Sei sulla pagina 1di 9

Republic of the Philippines

State Universities and Colleges


GUIMARAS STATE UNIVERSITY
GRADUATE SCHOOL
McLain, Buenavista, Guimaras

Educational Measurement and Evaluation


First Semester, A.Y. 2019-2020
Professor: ETHEL P. JUNCO
Discussant: RENE T. GALANZA, MATM

MEASURES OF CENTRAL TENDENCY

Learning Objectives:
1. Illustrate the measures of central tendency (mean, median, and mode) of
statistical data;
2. Calculate the measure of central tendency of ungrouped and grouped data; and
3. Use appropriate statistical measure in analyzing and interpreting data.

What is a measure of central tendency?


Numbers that describe what is average or typical of the distribution.
You can think of this value as where the middle of a distribution lies.

An important part of data analysis is to find the average value, middle value, or
the most frequent value of a set of data, which are commonly known as the mean,
median, and mode, respectively.

For the mean, we use the symbol “ X́ ”, read as “X-bar”, for the median, “
~
X ”, for the median, read as “X-tilde”, and for the mode “ ^
X ”, read as “X-hat”.

Definition
Measures of Central Tendency
The mean (commonly called the average) of a set of n numbers is the sum
of all numbers divided by n.
The median is the middle number when the number in a set of data is
arranged in descending order. When there are even numbers of elements, the
median is the mean of the two middle numbers.
The mode is the numbers that occurs most often in a set of data. A set of
data can have more than one mode. If all the numbers appear the same of times,
there is no mode for that data set.

The Mean X́
The mean is the most popular among the measures of central tendency for it
is widely used. It indicates a point around with the values in the distribution balance.
This can easily be justified by showing that the sum of the differences from the
mean is equal to zero. It is also affected by extreme values.
The computation of the mean is very simple. To get the mean, simply add all
the scores in a distribution and divide by the total number of values. The formulas
for the computation of the mean are as follows:
Formula:
Mean (Ungrouped Data)

X́ =
∑ Xi where: X́ = mean ∑ Xi = sum of the scores
N
Xi = scores N = total frequency
Example 1:
The following is a list of the weekly savings of ten students.

Studen Abe Brend Carlo Donn Edwi Fre Gin Han Izz Jaco
t l a s a n d a s y b
Weekly 60 50 40 50 70 50 50 80 70 70
Saving
s

Find the average weekly savings per student.

Solution:

X́ =
∑ Xi =
60+ 50+40+50+ 70+ 50+50+80+70+70
=59
N 10

The value of 59 is the mean of the set of values that represent the savings of
the students.

Formula:
Weighted Mean

X́ =
∑ fX where: X́ = mean f = frequency
N
X
= score N = total frequency
∑ fX= sum of the product of frequency and score
Let us represent the data in Example 1 in a frequency table.

Weekly Savings (X) 40 50 60 70 80


Number of Students (f) 1 4 1 3 1 N = 10
(fX) 40 200 60 210 80 ∑ fX =
590

Use the formula to calculate.

Solution: X́ =
∑ fX = 590 =59
N 10

The mean weekly savings per student is 59.

Formula:
Mean (Grouped Data)

X́ =
∑ f Xm where: X́ = mean f = frequency
N
Xm = class mark (average of lower interval and upper
interval
∑ m = sum of the product of frequencies and class
f X
marks
N = total frequency
Example 2:
Calculate the mean score of 40 students given in the Table below.

Grouped Frequency Distribution of Scores of 40 Students in a Math Quiz


Scores f Xm f Xm
98 – 100 2 99 198
95 – 97 1 96 96
92 – 94 1 93 93
89 – 91 6 90 540
86 – 88 6 87 522
83 – 85 5 84 420
80 – 82 9 81 729
77 – 79 2 78 156
74 – 76 3 75 225
71 – 73 5 72 360
N=40 ∑ f X m=3339
Solution:

X́ =
∑ f X m = 3339 =83.475
N 40

The mean score of 40 students in a Math quiz is approximately equal to 83.475.

