Professional Documents
Culture Documents
Department of Mathematics
College of Science and Engineering
Ateneo de Naga University
Learning Objectives
Definition of Terms
Measures of Location
The value within the range of data which describes its location or
position relative to the entire set of data.
Numerical Descriptive Measures
Measures of Location
Definition of Terms
Measures of Location
The value within the range of data which describes its location or
position relative to the entire set of data.
Definition of Terms
Mean (µ or x)
The sum of the observations divided by the number of totaled
observations
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Definition of Terms
Mean (µ or x)
The sum of the observations divided by the number of totaled
observations
Definition of Terms
Mean (µ or x)
The sum of the observations divided by the number of totaled
observations
Mode(mo or Mo)
Observations which occur most frequently in the data set
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
I Value is determined by every case in the distribution
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
I Value is determined by every case in the distribution
I Affected by extreme values
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
I Value is determined by every case in the distribution
I Affected by extreme values
When to use
I Variables are in at least interval scale
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
I Value is determined by every case in the distribution
I Affected by extreme values
When to use
I Variables are in at least interval scale
I Value of each score is desired
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The Mean (µ or x)
Measures of Central Tendency
Characteristics
I Interval statistic
I Calculated average
I Value is determined by every case in the distribution
I Affected by extreme values
When to use
I Variables are in at least interval scale
I Value of each score is desired
I Values are considerably concentrated or closed to each other
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
I Rank or position average
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
I Rank or position average
I NOT affected by extreme values
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
I Rank or position average
I NOT affected by extreme values
When to use
I Ordinal interpretation is needed
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
I Rank or position average
I NOT affected by extreme values
When to use
I Ordinal interpretation is needed
I Middle score is desired
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Ordinal statistic
I Rank or position average
I NOT affected by extreme values
When to use
I Ordinal interpretation is needed
I Middle score is desired
I We want to avoid influence of extreme values
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
I Most popular score
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
I Most popular score
I NOT affected by extreme values
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
I Most popular score
I NOT affected by extreme values
I Represents the majority
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
I Most popular score
I NOT affected by extreme values
I Represents the majority
When to use
I Nominal interpretation is needed
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Characteristics
I Nominal statistic
I Inspection average
I NOT unique
I Most popular score
I NOT affected by extreme values
I Represents the majority
When to use
I Nominal interpretation is needed
I Quick approximation of central tendency is required
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Populaton Mode Mo
. . . the data point with the most number of frequency is the mode.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Sample Mode mo
. . . the data point with the most number of frequency is the mode.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Drills
Example 1
Find the mean, median, and mode of the following data set.
Drills
Example 1
Find the mean, median, and mode of the following data set.
Example 2
Find the mean, median, and mode of the following data set.
Try this!
The following entrance test scores (100 is the perfect score) are
obtained by a sample of 20 freshmen in Oragon College. Find the
mean, median, and mode of the distribution, and give
corresponding interpretations.
43 55 66 70 72
78 85 89 93 98
48 59 67 70 73
78 86 90 94 98
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Population Mode Mo
FM o − Fb
M o = LT CBM o + c0 or M o = 3M dn − 2µ
2FM o − Fb − Fa
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Sample Mode mo
fmo − fb
mo = LT CBmo + c0
2fmo − fb − fa
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the middle class, or the class that
contains the (N/2)th value of the array.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the middle class, or the class that
contains the (N/2)th value of the array.
" #
30
2 − 13
M dn = 28.5 + 7
10
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the middle class, or the class that
contains the (N/2)th value of the array.
" #
30
2 − 13
M dn = 28.5 + 7 = 29.9
10
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the modal class, or the class that has
the highest frequency.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the modal class, or the class that has
the highest frequency.
10 − 3
M 0 = 28.5 + 7
2(10) − 3 − 7
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
The row (colored yellow) is the modal class, or the class that has
the highest frequency.
10 − 3
M 0 = 28.5 + 7 = 33.4
2(10) − 3 − 7
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Interpretations
Mean
µ =27.8 means the the average score in the test is 27.8
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Interpretations
Mean
µ =27.8 means the the average score in the test is 27.8
Median
Mdn = 29.9 means half the students got a score below or equal to
29.9 and the other half obtained a score higher than or equal to
29.9.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Interpretations
Mean
µ =27.8 means the the average score in the test is 27.8
Median
Mdn = 29.9 means half the students got a score below or equal to
29.9 and the other half obtained a score higher than or equal to
29.9.
