UNIT 1: UTILIZATION OF ASSESSMENT DATA

Lesson A: Measures of Central Tendency

The life of a teacher is always confronted with making decisions in a classroom.

In fact, some argues that on the average, on a 6-hour per day class hour, teachers
make at least 7 educational decisions. And to make sound and informed decisions,
teachers gather and process information. For example, grades of students in a
periodic examination are collected and analyzed to describe their performance.

Consider the random grades below of a group of students in two subjects.

Mathematics Science
95 97 90 66 97 82 83 77 88 94 88 72
87 70 74 76 79 86 96 68 87 68 75 82
65 72 77 76 74 89 91 73 74 78 70 79
71 79 78 83 69 75 72 95 77 92 82 80
85 77 81 89 96 99 79 93 71 75 85 65
68 70 71 94 95 97 73 67 68 69 70 86

Given the data, it would be tedious to report individual grades of students.

Instead, teachers report either the middle or typical values, or values where most of
the other grades are clustered. They are called “central values”, “averages”, measures
of central location, or measures of central tendency. These values become one of the
bases for decisions that teachers make relative to performance of the group of
students.

For this lesson, you will learn about measures of central tendency namely: the
mean, median and mode. A measure of central tendency provides a summary
measure that attempts to describe the whole set of data with a single value that
represents the middle or center of its distribution. It is the value at which other
values in the data set are clustered.

As a future teacher, it is imperative that you possess a good understanding of

these important concepts for making informed, evidenced-based decisions not only
on student’s academic performance but generally, on any quantitative data where its
use is appropriate.

A1.1 MEAN FOR RAW DATA

For raw data (data collected in their original form), the mean is simply referred
to as the arithmetic average (or arithmetic mean) of a set of data. To compute for the

Prepared by Page 1 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

mean of a data set, you add all the values in the data set then divide the sum by the
number of values in the data set. Mathematically, the mean denoted by 𝑥 is
∑&
' $%
𝑥= , where
(
n refers to the number of values in the data set, and
𝑥* are values in the data set from 1 up to n.

The formula is read as “the mean or x bar is equal to the sum of all x sub i’s i
from 1 to n, divided by n.

Note that he Greek uppercase letter Σ, pronounced as “sigma” means “sum of”.

Also, you may have noticed that the formula above is for a sample mean. A population
mean has a different notation although calculated in the same way as sample mean.
It is important to distinguish the two since in statistics, samples and populations
have different meanings and these differences are very important. The population
∑-
' $%
mean is denoted by a Greek lowercase letter 𝜇 (pronounced as “mu”). So, 𝜇= ,
.
where N refers to the number of values in the data set, and 𝑥* are values in the data
set from 1 up to N.

To illustrate, let us consider few values as the same process is used for larger
number of values.

Example 1:
Five students obtained the following scores in a test: 40, 46, 30, 35, 34.
Compute their mean score.

Solution 1.
1. Add all the values.
40 + 46 + 30 + 35 + 34 = 185. So, the sum is 185.
2. Divide the sum by the number of values.
Since there are 5 values and the sum 185, we have
185 ÷ 5 = 37.
Thus, the mean score of the five students is 37.
Solution 2.
Given n = 5; 𝑥0 = 40; 𝑥3 = 46; 𝑥5 = 30; 𝑥7 = 35; 𝑥9 = 34
∑&
' $% ∑;' $% 7<=7>=5<=59=57 0?9
𝑥= →𝑥= = = = 𝟑𝟕.
( 9 9 9
Thus, the mean score of the five students is 37.

Prepared by Page 2 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Example 2:
Let us take the data set, those random grades of a group of students in
Mathematics and Science subjects presented at the beginning of this
lesson.

Mathematics Science
95 97 90 66 97 82 83 77 88 94 88 72
87 70 74 76 79 86 96 68 87 68 75 82
65 72 77 76 74 89 91 73 74 78 70 79
71 79 78 83 69 75 72 95 77 92 82 80
85 77 81 89 96 99 79 93 71 75 85 65
68 70 71 94 95 97 73 67 68 69 70 86

In cases when data sets contain several values, when manual computation
become laborious, we may resort to using software such as SPSS (Statistical Package
for the Social Sciences), Minitab, R Studio, Stata, and the readily available MS Excel.
For this lesson, we will use MS Excel. Here is how to compute for the mean.
Step 1. Open a new MS Excel spreadsheet.
Step 2. Encode or copy the all the values to
the spreadsheet.

Step 3.
Select a cell where you want to put the
mean and enter the following formula.

=AVERAGE ().

