12/5/2022

MATH 11N
MATHEMATICS IN THE MODERN WORLD

Agenda: 12/5/22 LESSON 3.2:

1. Attendance and Time Keeper
2. Original (hard copies) of outputs must be
submitted. MEASURES OF CENTRAL
3. Lesson 3.1_Assessment (2) was due on
Friday, Dec2, 5pm and hard copies must also
TENDENCY AND LOCATION
be submitted
4. PPT Hand-out and recorded discussions on
Lesson 3.2 , Median, Mode and Fractiles are
shared https://www.balcs.ie/online-classroom-etiquette/

5. Exercise on Measures of Central Tendency

and Locations.

The Median
https://drive.google.com/file/d/1hXctJ4L95nsFFtWtAOq_1VxB4gMggB-
w/view?usp=sharing

The Mode
https://drive.google.com/file/d/1IAkC3PngB5rjtouo5TxuKbF9a16BZxSx
/view?usp=sharing
The Median
The Fractiles
https://drive.google.com/file/d/1iAy8Vcb-
PD4oxV04dU6Rf8U3qEioRkFM/view?usp=sharing

Note: Skip the part for Grouped Data and proceed to the Properties

SAMPLE EXERCISES
The Median
1. Determine the median for the data in the following lists
• the middle value of an array and interpret the values obtained.
a. 4, 8, 1, 14, 9, 21, 12
(data arranged in descending/ascending order)
• Computation: Ungrouped Data
i) Md = X N+1 , if N is odd
2

XN + X N b. 46, 23, 92, 89, 77, 108

+1
2 2
ii) Md = , if N is even
2

1
 12/5/2022

Sample Exercise
The Median
2. Estimate the median for the following data, which
represents the ages of a set of 130 representatives
• Computation: Grouped Data who took part in a statistical survey.
N 
  Ff  Age in Years No. of
Md G  L Md  C  2  Representatives
 Mdf  20-24 2
 
25-29 14
where:
LMd = lower true class boundary of the median class 30-34 29
C = class size
35-39 43
N = total no. of observations
Ff = less than cumulative frequency of the class one step lower the median class 40-44 33
fMd = frequency of the median class
median class = the first class (starting from the lowest class) 45-50 9
Q’s whose less than cumulative frequency reaches N/2

Effect of Extreme Observation to the value of the

The Median Median
Suppose we have two Data Sets:
Properties:
1. a unique value but may not be an actual value in Set A Set B
the data 3 3
2. a positional value and hence not affected by the 4 4
presence of extreme values unlike the mean 7 7
11 11
17 17
29 29
47 87

Can be used for Grouped FDT with open ended

intervals The Median
Example of an FDT with open ended intervals:

Age (years) Number of Workers Properties:

24 and below 16
3. not amenable to further computation and hence,
25 – 29 18 median of subgroups cannot be combined in the
30 – 34 24 same manner as the mean.
35 – 39 20
40 – 44 18
45 – 49 17
50 – 54 15
55 and above 14

2
 12/5/2022

The Mode

• What is it ?
• How to determine/obtain it
The Mode • Its implication/interpretation
• Its properties
• The skewness of the data set using the three
averages

The Mode The Mode

• is the value which occurs the most • However, all values occur with equal
frequent in the given data set. frequency, the frequency maybe equal to 1
• Thus, the data set or greater than 1, then there is no modal
value.
18, 15, 21, 16, 15, 14, 15, 21
• Thus, in the data set:
has a mode of 15. Why?
2, 5, 8, 9, 11, 4, 7, 23

The Mode The Mode

• Also, if two adjacent values occur with the • When two nonadjacent values occur such that the
frequency of both are greater than the frequencies in
same frequency which is larger than the
the adjacent intervals, then each value maybe taken
frequencies of the others, the mode maybe as the mode and the set of observations maybe
taken as the arithmetic mean of the two spoken of as bimodal.
adjacent values if the variable is continuous. • Hence in the following data set:
• Consider the following data set: 12, 34, 12, 71, 48, 93, 71
3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 6, 7, 7, 8 the modal values are