Mode
Mo= 33.4 means that 10 out of 30 students got a modal score of
33.4.
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Exercise
R = 41, k ≈ 7, and c0 ≈ 6
Class LL UL Freq. LTCB UTCB CM RF <CF >CF
9 to 14 9 14 3 8.5 14.5 11.5 6% 3 50
15 to 20 15 20 12 14.5 20.5 17.5 24% 15 47
21 to 26 21 26 9 20.5 26.5 23.5 18% 24 35
27 to 32 27 32 9 26.5 32.5 29.5 18% 33 26
33 to 38 33 38 7 32.5 38.5 35.5 14% 40 17
39 to 44 39 44 3 38.5 44.5 41.5 6% 43 10
45 to 50 45 50 7 44.5 50.5 47.5 14% 50 7
Numerical Descriptive Measures
Measures of Location
Measures of Central Tendency
Assignment
Midrange
The midrange (MR) is the sum of the lowest and highest values
in the data set divided by 2.
Numerical Descriptive Measures
Midrange and Weighted Mean
Midrange
The midrange (MR) is the sum of the lowest and highest values
in the data set divided by 2.
It is a rough estimate of the middle and can be affected by one
extremely high or low value.
Numerical Descriptive Measures
Midrange and Weighted Mean
Midrange
The midrange (MR) is the sum of the lowest and highest values
in the data set divided by 2.
It is a rough estimate of the middle and can be affected by one
extremely high or low value.
Formula for the Midrange
LV + HV
MR =
2
Numerical Descriptive Measures
Midrange and Weighted Mean
Midrange
The midrange (MR) is the sum of the lowest and highest values
in the data set divided by 2.
It is a rough estimate of the middle and can be affected by one
extremely high or low value.
Formula for the Midrange
LV + HV
MR =
2
Example
Find the midrange of the data set below.
Weighted Mean
Weighted Mean
Weighted Mean
Pn
i=1 wi Xi w1 X1 + w2 X2 + w3 X3 + . . . + wn Xn
X= P n =
i=1 wi w1 + w2 + w3 + . . . + wn
Example
The Ateneo de Naga University uses the 2005 Revised College
Grading System for old students. Below is a table of the numerical
rating, the letter grade, and the point value of the corresponding
grades.
NG LG PV Description
96 to 100 A 4.0 Excellent Academic Performance
90 to 95 B+ 3.5 Very Good Academic Performance
86 to 90 B 3.0 Good Academic Performance
81 to 85 C+ 2.5 Satisfactory Academic Performance
76 to 80 C 2.0 Satisfactory Academic Performance
75 D 1.0 Poor Academic Performance
<75 F 0.0 Unacceptable Academic Performance
Numerical Descriptive Measures
Midrange and Weighted Mean
Example
The Quality Point Index (QPI) is used to measure a student’s academic
performance. To determine the QPI, we use the formula for the weighted
mean. The weights w are the credit units of the subject and the values X are
point values of each grade.
Numerical Descriptive Measures
Midrange and Weighted Mean
Example
The Quality Point Index (QPI) is used to measure a student’s academic
performance. To determine the QPI, we use the formula for the weighted
mean. The weights w are the credit units of the subject and the values X are
point values of each grade.
The table below shows the grades of Student A for the Second Semester of SY
2017-2018. Compute for the QPI of Student A.
SUBJCODE Units LG PV
(Weight) (Value)
EDUM233 3 A 4.0
ENGS003 3 B+ 3.5
EVSS001 3 C+ 2.5
MTHS002 3 B 3.0
MTHS024(LAB) 1 B+ 3.5
MTHM211 5 C 2.0
PHIS003 3 B 3.0
Numerical Descriptive Measures
Midrange and Weighted Mean
Likert Scale
Likert Scale
Likert Scale
Likert Scale
Seatwork
Determine the weighted mean for each item in the survey and the
cumulative or total weighted mean. Then, interpret the cumulative
mean. Use the table below for your interpretation.
Numerical Descriptive Measures
Midrange and Weighted Mean
Thesis Title: Portable Games and Devices Towards Aggressive Behavior of the
First Year BS Digital Animation Students of the Ateneo de Naga University
Objective: To determine the level of influence of playing portable games and
devices on the behavior specifically aggressiveness of the respondents
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
Numerical Descriptive Measures
Fractiles
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
It divides a data set into 100 equal parts, each part having one
percent of all the data values.
