MEASURES OF

VARIABILIT Y
MEA SU RE S OF VAR IABILIT Y/DISPE RSION

• Dispersion or variation in a data set is the amount of difference

between data values.
• In a data set with little variation, almost all data values would be
close to one another.
• In a data set with a great deal of variation, the data values would
be spread widely.
RANGE
• the difference between the highest and lowest values in a set of
data
VARIANCE

• The variance of a set of values is a measure of variation equal to

the square of the standard deviation.

• The value of the variance can increase dramatically with the

inclusion of outliers.
STANDARD DEVIATION

• It is the most commonly used measure of variation.

• A measure of the “average” distance of the data values from the mean.
• To compute the standard deviation, we simply get the square root of
the variance.
• The value of the standard deviation is never negative.
• The units of the standard deviation is the same as the unit of the
original data values
NO TATIONS

for sample standard deviation

for population standard deviation
2 is sample variance

2 is population variance
 VARIA NCE

where
 𝑥 represents the observations
 𝜇 the population mean
 𝑁 the population size
Population variance

where
 𝑥 represents the observations

 𝑥̅ the sample mean

 𝑛 the sample size

Sample variance
 S TA NDARD D E VIATION

𝑵 𝟐 where
𝐢 𝟏 𝒊
 𝑥 represents the observations
 𝜇 the population mean
Population standard  𝑁 the population size

deviation

where
𝒏 𝟐  𝑥 represents the observations
𝐢 𝟏 𝒊  𝑥̅ the sample mean
Sample standard  𝑛 the sample size
deviation
S TA NDARD D E VIATION

where
 𝑥 represents the observations
 𝜇 the population mean
Population std  𝑁 the population size

deviation
where
 𝑥 represents the

observations
Sample std  𝑥̅ the sample mean

 𝑛 the sample size

deviation
EX AMPL E
Eight students were asked on how much they gained weight in three months of staying
at home in kilograms (kg). Below are the data. Find the standard deviation and
variance.

Steps Actual process and result

1. Determine the
mean of the
observations.
EX AMPL E
Eight students were asked on how much they gained weight in three months of staying at home in
kilograms (kg). Below are the data. Find the standard deviation and variance.
Solution

(𝒙𝒊 − 𝒙) (𝒙𝒊 − 𝒙) 𝟐 Steps

0.1875 0.035
-0.8125
2. For each observation, calculate
0.660
-0.3125 0.098
the deviation or difference
-0.8125 0.660 between each observation and the
0.1875 0.035 mean.
1.1875 1.41
0.1875 0.035 3. Calculate the square of each of
0.1875 0.035 the deviations and find the sum of
these squared deviations.
EX AMPL E
Eight students were asked on how much they gained weight in three months of staying at home in
kilograms (kg). Below are the data. Find the standard deviation and variance.
Solution

(𝒙𝒊 − 𝒙) (𝒙𝒊 − 𝒙) 𝟐 Steps

0.1875 0.035
-0.8125 0.660 4. Find the square root of the
-0.3125 0.098 variance to get the standard
-0.8125 0.660
0.1875
deviation
0.035
1.1875 1.41
0.1875 0.035
0.1875 0.035
 Key Notes to Remember:

1) The purpose of central tendency is to determine the single value that identifies
the center of the distribution and best represents the entire set of scores.
2) The mean is the arithmetic average. In most situations with numerical data from
an interval or a ratio scale, the mean is the preferred measure of central tendency.
3) Changing any score in the distribution causes the mean to be changed.
4) The median is the preferred measure of central tendency when a distribution has
a few extreme scores that displace the value of the mean. The median is the
preferred measure of central tendency for data from an ordinal scale.
 Key Notes to Remember:
5) The mode is the most frequently occurring score in a distribution. It is easily
located by finding the peak in a frequency distribution graph. For data measured
on a nominal scale, the mode is the appropriate measure of central tendency.
6) Measures of variability or dispersion can never be negative.
7) If all values in a set of data are equal, then there is no dispersion.
8) If values of a set of data are not equal, but very close to each other, then there is a
small dispersion.
9) While a larger measure of variability may imply the existence of outliers or extreme
observations.
EX AMPL E
Consider the following grades in five quizzes in Statistics of the two students. Who
performed better?
Student A: 80, 70, 98, 75, 77
Student B: 60, 95, 85, 82, 78

Steps 2-3:
Key Notes to Remember:
SHAPES OF DATA
DISTRIBUTIONS
SYMMETRIC
• the data distribution is approximately the same
shape on either side of a central dividing line.

• The mean and median (and mode if unimodal) are

equal in a symmetric distribution.

• A symmetrical data is bell-shaped and can be called

normal.
LEFT-SKEWED

• ‘tail extends to the left’

• few data values that are much lower than the

majority of values in the set

• the mean is less than the median (and mode) in a

left- skewed distribution.
RIGHT-SKEWED

• ‘tail extends to the right’

• few data values that are much higher than the

majority of values in the set

• the mean is greater than the median (and mode) in

a right- skewed distribution.
UNIFORM

• All data values are equally represented

MEASURES OF RELATIVE
POSITION
MEA SU RE S OF RE LATIVE POSITION

• It tells us the location of an observation relative to the other values when the
data are in ranked order

• It is a measure whether a value is about average, or whether its unusually high

or low

• It is used for quantitative data that falls on some numerical scale

• It can be also applied to ordinal variables

PE RCEN TILE S

• measures of position that divide the data set into one hundred equal parts
• can be found for any percent from 1 to 99 and is denoted as 𝑃𝑟 where the subscript 𝑟 is
the percentile rank

This means:
P10 is the tenth percentile and is equal or larger than 10% of the data
EX AMPL E
Using the data below, find 25, 60 and the percentile rank of 4.
2 6 3 4 2 1 2 0 1 3 6 3
Solution
Steps Actual process and result

1. Arrange the numbers in ascending order. 0 1 1 222 333 4 6 6

2. Find 𝐶 = 𝑛𝑟, where n is the number of 𝐶 = 𝑛𝑟 = 12(0.25) = 3

observations and 𝑟 is the percentile rank which, in
this example, is 25% = 0.25.

