0% found this document useful (0 votes)
382 views24 pages

MODULE7 Measures of Variability

This document discusses measures of variability or dispersion used to describe how data is spread out. There are four main measures discussed: range, standard deviation, variance, and coefficient of variation. The document provides examples to calculate and interpret these measures for different data sets to determine which has more or less variability. It explains that standard deviation is the most reliable measure of variability.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
382 views24 pages

MODULE7 Measures of Variability

This document discusses measures of variability or dispersion used to describe how data is spread out. There are four main measures discussed: range, standard deviation, variance, and coefficient of variation. The document provides examples to calculate and interpret these measures for different data sets to determine which has more or less variability. It explains that standard deviation is the most reliable measure of variability.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 24

Module 7

Measures of Variability or
Dispersion:
• It is a single number that describes how the data are
scattered or how much they are bunched. It is also
called the measure of dispersion or measure of spread
• the average distance of each observation from
the center of the distribution
• measure the homogeneity or heterogeneity of
a particular group/data set
Measures of Variability
Consider the following sets of grades in Statistics of two
groups of 5 students each:

Male Group Female Group

Jon: 100 Ann: 84


Ron: 65 Ria: 86
Dan: 75 Let: 85
Tom: 85 Bel: 82
Bob: 95 Nel: 83

Mean: 84 Mean: 84
Measures of Variability
How far apart are their grades from one another?
Ron Dan Tom Bob Jon
Males

65 70 75 80 85 90 95 100

Females

65 70 75 80 85 90 95 100
This shows that the grades of males are far apart from each
other as compared with that of the females. Thus, male
grades are more variable than that of the females.
Measures of Variability
A small measure of variability would indicate that the data are:
A big measure of variability would indicate that the data are:

1. Clustered closely around the mean


Far away from the mean.
2. More homogeneous
Heterogeneous
3. Less variable
More variable.
4. More consistent
Less consistent.
5. More uniformly distributed
Less uniformly distributed.
Measures of Variability
There are four measures of variability which we are going to study:
1. Range (R): The difference between the highest
and the lowest value in a set of data.
Formula: R = Hv - Lv
2. Standard Deviation: ( for population & s for sample): The
The most reliable
square measure
root of the sum of of
thevariability is deviation
of the squared the standard deviation!
from the
mean.
3. Variance: (2 for population & s2 for sample): The square
of standard deviation.

4. Coefficient of Variation (cv): use to compare the variability of 2


or more sets of data having different units.
sx
cv  , where s x = the standard deviation
x x = the mean
Disadvantage of Range

• For a very large sample, it is an unstable descriptive measure of


dispersion
• Since only two values are used in the computation, the range is an
unreliable measure of dispersion
• The range of two sets of data composed of different numbers of
samples are not directly comparable
Measures of Variability SYMBOLS
in Calculator
x n or  n or  is the population s tan dard deviation
x n 1 or s x or s is the sample s tan dard deviation

1] Only standard deviation can be obtained using calculator.


2] To get the range: Highest value – Lowest value in a data set.
3] To get the variance: Just get the square of the standard deviation;
To get the standard deviation: Just get the square root of the variance.
4] The coefficient of variation (c.v.) is used only if we are comparing different
sets of data; Example: height & weight, age & grades, etc…
Find the range, standard deviation, & variance &
Then interpret the results:

Male Group Female Group

Jon: 100 Ann: 84


Ron: 65 Ria: 86
Dan: 75 Let: 85
Tom: 85 Bel: 82
Bob: 95 Nel: 83

Mean: 84 Mean: 84
Find the range, standard deviation,
& variance. Interpret the results:
Male Group Female Group
100, 65, 75, 85, & 95 84, 86, 85, 82, 83
1] Range: Hv – Lv: 100 – 65 = 35 1] Range: Hv – Lv: 86 – 82 = 4
2] Standard deviation:
Concl: range 86 – 82 = 4
12.81
(  ) or x n 