Numerical Descriptive Measures
Fractiles
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
It divides a data set into 100 equal parts, each part having one
percent of all the data values.
Decile Di
The 9 score - points which divide a distribution into 10 equal parts.
Numerical Descriptive Measures
Fractiles
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
It divides a data set into 100 equal parts, each part having one
percent of all the data values.
Decile Di
The 9 score - points which divide a distribution into 10 equal parts.
It divides a data set into 10 equal parts, each part having ten
percent of all data values.
Numerical Descriptive Measures
Fractiles
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
It divides a data set into 100 equal parts, each part having one
percent of all the data values.
Decile Di
The 9 score - points which divide a distribution into 10 equal parts.
It divides a data set into 10 equal parts, each part having ten
percent of all data values.
Quartile Qi
The 3 score - points which divide a distribution into 4 equal parts.
Numerical Descriptive Measures
Fractiles
Definition of Terms
Percentile Pi
The 99 score - points which divide a distribution into 100 equal
parts.
It divides a data set into 100 equal parts, each part having one
percent of all the data values.
Decile Di
The 9 score - points which divide a distribution into 10 equal parts.
It divides a data set into 10 equal parts, each part having ten
percent of all data values.
Quartile Qi
The 3 score - points which divide a distribution into 4 equal parts.
It divides the data set into 4 equal parts, each part having 25
percent of all the data value.
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: Q1
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: Q3
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: D3
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: D7
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: D9
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: D5
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P7
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P18
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P30
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P50
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P63
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P70
Numerical Descriptive Measures
Fractiles
Example
5, 5, 7, 8, 8, 8, 9, 10, 10, 11, 12, 12, 12, 14, 15, 15, 17, 18, 19, 20
Find: P85
Numerical Descriptive Measures
Fractiles
Example
Example
Example
Example
Example
Example
Example
Example
Example
Example
Example
Example
Interpretations
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Deciles
D1 : 10% fall below or equal to the first decile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Deciles
D1 : 10% fall below or equal to the first decile
D2 : 20% are below or equal to the second decile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Deciles
D1 : 10% fall below or equal to the first decile
D2 : 20% are below or equal to the second decile
D5 : 50% are less than or equal to the fifth decile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Deciles
D1 : 10% fall below or equal to the first decile
D2 : 20% are below or equal to the second decile
D5 : 50% are less than or equal to the fifth decile
D9 : 90% fall below or equal to the ninth decile
Numerical Descriptive Measures
Fractiles
Interpretations
Quartiles
Q1 : 25% fall below or equal to the first quartile
Q1 : 75% fall above or equal to the first quartile
Q2 : 50% are below or equal to the second quartile
Q3 : 75% are less than or equal to the third quartile
Deciles
D1 : 10% fall below or equal to the first decile
D2 : 20% are below or equal to the second decile
D5 : 50% are less than or equal to the fifth decile
D9 : 90% fall below or equal to the ninth decile
D9 : 10% fall above or equal to the ninth decile
Numerical Descriptive Measures
Measures of Dispersion/Variation
Find the mean and median of the sets of data below. The data
below shows the number of years the brands of laptop last.
Find the mean and median of the sets of data below. The data
below shows the number of years the brands of laptop last.
The mean and the median of the two data sets are x = 20 and
mdn = 20, respectively (note that n = 9).
Numerical Descriptive Measures
Measures of Dispersion/Variation
Measures of Variation/Dispersion
I Measures of how the data are spread out or dispersed along
the scale of distribution
Numerical Descriptive Measures
Measures of Dispersion/Variation
Measures of Variation/Dispersion
I Measures of how the data are spread out or dispersed along
the scale of distribution
I Describe the extent to which the data are dispersed
Numerical Descriptive Measures
Measures of Dispersion/Variation
Measures of Variation/Dispersion
I Measures of how the data are spread out or dispersed along
the scale of distribution
I Describe the extent to which the data are dispersed
I Lesser/Lower means more stable, consistent, and homogenous
Numerical Descriptive Measures
Measures of Dispersion/Variation
Measures of Variation/Dispersion
I Measures of how the data are spread out or dispersed along
the scale of distribution
I Describe the extent to which the data are dispersed
I Lesser/Lower means more stable, consistent, and homogenous
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Measures merely how far the highest value is from the lowest value
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Measures merely how far the highest value is from the lowest value
Does not tell anything about the scores between these two
extreme values makes it a weak measure of variation
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Measures merely how far the highest value is from the lowest value
Does not tell anything about the scores between these two
extreme values makes it a weak measure of variation
NOT stable measure of variation
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Measures merely how far the highest value is from the lowest value
Does not tell anything about the scores between these two
extreme values makes it a weak measure of variation
NOT stable measure of variation
Easiest to compute but the least satisfactory
Numerical Descriptive Measures
Measures of Dispersion/Variation
Range
The range is the difference of the highest value and the lowest
value in the data set (ungrouped data).
