
The Range
the result of subtracting the lowest value from the
highest value in a set of data
Example: Find The range of (12, 24, 19, 20, 7) .
Solution:
R = 24 – 7 =17
One of the simplest measures of variability to be
calculated.
Depends only on extreme values and provides no
information about how the remaining data is
distributed.
The Range
Example: from the following two sets of data compute
1. The mean of each set .
2. Range of each set.
3. Compare the dispersion for the two sets of data.
A: 86, 70, 91, 110, 89
B: 89, 87, 89, 92, 85, 92
Solution
Data set Mean Rang
The two set of data A and B have
A 89.2 40
the same means.
B 89.2 7

The conclusion is that the range of B less than that of A, so that


the variation in B is less than that of A.
The Population Variance and standard deviation

If 𝒙𝟏 , 𝒙𝟐 , … , 𝒙𝑵 are the population values, then the


population variance and standard deviation are given
respectively as:
𝟐 𝟐 𝟐 𝑵
𝒙𝟏 − 𝝁 + 𝒙𝟐 − 𝝁 + ⋯ + 𝒙𝑵 − 𝝁 𝟏
𝝈𝟐 = = * 𝒙𝒊 − 𝝁 𝟐
𝑵 𝑵
𝒊%𝟏

𝑵
𝒙𝟏 − 𝝁 𝟐 𝟐
+ 𝒙𝟐 − 𝝁 + ⋯ + 𝒙𝑵 − 𝝁 𝟐 𝟏
𝝈= = * 𝒙𝒊 − 𝝁 𝟐
𝑵 𝑵
𝒊%𝟏

Where 𝝁 is population mean


The Sample Variance and standard deviation

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


variance and standard deviation are given respectively
as:
𝟐 𝟐 𝟐 𝒏
,
𝒙𝟏 − 𝒙 , + ⋯ + 𝒙𝒏 − 𝒙
+ 𝒙𝟐 − 𝒙 , 𝟏
𝒔𝟐 = = ,
* 𝒙𝒊 − 𝒙 𝟐
𝒏−𝟏 𝒏−𝟏
𝒊%𝟏

𝒏
,
𝒙𝟏 − 𝒙 𝟐 𝟐
, + ⋯ + 𝒙𝒏 − 𝒙
+ 𝒙𝟐 − 𝒙 , 𝟐 𝟏
𝒔= = ,
* 𝒙𝒊 − 𝒙 𝟐
𝒏−𝟏 𝒏−𝟏
𝒊%𝟏

% is sample mean
Where 𝒙
Example. Compute the population variance and
standard deviation of the following observations (ages in
year): 10, 21, 30, 53, 56.
𝑵
Solution 𝟏 𝟏𝟎 + 𝟐𝟏 + 𝟑𝟎 + 𝟓𝟑 + 𝟓𝟔 𝟏𝟕𝟎
𝝁 = * 𝒙𝒊 = = = 𝟑𝟒
𝑵 𝟓 𝟓
𝒊%𝟏
𝑵
𝟏
𝝈𝟐 = * 𝒙𝒊 − 𝝁 𝟐
𝑵
𝒊%𝟏
10 − 34 ' + 21 − 34 '+ 30 − 34 ' + 53 − 34 ' + 56 − 34 '
=
5
1606
= = 𝟑𝟐𝟏. 𝟐 Mean 34
5
𝑵 Variance 321.2
𝟏 𝟐
𝝈= * 𝒙𝒊 − 𝝁 = 𝟑𝟐𝟏. 𝟐 = 𝟏𝟕. 𝟗𝟐 Standard deviation 17.92
𝑵
𝒊%𝟏
Example. Compute the sample variance and standard
deviation of the following observations (ages in year):
10, 21, 30, 53, 56.
𝒏
Solution 𝟏 𝟏𝟎 + 𝟐𝟏 + 𝟑𝟎 + 𝟓𝟑 + 𝟓𝟔 𝟏𝟕𝟎
, = * 𝒙𝒊 =
𝒙 = = 𝟑𝟒
𝒏 𝟓 𝟓
𝒊%𝟏
𝒏
𝟏
𝒔𝟐 = ,
* 𝒙𝒊 − 𝒙 𝟐
𝒏−𝟏
𝒊%𝟏
10 − 34 ' + 21 − 34 '
+ 30 − 34 ' + 53 − 34 ' + 56 − 34 '
=
4
()*)
= = 𝟒𝟎𝟏. 𝟓 Mean 34
+
Variance 401.5
𝒔 = 𝟒𝟎𝟏. 𝟓 = 𝟐𝟎. 𝟎𝟒 Standard deviation 20.04
The Variance and standard deviation (Formula 2)

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


variance and standard deviation are given respectively
as:
𝒏
𝒙𝟐𝟏 𝟐
+ 𝒙𝟐 + ⋯ + 𝒙𝒏 𝟐 𝒙𝟐
− 𝒏, 𝟏
𝒔𝟐 = = * 𝒙𝟐𝒊 − 𝒏,
𝒙𝟐
𝒏−𝟏 𝒏−𝟏
𝒊%𝟏