Alternative Formula:
Mean (Grouped Data)
∑ f Xc
(
X́ =X 0 +
N ) i where: X́ = mean f = frequency

X0 = coded value ( X −i X )∨ X
m 0
c

i = size of the class interval


N = total frequency

Use example 2:

Grouped Frequency Distribution of Scores of 40 Students in a Math Quiz


Scores f Xm Xc f Xc
98 – 100 2 99 4 8
95 – 97 1 96 3 3
92 – 94 1 93 2 2
89 – 91 6 90 1 6
86 – 88 6 87 0 0
83 – 85 5 84 -1 -5
80 – 82 9 81 -2 -18
77 – 79 2 78 -3 -6
74 – 76 3 75 -4 -12
71 – 73 5 72 -5 -25
N=40 ∑ f X m=−47
Solution:
X́ =X 0 + (∑ ) f Xc
N
i=87+
−47
40 ( )
3=83.475

Note: This is the same mean that we got in example 2.


~
The Median X

The median is the value in the distribution which divides an


arranged (ascending or descending) distribution into two equal parts. The
arrangement of data in this manner is called an array. We use the median when we
want to know the value in which half of the scores are more extreme and half are
less extreme.
To find the median, we arrange the measurements in ascending
order and take the middle term.
The median of the 5 numbers 20, 40, 70, 80, and 90 is the third
number, 70.
If the sixth number, 95, is added to the sequence, there is no
middle number. In this case, the median is taken to be the mean of the third and
70+ 80
fourth number, or 75.
2

Example 3:
The scores of the 9 students in Example 1 are arranged in
ascending order as follows. Find the median of the distribution.

Studen Fre Brend Gina Donna Abel Edwin Izzy Jacob Hans
t d a
Weekly 50 50 50 50 60 70 70 70 80
Savings

Since there are 9 scores and it is odd, simply get the middle score
which is 60. Therefore, the median is 60.

In general, a data with N observations are arranged in ascending order:


th
N
1. If N is odd, the median is the middle position which is ( )
2
position.

2. If N is even, the median is the mean of the two middle data which are the
th th
N N
( )
2
and ( 2
+1 ) data.

The Median of a Grouped Data


The first step in the computation of a grouped data is to determine
th
N
the class interval which contains the ( )
2
score. This can be located under the

column <cf of the cumulative frequency distribution. The class interval that contains
th
N
the ( )
2
score is called the median class of the distribution. To calculate for the

median, we use the formula below.

Formula:

Median (Grouped Data)


N
~
X= X LB +

interval
2
( )
−cf b
fm
i where:
~ = median
X i = size of the

cf b = cumulative frequency before the median class


X LB = the lower boundary or true limit of the median class
f m = frequency of the median class
N = total frequency

Example 4:
Cumulative Frequency Distribution of a 30-point Math Quiz
Scores f <cf
28 – 29 1 60
26 – 27 3 59
24 – 25 3 56
22 – 23 3 53
20 – 21 6 50
18 – 19 6 44
16 – 17 8 38
14 – 15 6 30 Median class
12 – 13 10 24
10 – 11 14 14
N = 60

Solution:
N 60
2
th score= ( )
2
thscore=30 th score

The class interval that contains the 30th score is 14 – 15.

N
~
X= X LB +
2
( )
−cf b
fm
i=13.5+
30−24
6 ( )
2=13.5+2=15.5

This means that 50 percent of the students got scores below 15.5 or if the
passing score is 50 percent of the total number of points, almost one-half of the
class failed in that particular quiz.

Example 5:
Find the median of the grouped data in the table below.
Birth Weight (in ounces) f <cf
134 – 139 10 50

Median class
128 – 133 9 40
122 – 127 8 31
116 – 121 1 23
110 – 115 5 22
104 – 109 2 17
98 – 103 9 15
92 – 97 5 6
86 - 91 1 1
N = 50

Solution:
N 50
Locate the
2
th score=
2( )
thscore=25 th score

The class interval containing the 25th score is 122 – 127.

N
~
X= X LB +
2
( )
−cf b
fm
i=121.5+
25−23
8 (
6=123 )
The Mode ^ X
The mode of a distribution is the data with the highest frequency. The mode
of the data can be more than one. It is also possible that there can be no mode in a
set of data.

Example 6:
Find the mode of the data below.

Studen Abe Brend Carlo Donn Edwi Fre Gin Han Izz Jaco
t l a s a n d a s y b
Weekly 60 50 40 50 70 50 50 80 70 70
Saving
s

Since, 50 appeared four times, therefore 50 is the mode of the set of data above.

The Mode of a Grouped Data


In the computation of the mode given a frequency distribution, the first step
is to get the modal class. The modal class is that the class interval with the highest
frequency. To compute the mode, we use the formula below.