Estimated by subtracting the lower boundary of the lowest class
interval from the upper boundary of the highest class interval
(grouped data)
Measures merely how far the highest value is from the lowest value
Does not tell anything about the scores between these two
extreme values makes it a weak measure of variation
NOT stable measure of variation
Easiest to compute but the least satisfactory
Example (Number of Years the Brands of Laptop Last)
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
R = highest value − lowest value = 24 − 15 = 9
Brand B: 3, 7, 10, 12, 20, 25, 28, 35, 40
R = highest value − lowest value = 40 − 3 = 37
Numerical Descriptive Measures
Measures of Dispersion/Variation
Interquartile Range
This is the difference of the first quartile from the third quartile.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Interquartile Range
This is the difference of the first quartile from the third quartile.
IR = Q3 − Q1
Numerical Descriptive Measures
Measures of Dispersion/Variation
Interquartile Range
This is the difference of the first quartile from the third quartile.
IR = Q3 − Q1
More desirable than the range when the distribution we want to
describe is markedly truncated or skewed, or when the median is
the only measure of central tendency that is available.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Interquartile Range
This is the difference of the first quartile from the third quartile.
IR = Q3 − Q1
More desirable than the range when the distribution we want to
describe is markedly truncated or skewed, or when the median is
the only measure of central tendency that is available.
Indicates the distance between the two values which determine the
middle 50% of all observations within the distribution
Numerical Descriptive Measures
Measures of Dispersion/Variation
Interquartile Range
This is the difference of the first quartile from the third quartile.
IR = Q3 − Q1
More desirable than the range when the distribution we want to
describe is markedly truncated or skewed, or when the median is
the only measure of central tendency that is available.
Indicates the distance between the two values which determine the
middle 50% of all observations within the distribution
It is necessary to verify a suspect outlier.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
IR = Q3 − Q1 = 22 − 18 = 4
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
Examples
Interquartile Range for Ungrouped Data
IR = Q3 − Q1 = 28 − 10 = 18
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Interquartile Range for Grouped Data
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18,
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Step 4: Subtract 1.5IR from Q1 and add 1.5IR to Q3
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Step 4: Subtract 1.5IR from Q1 and add 1.5IR to Q3
Q1 − 1.5IR = 17 − 6 = 11
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Step 4: Subtract 1.5IR from Q1 and add 1.5IR to Q3
Q1 − 1.5IR = 17 − 6 = 11
Q3 + 1.5IR = 22 + 6 = 28
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Step 4: Subtract 1.5IR from Q1 and add 1.5IR to Q3
Q1 − 1.5IR = 17 − 6 = 11
Q3 + 1.5IR = 22 + 6 = 28
Step 5: Check if there are data values less than Q1 − 1.5IR or
greater than Q3 + 1.5IR.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Number of Years the Brands of Laptop Last
Step 1: Arrange and find Q1 and Q3
Brand A: 15, 17, 18, 19, 20, 22, 22, 23, 24
Q1 = 18, Q3 = 22
Step 2: Find the interquartile range
IR = Q3 − Q1 = 22 − 18 = 4
Step 3: Multiply the IR by 1.5.
1.5IR = 1.5(4) = 6.
Step 4: Subtract 1.5IR from Q1 and add 1.5IR to Q3
Q1 − 1.5IR = 17 − 6 = 11
Q3 + 1.5IR = 22 + 6 = 28
Step 5: Check if there are data values less than Q1 − 1.5IR or
greater than Q3 + 1.5IR.