𝒏
𝒙𝟐𝟏 𝟐
+ 𝒙𝟐 + ⋯ + 𝒙𝒏 𝟐 𝒙𝟐
− 𝒏, 𝟏
𝒔= = * 𝒙𝟐𝒊 − 𝒏,
𝒙𝟐
𝒏−𝟏 𝒏−𝟏
𝒊%𝟏
Example. Compute the sample variance and standard
deviation of the following observations (ages in year):
10, 21, 30, 53, 56. 𝒙𝒊 𝒙𝟐𝒊
10 100
Solution
21 441
30 900
𝟏𝟕𝟎 53 2809
,=
𝒙 = 𝟑𝟒
𝟓 56 3136
∑𝒏𝒊%𝟏 𝒙𝒊 =170 ∑𝒏𝒊%𝟏 𝒙𝟐𝒊 =7386
𝒏
𝟏 𝟐 𝟏 𝟏𝟔𝟎𝟔
𝒔𝟐 = * 𝒙𝒊 − 𝒏, 𝟐
𝒙 = 𝟕𝟑𝟖𝟔 − 𝟓 𝟑𝟒 𝟐 = = 𝟒𝟎𝟏. 𝟓
𝒏−𝟏 𝟒 𝟒
𝒊%𝟏
𝒔 = 𝟒𝟎𝟏. 𝟓 = 𝟐𝟎. 𝟎𝟒
The Var and std (Formula 1 & Formula 2)

Formula 1 Formula 2

𝑵 𝑵
𝟏 𝟏
# 𝒙𝒊 − 𝝁 𝟐
# 𝒙𝟐𝒊 − 𝑵𝝁𝟐
Variance 𝑵 𝑵
𝒊"𝟏 𝒊"𝟏

Population
𝑵 𝑵
𝟏 𝟏
# 𝒙𝒊 − 𝝁 𝟐 # 𝒙𝟐𝒊 − 𝑵𝝁𝟐
Standard deviation 𝑵
𝒊"𝟏
𝑵
𝒊"𝟏

𝒏 𝒏
𝟏 𝟏
(
# 𝒙𝒊 − 𝒙 𝟐
# 𝒙𝟐𝒊 − 𝒏(
𝒙𝟐
Variance 𝒏−𝟏
𝒊"𝟏
𝒏−𝟏
𝒊"𝟏

Sample 𝒏 𝒏
𝟏 𝟏
# 𝒙𝒊 − 𝒙
( 𝟐 # 𝒙𝟐𝒊 − 𝒏(
𝒙𝟐
Standard deviation 𝒏−𝟏
𝒊"𝟏
𝒏−𝟏
𝒊"𝟏
Coefficient of Variation
The coefficient of variation is a measure of dispersion that

describes the amount of variability relative to the mean.

Because the coefficient of variation is unitless, you can use it

instead of the standard deviation to compare the spread of

data sets that have different units or different means.


𝒔
𝑪𝑽 = ∗ 𝟏𝟎𝟎
%
𝒙
Example
A sample of two aptitude tests, one dealt with mechanical
aptitude, the other with aptitude for social work. The
result is as follows:

𝒙) =200, 𝑺 = 𝟑𝟎.
Mechanical mean (%

𝒙) =500, 𝑺 = 𝟒𝟎.
Social work mean (%

Calculate the coefficient of variation (CV), and

comment on your results.


Solution
𝒔
𝑪𝑽 = ∗ 𝟏𝟎𝟎
%
𝒙

𝟑𝟎
For Mechanical: 𝑪. 𝑽. = ∗ 𝟏𝟎𝟎 = 𝟏𝟓%
𝟐𝟎𝟎

𝟒𝟎
For Social work: 𝑪. 𝑽. = 𝟓𝟎𝟎
∗ 𝟏𝟎𝟎 = 𝟖%

It’s clearly obvious that there’s a larger relative dispersion

in mechanical aptitude compared with that of social work.


Example

two sampled set of data are as follows:

Set A: 5 , 6 , 8 , 10 , 12 , 14 , 15

Set B: 1 , 2 , 5 , 10 , 15 , 18 , 19

Calculate the coefficient of variation (CV), and

comment on your results.


Solution
- 𝑨)𝟐 - 𝑩)𝟐 ∑𝒙 𝟕𝟎
set A set B (𝑿 − 𝑿 (𝑿 − 𝑿 ,𝑨 =
𝒙 = = 𝟏𝟎.
𝒏 𝟕
5 1 25 81
6 2 16 64
8 5 4 25 ∑𝒙 𝟕𝟎
,𝑩 =
𝒙 = = 𝟏𝟎.
10 10 0 0 𝒏 𝟕
12 15 4 25
> =.BC
14 18 16 64 𝐶𝑉2 = @̅- = (*
= 0.387
15 19 25 81 -

% 𝑨)𝟐
!(𝑿 − 𝑿 % 𝑩)
𝟐
𝑆: 7.5
70 70 !(𝑿 − 𝑿 𝐶𝑉D = = = 0.0.75
= 𝟗𝟎
𝑥̅: 10
= 𝟑𝟒𝟎

6 𝑨 )𝟐
∑(𝑿5𝑿 9* We can say that although
𝑠2 = = = 15 = 3.87
85( ) the two sets have the same
6𝑩;
∑<𝑿5𝑿
,
=+*
mean, the variations in set
𝑠: = 85(
= )
= 56.7 = 7.5 A is greater than that in
set B.

You might also like