Formula:

Mode (Grouped Data)


∆1
^
X =X LB + ( ∆1+∆2
i) where: ^
X = mode i = size of the interval

X LB = the lower boundary or true limit of the median class


∆1 = difference between the frequency of the modal class
and the frequency of the class interval preceding it
∆ 2 = difference between the frequency of the modal class
and the frequency of the class interval succeeding it
Example 7:
Find the mode of the grouped data in the table below.

Scores of 40 Students in Math Quiz


Scores f
98 – 100 2
95 – 97 1
92 – 94 1
89 – 91 6
86 – 88 6
83 – 85 5
80 – 82 9 Modal class
77 – 79 2
74 – 76 3
71 – 73 5
N=40

Solution:
∆1
^
X =X LB + ( )
∆1+ ∆2
i=79.5+( )7
7 +4
3=81.41

Approximately, the mode of the scores of 40 students in a Math quiz is 81.41.


Example 8:
Find the mode of the grouped data in the table below.

Birth Weight (in ounces) F


134 – 139 10 Modal class
128 – 133 9
122 – 127 8
116 – 121 1
110 – 115 5
104 – 109 2
98 – 103 9
92 – 97 5
86 - 91 1
N = 50

Solution:
∆1
^
X =X LB + ( )
∆ 1+ ∆ 2 (
i=133.5+
1
)
1+10
6=134.05

Approximately, the mode of the birth weight in ounces is 134.05.

When to use the Mean?


 You should use the mean when
 the data are interval or ratio scaled
 Many people will use the mean with ordinally scaled data too
 and the data are not skewed
The mean is preferred because it is sensitive to every score
If you change one score in the data set, the mean will change

When to use the Median?


 The median is often used when the distribution of scores is either positively
or negatively skewed
 The few really large scores (positively skewed) or really small scores
(negatively skewed) will not overly influence the median

When to use the Mode?


 The mode is not a very useful measure of central tendency
 It is insensitive to large changes in the data set
 That is, two data sets that are very different from each other can
have the same mode
 The mode is primarily used with nominally scaled data
 It is the only measure of central tendency that is appropriate for
nominally scaled data

Relations between the Measures of Central Tendency


In symmetrical distributions, the median and mean are equal
 For normal distributions, mean = median = mode
 In positively skewed distributions, the mean is greater than the median
 In negatively skewed distributions, the mean is smaller than the median
PRACTICE AND APPLICATION

Find the mean, median, and mode for each set of data.

1. 67, 89, 93, 77, 84 2. 32, 43, 31, 52, 28, 39


3. 13, 11, 10, 12, 14, 9, 11, 8, 11 4. 10.5, 7, 10, 9.1, 10, 9.1

5.
x 13.5 13.7 14.0 14.1 14.2 14.8
f 2 6 22 29 12 4

6.
x 2 2 2 2 2 2
f 3 5 20 31 10 6

7. 8.
x f
95 – 109 8 x f
80 – 94 10 65 – 69 7
65 – 79 12 60 – 64 8
50 – 64 45 55 – 59 9
35 – 49 20 50 – 54 15
20 – 34 5 45 – 49 12
40 - 44 7
35 – 39 4
30 – 34 8
ENRICHMENT

Solve each problem. State the type of average used.

1. The ages of 20 guests at a party are 22, 23, 24, 32, 27, 28, 29, 27, 7, 20, 22, 81,
33, 27, 26, 24, 19, 20, 21, and 33. Which average best describes the typical age and
what is it?

2. Edna’s Math test scores were 79, 51, 83, 76, 99, 75, 73, 84, and 77. What is
Edna’s average test scores? If her teacher drops the lowest score, what will Edna’s
average be?

3. A survey at a grocery store showed that 7 people preferred Brand A, 17 people


preferred Brand B, 29 people preferred Brand C, and 12 people preferred Brand D.
Which brand did the “average” customer prefer?

4. Two friends own a small business. The partners pay themselves P32 000.00 each
of their 12 employees, one earns P25 000.00, one earns P19 000.00, two earn P16
000.00 each, five earn P13 000.00 each, and three earn P11 000.00 each. The two
friends want to make the average salary sound as great as possible. Which average
would they choose and how much is it?

Prepared by: RENE T. GALANZA, MATM


Taken from: E-MATH Worktext in Mathematics 7, Oronce, Orlando A. & Mendoza, Marilyn O., pp.598 - 613