Since there are no values less than 11 or greater than 28, then
there is no outlier in the data set.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Checking for Outliers for Grouped Data
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
IR = Q3 − Q1 = 22 − 18 = 4
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Quartile Deviation for Ungrouped Data
IR = Q3 − Q1 = 22 − 18 = 4
IR 4
QD = = = 2
2 2
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
Examples
Quartile Deviation for Ungrouped Data
IR = Q3 − Q1 = 28 − 10 = 18
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Quartile Deviation for Ungrouped Data
IR = Q3 − Q1 = 28 − 10 = 18
IR 18
QD = = = 9
2 2
Numerical Descriptive Measures
Measures of Dispersion/Variation
Examples
Interquartile Range for Grouped Data
Average Deviation
Numerical Descriptive Measures
Measures of Dispersion/Variation
Average Deviation
Average Deviation
Population
P
|xn − µ|
MD =
N
Example
Recall that the mean is 20.
x x− mean |xn − mean|
15 −5 5
17 −3 3
18 −2 2
19 −1 1
20 0 0
22 2 2
22 2 2
23 3 3
24 4 4
P
n=9 |xn − mean| = 22
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
Recall that the mean is 20.
x x− mean |xn − mean|
15 −5 5
17 −3 3
18 −2 2
19 −1 1
20 0 0
22 2 2
22 2 2
23 3 3
24 4 4
P
n=9 |xn − mean| = 22
22
md = = 2.44
9
Numerical Descriptive Measures
Measures of Dispersion/Variation
329.4
MD = = 6.59
50
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Considers the position of each observation relative to the mean
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Considers the position of each observation relative to the mean
Average of the square of the distance that each value is from the
mean
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Considers the position of each observation relative to the mean
Average of the square of the distance that each value is from the
mean
Variance for Ungrouped Data
Population σ 2
(x − µ)2
P
2
σ =
N
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Considers the position of each observation relative to the mean
Average of the square of the distance that each value is from the
mean
Variance for Ungrouped Data
Population σ 2
(x − µ)2
P
2
σ =
N
Sample s2
(x − x)2
P
2
s =
n−1
Numerical Descriptive Measures
Measures of Dispersion/Variation
Variance (s2 or σ 2 )
The standard Deviation Squared
Considers the position of each observation relative to the mean
Average of the square of the distance that each value is from the
mean
Variance for Ungrouped Data
Population σ 2
(x − µ)2
P
2
σ =
N
Sample s2
(x − x)2
P
2
s =
n−1
Population
x2 − ( x)2
P P
2 N
σ =
N2
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
x2 − ( x)2
P P
2 N
σ =
N2
Sample
x2 − ( x)2
P P
2 n
s =
n(n − 1)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
Example
For Population
x2 − ( x)2
P P
2 N
σ =
N2
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
For Population
x2 − ( x)2
P P
2 N 648
σ = = =
N2 81
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
For Population
x2 − ( x)2
P P
2 N 648
σ = = =8
N2 81
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
For Population
x2 − ( x)2
P P
2 N 648
σ = = =8
N2 81
For Sample
x2 − ( x)2
P P
2 n
s =
n(n − 1)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
For Population
x2 − ( x)2
P P
2 N 648
σ = = =8
N2 81
For Sample
x2 − ( x)2
P P
2 n 648
s = =
n(n − 1) 9(8)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Example
For Population
x2 − ( x)2
P P
2 N 648
σ = = =8
N2 81
For Sample
x2 − ( x)2
P P
2 n 648
s = = =9
n(n − 1) 9(8)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
F (CM − µ)2
P
2
σ =
N
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
F (CM − µ)2
P
2
σ =
N
Sample
f (CM − X)2
P
2
s =
n−1
Numerical Descriptive Measures
Measures of Dispersion/Variation
F (CM − µ)2
P
3114.50
σ2 = = = 62.29
N 50
Numerical Descriptive Measures
Measures of Dispersion/Variation
f (CM − x)2
P
3114.50
s2 = = = 63.56
n−1 50 − 1
Numerical Descriptive Measures
Measures of Dispersion/Variation
Standard Deviation σ or s
Best measure of variation
Numerical Descriptive Measures
Measures of Dispersion/Variation
Standard Deviation σ or s
Best measure of variation
Important as a measure of heterogeniety or unevenness within a set
of observations
Numerical Descriptive Measures
Measures of Dispersion/Variation
Standard Deviation σ or s
Best measure of variation
Important as a measure of heterogeniety or unevenness within a set