3. Since 𝐶 is a whole number, get the 𝑃25 = 1.5

average of the 3rd and the 4th number in the
ordered list. This will be 𝑃25.

This means that 25% of the observations are less than or equal
to 1.5.
EX AMPL E
Using the data below, find 25, 60 and the percentile rank of 4.
2 6 3 4 2 1 2 0 1 3 6 3
Solution
Steps Actual process and result

1. Arrange the numbers in ascending order. 0 1 1 222 333 4 6 6

2. Find 𝐶 = 𝑛𝑟, where n is the number of 𝐶 = 𝑛𝑟 = 12(0.60) = 7.2

observations and 𝑟 is the percentile rank
which, in this example, is 60% = 0.60

3. Since 𝐶 is not a whole number, round up to =3

8. Locate the 8th observation. This will be 𝑃60 .

We conclude that 60% of the observations are less than or equal

to 3
EX AMPL E
Using the data below, find 25, 60 and the percentile rank of 4.
2 6 3 4 2 1 2 0 1 3 6 3
Solution
Steps Actual process and result

1. Arrange the numbers in ascending order. 0 1 1 222 333 4 6 6 r

2. To determine r: 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑣𝑎𝑙𝑢𝑒𝑠 𝑏𝑒𝑙𝑜𝑤 𝑡h𝑒 𝑔𝑖𝑣𝑒𝑛 𝑣𝑎𝑙𝑢𝑒−0.5

𝑟 =( )(100%)
𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑣𝑎𝑙𝑢𝑒𝑠

10−0.5
=( ) 100%
12
DE CILES

• measures of position that divide the data set into ten equal parts
• can be found for 1 through 9

Example:

is the second decile and is the value that is larger than two-tenths of the
other values.
EX AMPL E
Using the data below, find D6.
2 6 3 4 2 1 2 0 1 3 6 3
Solution
Steps Actual process and result

1. Arrange the numbers in ascending order. 0 1 1 222 333 4 6 6

2. Find 𝐶 = 𝑛𝑟, where n is the number of 𝐶 = 𝑛𝑟 = 12(0.6) = 7.2

observations and 𝑟 is the decile rank which, in this
example, is 6 or 60%=0.6.

3. Since 𝐶 is not a whole number, round up to 8. D6 = 3

Locate the 8th observation. This will be D6.

This means that the 6th decile is 3 and it is greater than or

equal to six-tenths of other values.
QUARTILES

• measures of position that divide the data set into four equal parts

Example:

is the first quartile and is the value that is larger than one-fourth (or 25%)
of the observations in the distribution.
EX AMPL E
Using the data below, find Q1.
2 6 3 4 2 1 2 0 1 3 6 3
Solution
Steps Actual process and result

1. Arrange the numbers in ascending order. 0 1 1 222 333 4 6 6

2. Find 𝐶 = 𝑛𝑟, where n is the number of 𝐶 = 𝑛𝑟 = 12(0.25) = 3

observations and 𝑟 is the quartile rank which, in
this example, is 1 or (1/4)=0.25.

3. Since 𝐶 is a whole number, get the Q1 = 1.5

average of the 3rd and the 4th number in the
ordered list. This will be Q1.

This means that the 1st quartile is 1.5 and it is greater than or
equal to one-fourth of the other values.
S TA NDARD SCORE OR Z-SCOR E

 Measures the distance between an observation and the mean

 the number of standard deviations that the value lies above or below the mean

• If the z-score is positive, the score is above the mean.

• If the z-score is 0, the score is the same as the mean.
• If the z-score is negative, the score is below the mean.
• A data value is considered to be unusual if it is more than two standard deviations from the
mean.
 EX AMPL E
An IQ test has a mean of 105 and a standard deviation of 20. Find the corresponding z-scores for each
IQ:
a) 88
b) 109
c) 122
Solution
a) 88
88 − 105 The IQ score of 88 is below the mean
𝒛= = −0.85
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑
20
b) 109
109 −105
𝒛= = 0.20 The IQ score of 109 is above the mean
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑
20
b) 122
122 −105 The IQ score of 122 is above the mean
𝒛= = 0.85
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑
20
EX AMPL E
Which of the following exam grades has a better relative position?
A grade of 43 on an Algebra test with mean score of 40 and standard deviation of 3,
or a grade of 75 on Geometry with mean score of 72 and standard deviation of 5?
Solution

For a grade of 43: 𝑥̅ = 40 𝑠=3 For a grade of 75: 𝑥̅ = 72 𝑠=5

43 − 40 75 − 72
𝒛= =1 𝒛= = 0.6
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑
3 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑
5

Since the z-score for the Algebra test is greater than the Geometry test, the
position of 43 score on Algebra test is higher than the position of 75 score on
Geometry test.