Quantitative Reasoning

Ms. Zunaira Khurrum

Statistics Department

(Only the main points are covered on the slides. Please ensure the
use of reference books also)
 Measures of Dispersion/Variability

Measures of dispersion quantify the spread or

variability of data points within a dataset. Consider
the following distributions and their means:
• 10,10,10 𝑋ത = 10 (Zero dispersion)
• 9,10,11 𝑋ത = 10 (Low dispersion)
• 0,10,20 𝑋ത = 10 (High dispersion)
Types of Measures of Dispersion

Measures of
Dispersion

Absolute Relative
Absolute Measure of Dispersion
It measures the amount of dispersion in a set of observations in the same
units as the units of original observations. The common absolute measures
are:
Absolute
Measure

Standard
Range Variance
Deviation
Relative Measure of Dispersion
It measures the amount of dispersion in a set of observations free of units
in which the original data is measured and is expressed in the form of
ratio, coefficient or percentage. The common relative measures are:

Relative Measure

Coefficient of Standard
Coefficient of Range Coefficient of variation
Deviation
 Range Coefficient of Range
The difference between the largest The Coefficient of Range (CR) is a
and smallest observations in a data set relative measure of dispersion that
is known as the range. calculates the spread of data relative to
𝑹 = 𝑿𝒎 − 𝑿𝒐 its range.
𝑿𝒎−𝑿𝒐
CR =
For example, if the given data set is 𝑿𝒎+𝑿𝒐

{2,5,8,10,3}, then the range will be For example, if the given data set is
10 – 2 = 8. {2,5,8,10,3}, then Coefficient of Range
will be
𝟏𝟎−𝟐 𝟖
CR = = = 𝟎. 𝟔𝟔
𝟏𝟎+𝟐 𝟏𝟐
 Quartile Deviation Coefficient of Quartile Deviation

The difference between the lower and The Coefficient of Quartile Deviation
upper quartiles is known as the (CQD) is a relative measure of
Quartile range/Interquartile Range. dispersion that calculates the spread of
𝐐. 𝑹 = 𝑸𝟑 − 𝑸𝟏 data using the interquartile range (IQR).
𝑸𝟑−𝑸𝟏
CQD =
Semi Interquartile range (S.I.Q.R) or 𝑸𝟑+𝑸𝟏
Quartile Deviation (Q.D) is the half
of the InterQuartile Range.
𝑸𝟑−𝑸𝟏
Q.D =
𝟐
 Standard Deviation Ungrouped Example
Find the standard deviation S for the following set of numbers: 12,6,7,3,15,10,18,5
∑𝑿 12+6+7+3+15+10+18+5
ഥ
The mean 𝑿 = = =9.5 and
𝒏 8

∑(𝑿−𝑿)𝟐 X ഥ
X-𝑿 ഥ )2
(X-𝑿
𝑺=
𝒏 12 12-9.5=2.5 2.52=6.25
𝟏𝟗𝟎 6 -3.5 12.25
= = 𝟒. 𝟖𝟕
𝟖 7 -2.5 6.25
3 -6.5 45.25
15 5.5 30.25
10 0.5 0.25
18 8.5 72.25
5 -4.5 20.25
190
 variance
Variance is a measure of dispersion that quantifies the average squared
difference between individual data points and the mean. A high value of
variance shows the values are not close to the mean and they spread over a
wider range. It is denoted by S2 for sample and 𝝈𝟐 for population.
∑(𝑿−𝑿)𝟐 ∑(𝑿−𝝁)𝟐
𝑺𝟐 = (Ungrouped) 𝝈𝟐 =
𝒏 𝑵

In the previous examples, taking square of standard deviation will give you
variance.
In example of ungrouped case, sd=4.87, so variance=(4.87)2=23.7169
 Coefficient of standard deviation Coefficient of Variation

The Coefficient of Standard Deviation The Coefficient of variation, is a measure of

(CSD), also known as the Relative Standard dispersion that expresses the standard
Deviation (RSD), is a measure of dispersion deviation as a percentage
that expresses the standard deviation as a 𝒔𝒕𝒂𝒏𝒅𝒂𝒓𝒅 𝒅𝒆𝒗𝒊𝒂𝒕𝒊𝒐𝒏
Coefficient of variation = ∗ 𝟏𝟎𝟎
ratio 𝒎𝒆𝒂𝒏
𝑺𝒅
𝒔𝒕𝒂𝒏𝒅𝒂𝒓𝒅 𝒅𝒆𝒗𝒊𝒂𝒕𝒊𝒐𝒏 =
CSD = 𝑿ഥ *100
𝒎𝒆𝒂𝒏
𝟒.𝟖𝟕
𝑺𝒅 For ungrouped example, CV= 𝟗.𝟓 *100=51
= ഥ
𝑿
𝟐.𝟗𝟐
𝟒.𝟖𝟕 For grouped example, CV= 𝟔𝟕.𝟒𝟓*100=4
For ungrouped example, CSD= 𝟗.𝟓 =0.51
𝟐.𝟗𝟐
For grouped example, CSD= 𝟔𝟕.𝟒𝟓=0.04
The data with higher CV shows more
The data with higher CSD shows more variation in the data
variation in the data
 Symmetry and Skewness

A distribution is symmetric when the distribution on either side of the mean is a mirror
image of the other. In a symmetrical distribution, mean = median = mode. If a distribution is
non-symmetrical, it is said to be skewed. Skewness can be negative or positive.
 Symmetric Distribution
A symmetric distribution is a probability distribution where the left and right sides of the distribution
are mirror images of each other, around the central value (mean, median, and mode).
Characteristics of Symmetric Distributions:
1. Mean = Median = Mode
2. Left and right tails are identical
3. Skewness = 0
 Positively skewed Distribution
A positively skewed distribution is a probability distribution where the majority of the data points
are concentrated on the left side of the distribution, with a longer tail on the right side. This means
that the most extreme values are on the right side. Characteristics of Positively Skewed
Distributions:
1. Mean > Median > Mode
2. Right tail is longer than left tail
3. Skewness > 0
4. More extreme values on the right side.
 Negatively skewed Distribution
A negatively skewed distribution is a probability distribution where the majority of the data points
are concentrated on the right side of the distribution, with a longer tail on the left side.
Characteristics of Negatively Skewed Distributions:
1. Mean < Median < Mode
2. Left tail is longer than right tail
3. Skewness < 0
4. More extreme values on the left side.
 Formulae

Range 𝑹 = 𝑿𝒎 − 𝑿𝒐
Coefficient of Range 𝑿 −𝑿𝒐
CR = 𝑿𝒎+𝑿𝒐
𝒎

∑(𝑿−𝑿)𝟐 ∑(𝑿−𝝁)𝟐
Standard Deviation 𝑺= or 𝝈 =
𝒏 𝑵

Coefficient of Standard 𝒔𝒕𝒂𝒏𝒅𝒂𝒓𝒅 𝒅𝒆𝒗𝒊𝒂𝒕𝒊𝒐𝒏 𝑺𝒅

CSD = = 𝑿ഥ
Deviation 𝒎𝒆𝒂𝒏

∑(𝑿−𝑿)𝟐 ∑(𝑿−𝝁)𝟐
Variance 𝑺𝟐 = or 𝝈𝟐 =
𝒏 𝑵

𝒔𝒕𝒂𝒏𝒅𝒂𝒓𝒅 𝒅𝒆𝒗𝒊𝒂𝒕𝒊𝒐𝒏 𝑺𝒅
Coefficient of variation CV= ∗ 𝟏𝟎𝟎= ഥ *100
𝒎𝒆𝒂𝒏 𝑿
Any Questions