of observations
Used when comparing 2 or more sets of data having the same units
of measurement
Numerical Descriptive Measures
Measures of Dispersion/Variation
Standard Deviation σ or s
Best measure of variation
Important as a measure of heterogeniety or unevenness within a set
of observations
Used when comparing 2 or more sets of data having the same units
of measurement
Standard Deviation for Ungrouped Data
Population rP
(x − µ)2
σ=
N
Sample s
(x − X)2
P
s=
n−1
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
r
x2 − ( x)2
P P
N
σ=
N2
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
r
x2 − ( x)2
P P
N
σ=
N2
Sample
s P
n x2 − ( x)2
P
s=
n(n − 1)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Sample
s P
n x2 − ( x)2
P
s=
n(n − 1)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Sample
s P s
n x2 − ( x)2
P
648
s= =
n(n − 1) 9(8)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Sample
s P s
n x2 − ( x)2
P
648
s= = = 3
n(n − 1) 9(8)
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
rP
F (CM − µ)2
σ=
N
Numerical Descriptive Measures
Measures of Dispersion/Variation
Population
rP
F (CM − µ)2
σ=
N
Sample
s
f (CM − X)2
P
s=
n−1
Numerical Descriptive Measures
Measures of Dispersion/Variation
Chebyshev’s Theorem
For any set of values and any constant k greater than 1, at least
1 − k12 of the values must lie within k standard deviations of the
mean.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Chebyshev’s Theorem
For any set of values and any constant k greater than 1, at least
1 − k12 of the values must lie within k standard deviations of the
mean.
Example
For any set of data and for k = 2, at least three-fourths, or 75%,
of all the data values fall within 2 standard deviations of the mean
of the data set.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s
cv = × 100%
x
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100
x 87
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100 = 5.7%
x 87
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100 = 5.7%
x 87
s
cv = × 100%
x
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100 = 5.7%
x 87
s 773
cv = × 100% = × 100
x 5225
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100 = 5.7%
x 87
s 773
cv = × 100% = × 100 = 14.8%
x 5225
Numerical Descriptive Measures
Measures of Dispersion/Variation
Coefficient of Variation
Example
Sales of Automobiles
The mean of the number of sales of cars over a three-month
period is 87, and the standard deviation is 5. The mean of the
commissions is $5225, and the standard deviation is $773.
Compare the variations of the two.
Solution
s 5
cv = × 100% = × 100 = 5.7%
x 87
s 773
× 100% =
cv = × 100 = 14.8%
x 5225
Since the coefficient of variation is larger for commissions, the
commissions are more variable than the sales.
Numerical Descriptive Measures
Measures of Dispersion/Variation
Seatwork
The data below shows the scores of 15 students enrolled in
MTHS002 N1 for the first semester of SY 2018-2019. Find the ...
I ... range.
I ... interquartile range.
I ... quartile deviation.
I ... mean deviation.
I ... variance.
I ... standard deviation.
I ... coefficient of variation.
19, 15, 19, 19, 23, 22, 16, 8, 17, 21, 17, 16, 16, 20, 21
Numerical Descriptive Measures
Measures of Skewness
Objectives
Recall
Frequency Curve
A smoothed frequency polygon obtained by increasing the number
of class intervals and consequently decreasing the interval size.
Numerical Descriptive Measures
Measures of Skewness
Recall
Frequency Curve
A smoothed frequency polygon obtained by increasing the number
of class intervals and consequently decreasing the interval size.
Types of Curves
I Bell-shaped curve
Numerical Descriptive Measures
Measures of Skewness
Recall
Frequency Curve
A smoothed frequency polygon obtained by increasing the number
of class intervals and consequently decreasing the interval size.
Types of Curves
I Bell-shaped curve
I Skewed Curve
Numerical Descriptive Measures
Measures of Skewness
Recall
Frequency Curve
A smoothed frequency polygon obtained by increasing the number
of class intervals and consequently decreasing the interval size.
Types of Curves
I Bell-shaped curve
I Skewed Curve
I Positively-skewed Curve
Numerical Descriptive Measures
Measures of Skewness
Recall
Frequency Curve
A smoothed frequency polygon obtained by increasing the number
of class intervals and consequently decreasing the interval size.