-Male grades are xmore
  
x
2
variable bec. of a bigger measure
population population
standard
std.
of variability.
dev. 1.41
Male grades
N
are more
std. dev. spread because deviation
of ….
-FemaleMalesgrades are less variable
are heterogeneous bec. itof
because has
….a smaller
sample std. dev. 1.58
 
x  x 14.32
2
measure of variability.
population variance 1.99
( s ) or x 
Standard
x n 1deviation
sample
n 1 std. dev. Sample variance
2.50
Female the
3] Variance: grades are of
square less spread
std. dev. or more compact because of ….
Females2 are homogeneous bec of….
population
  (12.81)  164.10
2

s 2  (14.32) 2  205.06 sample


Find the range, standard deviation,
& variance. Interpret the results:
Example 1. The following are the monthly incomes of
10 sample families living in Block 21 of XYZ Subdivision. Find
the range, variance & standard deviation. Interpret results (use
sample std. dev.)
P52,000.00 P28,000.00 Interpretation:
P35,000.00 P40,000.00 On the average, the
P50,000.00 P45,000.00 monthly
income of families living
P33,000.00 P39,000.00 in B21 of XYZ subd.
P41,000.00 P48,000.00 deviates by P7,752.42
Range  52,000  28,000  P 24,000 from the mean of
s x  P 7,752.42 P41,100.
s 2 x  P 60,100,015.86
Suppose the data sets below are the normal daily high
temperatures, measured In degrees Celcius, for 3 different
cities during one week of winter vacation. Complete
the table below & answer the questions which follow:

City 1 1, 1, 4, 6, 9, 13, 15
City 2 2, 5, 6, 6, 7, 7, 16 COPY THE TABLE!
City 3 2, 2, 2, 6, 10, 11, 16
Mean Median Mode Range SD
Variance
City 1 ________ ________ ________ _________ ________
_______
City 2 ________ ________ ________ _________ ________
1] Which City has a more variable temperature? Justify
_______
City 3 your answer.
________ ________ ________ _________ ________
_______2] Which City has a more uniform temperature? Justify
your answer.
3] Which City has the warmest temperature? Justify
your answer.
Suppose the data sets below are the normal daily high
COPY THE TABLE!
temperatures, measured In degrees Celcius, for 3 different
cities during one week of winter vacation. Complete
the table below & answer the questions which follow:

City 1
Mean 1, 1,
Median 4, Mode
6, 9, 13, 15
Range SD
Variance
City 2 2, 5, 6,1 6, 7, 7, 16 5.57 31.02

2,2 6, 10,_______ ______ 18.66


City 1 City
________ ________ 6&7 4.32
3 2, 2, ________ 11, 16 5.51 30.36
_____
City1]2Which
________
City has________ ________
a more variable _________
temperature? ________
Justify your answer.
_______City 1 bec. It has the biggest standard deviation.
City2]3Which
________
City has________ ________
a more uniform _________
temperature? ________
Justify your answer.
_______City 2 bec. It has the smallest standard deviation.
3] Which City has the warmest temperature? Justify your answer.
All cities have the same temperature because they have the same mean.
Find the range, standard deviation,
& variance. Interpret the results:

Example 2. Table 5.1


Test Scores Got by Two Students
Test 1 2 3 4 5 6 7 8 9 10
Student A 12 6 13 2 5 0 9 6 10 7
Student B 8 10 9 12 5 1 4 7 9 3

x s2 x n 1
Measurement x
Student A 70 7.0 17.14 4.14
Student B 68 6.8 11.96 3.46
Student A performed better bec. s/he has a
1] Who mean
higher performed
score better? Justify!
of 7.0 as against 6.8 of B.
2] who has
Student a more
B has consistent
a more set of
consistent setscores? Justify!
of scores bec. s/he has a
smaller standard deviation of 3.46 as against 4.14 of B.
Def: It is used to compare the variability of two or more sets
of data when they are expressed in different units of measurement.
Concl: Therefore Player C performed
s x ( s tanconsistently on )
dard deviation
cv(coefficien
making t of var
points rather thaniation )  assists because points has a
on giving
lower c.v. of 0.2373 as against c.v. of assistsx(which
mean)is 0.5017.
Table 5.2: Number of Assists and the Number of Points Made by Player C
in 10 Randomly-Selected Games in the 2002 PBA Season Measurement mean sd c.v.