3
 12/5/2022

The Mode The Mode

To summarize: Computation: Grouped Data
• the value which occurs the most frequent in the given
data set is the mode.
• However, in the cases where
 f f 
→ all values occur with equal frequency, the frequency maybe Mo G  L Mo  C  Mo 1 
 2f Mof1  f 2 
equal to 1 or greater than 1, then there is no modal value.
→ If two adjacent values occur with the same frequency which
is larger than the frequencies of the others, the mode
maybe taken as the arithmetic mean of the two adjacent
values if the variable is continuous where:
Lmo = lower class boundary of the modal class
→ When two nonadjacent values occur such that the C = class size
frequency of both are greater than the frequencies in the fMo = frequency of the modal class
adjacent intervals, then each value maybe taken as the f = frequency of the class one step lower than the modal class
𝐟𝟐 = frequency of the class one step higher than the modal class
mode and the set of observations maybe spoken of as
bimodal

Sample Exercise
The Mode
Estimate the modal age for the following data onthe
Computation: Grouped Data Age in No. of
ages of a set of 130 representatives who took part in a
Years Represent statistical survey.
atives
 f f  Age in Years No. of
Mo G  L Mo  C  Mo 1  20-24 2
Representatives
 2f Mof1  f 2  25-29 14
20-24 2
30-34 29
35-39 43 25-29 14

where: 40-44 33 30-34 29

Lmo = lower class boundary of the modal class
C = class size 45-50 9
fMo = frequency of the modal class 35-39 43
f = frequency of the class one step lower than the modal class
𝐟𝟐 = frequency of the class one step higher than the modal class 40-44 33

45-50 9

Comparison of the Mean, Median,

The Mode and Mode
Properties: In a perfectly symmetric distribution, all
The mode is determined by the frequency and
1. the three measures are equal
not by the value of the observations.
2. It cannot be manipulated algebraically and
hence modes of subgroups cannot be
combined like the mean.
3. The mode can be defined in both qualitative A symmetric distribution

and quantitative data

24

4
 12/5/2022

When extreme observations are found on the right end If extremely low observations are present
of the distribution (positively skewed distribution): (negatively skewed distribution): μ < Md < Mo
Mo < Md < μ

A negatively skewed distribution

A positively skewed distribution.

25 26

SAMPLE EXERCISES ON
EXAMPLE: AVERAGES
Describe the skewness of the following data, using the 1. Find the mode for the data in the following lists.
relationship between the mean, median, and mode. a. 18, 15, 21, 16, 15, 14, 15, 21
b. 2, 5, 8, 9, 11, 4, 7, 23
18, 15, 90, 16, 15, 14, 15, 21 c. 3, 3, 3, 3, 3, 4, 4, 5, 5, 5, 8
d. 12, 34, 12, 71, 48, 93, 71

2. Compare the mean, the median, and the mode for the
salaries of 5 employees of a small company.
Salaries: P 370,000 P 60,000
P 36,000 P 20,000
P 20,000
Which among the measures of center better
represents the average of the salaries?

The Fractile /Quantiles

The Fractile /Quantiles • What are these values?
• How to solve these values?
• Its implication/interpretation

5
 12/5/2022

Other Measures of Position or Location

The Fractile /Quantiles  Fractiles are values which are obtained from
Reminder: The averages, like the arithmetic equal subdivisons of the data. The subdivisions
mean, median, and mode are measures of into four equal parts, 10 equal parts and 100
central location. equal parts are called quartiles, deciles and
percentiles, respectively.
The fractiles or quantiles are other
measure of position or location.

Quartiles Quartiles
→The three numbers Q1, Q2, and Q3 that →The three numbers Q1, Q2, and Q3 that
partition a ranked data set into four partition a ranked data set into four
(approximately) equal groups are called (approximately) equal groups are called
the quartiles of the data. the quartiles of the data.