Types of Curves
I Bell-shaped curve
I Skewed Curve
I Positively-skewed Curve
I Negatively-Skewed Curve
Numerical Descriptive Measures
Measures of Skewness
Recall
Bell-Shaped Curve
This shows normal distribution.
Numerical Descriptive Measures
Measures of Skewness
Recall
Bell-Shaped Curve
This shows normal distribution.
Positively-skewed Curve
The frequencies of the smaller class intervals are higher than those
of the class intervals at the other end of the distribution, the curve
will tail off to the right and we have positively-skewed distribution.
Numerical Descriptive Measures
Measures of Skewness
Recall
Bell-Shaped Curve
This shows normal distribution.
Positively-skewed Curve
The frequencies of the smaller class intervals are higher than those
of the class intervals at the other end of the distribution, the curve
will tail off to the right and we have positively-skewed distribution.
Negatively-skewed Distribution
The frequencies of the larger class intervals are higher than those
of the smaller classes, the curve will tail off to the left and we have
a negatively-skewed distribution.
Numerical Descriptive Measures
Measures of Skewness
Measures of Skewness
Numerical Descriptive Measures
Measures of Skewness
Measures of Skewness
Formula
Population
3(µ − M dn)
Sk =
σ
Numerical Descriptive Measures
Measures of Skewness
Measures of Skewness
Formula
Population
3(µ − M dn)
Sk =
σ
Sample
3(X − mdn)
Sk =
s
Numerical Descriptive Measures
Measures of Skewness
Try this!
Scores of 50 Students in a Math Test
LL UL LTCB UTCB CM F <CF
20 - 24 19.5 - 24.5 22 2 2 (1-2)
25 - 29 24.5 - 29.5 27 6 8 (3-8)
30 - 34 29.5 - 34.5 32 9 17 (9-17)
35 - 39 34.5 - 39.5 37 10 27 (18-27)
40 - 44 39.5 - 44.5 42 12 39 (28-39)
45 - 49 44.5 - 49.5 47 7 46 (40-46)
50 - 54 49.5 - 54.5 52 4 50 (47-50)
c0 = 5 µ = 38.1 σ = 7.89 N = 50
Numerical Descriptive Measures
Measures of Skewness
Try this!
Scores of 50 Students in a Math Test
LL UL LTCB UTCB CM F <CF
20 - 24 19.5 - 24.5 22 2 2 (1-2)
25 - 29 24.5 - 29.5 27 6 8 (3-8)
30 - 34 29.5 - 34.5 32 9 17 (9-17)
35 - 39 34.5 - 39.5 37 10 27 (18-27)
40 - 44 39.5 - 44.5 42 12 39 (28-39)
45 - 49 44.5 - 49.5 47 7 46 (40-46)
50 - 54 49.5 - 54.5 52 4 50 (47-50)
c0 = 5 µ = 38.1 σ = 7.89 N = 50
3(µ − M dn)
Sk =
σ
Numerical Descriptive Measures
Measures of Skewness
Try this!
Scores of 50 Students in a Math Test
LL UL LTCB UTCB CM F <CF
20 - 24 19.5 - 24.5 22 2 2 (1-2)
25 - 29 24.5 - 29.5 27 6 8 (3-8)
30 - 34 29.5 - 34.5 32 9 17 (9-17)
35 - 39 34.5 - 39.5 37 10 27 (18-27)
40 - 44 39.5 - 44.5 42 12 39 (28-39)
45 - 49 44.5 - 49.5 47 7 46 (40-46)
50 - 54 49.5 - 54.5 52 4 50 (47-50)
c0 = 5 µ = 38.1 σ = 7.89 N = 50
Try this!
Scores of 50 Students in a Math Test
LL UL LTCB UTCB CM F <CF
20 - 24 19.5 - 24.5 22 2 2 (1-2)
25 - 29 24.5 - 29.5 27 6 8 (3-8)
30 - 34 29.5 - 34.5 32 9 17 (9-17)
35 - 39 34.5 - 39.5 37 10 27 (18-27)
40 - 44 39.5 - 44.5 42 12 39 (28-39)
45 - 49 44.5 - 49.5 47 7 46 (40-46)
50 - 54 49.5 - 54.5 52 4 50 (47-50)
c0 = 5 µ = 38.1 σ = 7.89 N = 50