Game 1 2 3 4 5 6 7 8 9 10 Assists 5.9 2.96 2.96/5.9


x x n 1 0.5017
Assists 7 10 9 1 5 3 4 7 9 4 5.9 2.96 Points 23.6 5.60 5.60/23.6
Points 25 25 30 22 23 22 16 35 20 18 23.6 5.60 0.2373

In which area (assist/point) does Player C perform consistently?


Since these are 2 different areas, we cannot refer to std. dev. We need
to find the coefficient of variation (cv,)
The following are the scores of two groups of students who took
the make-up test in Arithmetic. Copy & Complete the table
below and then answer the questions that follow. All
measurements in 2-decimal palaces:
Group A Group B Measurement Group A Group B
62 75 Mean 60.00 54.20
58 42
65 35 Range 29.00 40.00
43 53 Std. dev
10.79 16.51
72 66 (sample)

1] Which
Groupgroup performed
A because better?
it has Justify
higher yourscore.
mean answer.
2] Which group shows more variability in scores? Justify
Group
your B because it has higher standard deviation.
answer.
X
14 19 24 29 34 39 44
The Normal Distribution
Mean=Median
(Not Skewed/Mesokurtic)
Normal Distribution No. of f
Correct
Answers
1 1
5
4.5 2 2
4
3.5
3 3 4
2.5
2 4 5
1.5
1 5 4
0.5
0
1 2 3 4 5 6 7 6 2

7 1

N  19
Mean = Median = 4.0
Measures of Skewness
Skewness (SK): refers to the degree of symmetry
or asymmetry of a distribution.

SK 
 xi  x 
3

 N  1 s 3

If SK = 0, the distribution is normal relative to the center


If SK is almost 0 (0.0something), the distribution is
almost normal.
If SK < 0, the distribution is skewed to the left
If SK > 0, the distribution is skewed to the right
No. of f
Skewed to the Left Distribution Correct
Answers
1 0
7
2 0
6
3 1
5
4 4 2
3 5 5
2
6 7
1
7 4
0
1 2 3 4 5 6 7
N  19

Mean(5.58) < Median(6)


Skewed to the Right Distribution No. of f
Correct
7 Answers
1 4
6
2 7
5
3 5
4
3 4 2

2 5 1
1 6 0
0 7 0

1 2 3 4 5 6 7 N  19

Mean(2.42) > Median(2.0)


Measures of Kurtosis
Kurtosis (Ku): refers to the peakedness or
flatness of a distribution.
ku 
 xi  x 
4
3
 N  1 s 4

If Ku = 0, the distribution is mesokurtic or normal in relation to height


If Ku is almost 0 (0.0something), the distribution is almost normal.
If Ku < 0, the distribution is platykurtic or shorter than normal
If Ku > 0, the distribution is leptokurtic or taller than normal
Distribution with different Coefficient of Kurtosis

Leptokurtic (Ku > 0 or +)


(Taller than normal)

Mesokurtic (Ku = 0)
(Normal)
Platykurtic (Ku < 0 or -)
(Shorter than normal)
Give the shape (symmetry) of the distribution of the result of:

1. A test given to a class which is composed mostly


of dean’s listers. Skewed to the left [SK is “-”]

2. A Grade V spelling test administered to 4th year


high school students. Skewed to the left [SK is “-”]

3. A second year high school math test administered to Grade 2


students. Skewed to the right [SK is “+”]

4. A regular quiz given to an ordinary group of students.


Normal “SK=0”

You might also like