→25% of the data fall below Q1, 50% fall →25% of the data fall below Q1, 50% fall
below Q2, and 75% fall below Q3. below Q2, and 75% fall below Q3.
For instance, for the data set below, the values
Q1 = 11, Q2 = 29, and Q3 = 104 are the quartiles of the
data below:
2, 5, 5, 8, 11, 12, 19, 22, 23, 29, 31, 45, 83, 91, 104,
159, 181, 312, 354

Quartiles Deciles
→the first quartile, Q1 indicates the value below
• values that divide a set of arrayed
which 25% of observation may be found.
observations into 10 equal parts
→ And it is also the value above which 75% of the
observations may be found.
denoted by D1, D2,..., D9;
→ on the other hand, the third quartile, Q3 • 10% of the data fall below D1, 20% fall
indicates the value below which 75% of the below D2, ..., and 90% fall below D9.
observations may be found.
→ And it is also the value above which 25% of the
observations may be found.

6
 12/5/2022

Deciles Percentiles
 A percentile, (Pi) is a measure used to indicate
→the first decile, D1 indicates the value below the value below which a given percentage of
which 10% of observation may be found. And it is observation fall.
also the value above which 90% of the  values that divide a set of arrayed
observations may be found. observations into 100 equal parts denoted by
→ while, the 6th decile, D6 indicates the value P1, P2, ...,P99 ; 1% of the data fall below P1,
below which 60% of the observations may be 2% fall below P2, ..., and 99% fall below P99.
found. And it is also the value above which 40%
of the observations may be found.  the 90th percentile (P90) indicates the value
→ it is the 5th decile, D5 which is equivalent to below which 90% of observation may be found.
the median. And it is also the value above which 10% of the
observations may be found.

Consider the following sample data:

Calculation from Ungrouped Data: 43 26 41 37 53
58 40 48 42 53
For Qi (ith quartile) For Di (ith decile), For Pi (ith percentile),
45 39 62 39 36
compute compute compute 48 50 40 49 45
iN iN iN 36 56 42 73 32
4 10 100 The array:
26 39 42 48 53
where N = total number of observations in the data set. 32 39 42 48 56
• If the result above is a whole number, the ith quantile is the
36 40 43 49 58
mean of that ranked observation and the next higher
observation. 36 40 45 50 62
• If the result is not a whole number, the ith quantile is the 37 41 45 53 73
next higher observation.

The array: The array:

26 39 42 48 53 26 39 42 48 53
32 39 42 48 56 32 39 42 48 56
36 40 43 49 58 36 40 43 49 58
36 40 45 50 62 36 40 45 50 62
37 41 45 53 73 37 41 45 53 73

Determine the following and interpret the value obtained. Determine the following and interpret the value obtained.
1. 𝑄 2. 𝑄 4. 𝐷 5. 𝐷

7
 12/5/2022

The array:
26 39 42 48 53 Calculation from Grouped Data
32 39 42 48 56 where:
36 40 43 49 58 iN L - lower class boundary of the
−F quantile class
36 40 45 50 62 Q =L +c 4 F - less than cumulative frequency
37 41 45 53 73 f of the class one step lower than
the quantile class
Determine the following and interpret the value obtained. f - frequency of the quantile class
6. 𝑃 7. 𝑃 iN c - class size
10 −F
N – number of
D =L +c
f
Qi class → the first class (starting
from the lowest class)
whose less than cumulative
iN frequency reaches iN/4
−F
P = L + c 100
f
Md

Illustrative Example: Consider the following FDT.

Compare the above Formula with that of the Determine the required value and interpret it.
Median for Grouped Data:
Class Class <CF 1. 𝑸𝟑
Intervals Frequency
1.1 – 1.5 4 4
N 
  Ff  1.6 - 2.0 6 10
Md G  L Md  C  2 
 fMd  2.1 - 2.5 8 18
 
2.6 - 3.0 20 38
where:
LMd = lower true class boundary of the median class 3.1 – 3.5 7 45
C = class size
N = total no. of observations 3.6 - 4.0 5 50
Ff = less than cumulative frequency of the class one step lower the median class
fMd = frequency of the median class
Total 50
median class = the first class (starting from the lowest class)
Q’s whose less than cumulative frequency reaches N/2

Illustrative Example: Consider the following FDT.

Determine the required value and interpret it.
Class Class <CF 2. 𝑫𝟐 Thank you for listening….
Intervals Frequency
1.1 – 1.5 4 4
1.6 - 2.0 6 10
2.1 - 2.5 8 18
2.6 - 3.0 20 38
3.1 – 3.5 7 45
3.6 - 4.0 5 50
Total 50