Step 4. While the cursor is inside the

parenthesis, highlight all the values.
This is to add the range of values to be
considered for computing the mean.
The range in this case is B4:G9.
Step 5. Press ENTER and the mean of the
values will appear in the selected cell.

Thus, the mean grade of students in Mathematics is 81. 36.

Prepared by Page 3 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

What does a mean of 81.36 indicate? A mean grade of 81.36 tells that on the
average, the performance of the students in Mathematics 81.36, and is above the 75
passing mark. Moreover, we do not claim that all students obtained a grade of
81.36. Instead, we argue that the majority of the grades of the students are close to
81.36.
While the mean as a single value is very useful in describing an entire data
set, it is also suitable for comparing two or more data sets whether sample or
population data.

Compute for the mean grade of the group of students in Science.

CHECKPOINT
In which subject did the group of students obtain a higher mean
01
grade?

Now, recall the means that you and I have computed from the two examples
and the Checkpoint? Are these values found in the data set?

More often than not, the mean will be different from all the actual values you
observed in the data set. Yet, it minimizes the error in the prediction of any actual
value in the data set. Thus, creating the least quantity of error from among all
values in the data set.

A significant characteristic of the mean is that every value in the data set are
included in the computation. Furthermore, the mean is the only measure of central
tendency where the sum of the deviations of each value from the mean is always
zero.

A1.2. MEAN FOR GROUPED DATA

You might be able to encounter a case when a mean of a grouped data (data
that have been sorted and organized into a frequency distribution) is needed. How
do we do it?

The mean of a data set reported in a frequency distribution can be estimated

by using the class marks or midpoints of the interval. We apply the idea that the
mean of the values in an interval is equal to the midpoint of the interval. Using
frequency counts, we can reconstruct estimate values of the data set using the
midpoints. Now, we apply the idea for computing the mean discussed in Lesson 1.1

Prepared by Page 4 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Example 3:
Consider the IQ levels of 20 students reported as follows. Compute for their
mean IQ score.
IQ f %
119 – 127 4 20
110 – 118 10 50
101 – 109 6 30
Total (n) 20 100

Solution
Step 1: Compute for the midpoints of each interval.
The class midpoint or simply midpoint of an interval, denoted
by X is the mean of the limits of the class interval.
For the interval, 119 – 127, the midpoint is 123 obtained from
00B=03C 37>
= = 123.
3 3
For the interval 110 – 118, the midpoint is 114 obtained from
00<=00? 33?
= = 114.
3 3
For the interval 101 – 109, the midpoint is 105 obtained from
0<0=0<B 30<
= = 105.
3 3
Step 2. Reconstruct the IQ scores of 20 students using the midpoints and
the corresponding frequencies of the intervals.
The frequency denoted by f tells the number of scores that fall in an
interval.
Thus, the IQ scores arranged in decreasing order are
123 123 123 123 114
114 114 114 114 114
114 114 114 114 105
105 105 105 105 105
Step 3. Compute for the mean.
To compute the mean IQ score 𝑥 we have,
123 + 123 + 123 + 123 + 114 + 114 + 114 + 114 + 114 + 114 + 114 + 114 + 114 + 114 + 105 + 105 + 105 + 105 + 105 + 105
.
20
33>3
𝑥= 3<
= 113.1 . Thus, the mean IQ score of 20 students is 113.1. This means

that the IQ score of 113.1 is the value about which IQ scores of 20 students tend to

Prepared by Page 5 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

cluster. Further, a mean IQ score of 113.1 suggests that on the average, the 20
students have high average IQ.

N.B. On The Wechsler Adult Intelligence Scale and the Stanford-Binet test,
scores that fall between 90 and 109 are high average IQ scores.

Alternatively, the sum in the long expression above can be shortened as

7(035)=0<(007)=>(0<9)
𝑥= ,
3<
where 4, 10, and 105 are the corresponding frequencies of the class interval
with midpoints 123, 114 and 105, respectively.

Generally, the estimated mean of grouped data 𝑥 is given by

∑ JK
𝑥= ,
(
where f is the corresponding frequency of the class interval with midpoint X
and n is the total number of cases.

∑ JK 7(035)=0<(007)=>(0<9) 33>3
Thus, 𝑥= →𝑥= = = 113.1.
( 3< 3<
Therefore, the mean IQ score of 20 students is 113.1.

We can also use the MS Excel for facility in the computation especially when
the distribution table consists of many class intervals.

Example 4:
Compute for the mean of the hypothetical data.

Class Interval f
95 - 99 3
90 - 94 2
85 - 89 1
80 - 84 16
75 - 79 20
70 - 74 12
65 - 69 6
TOTAL 60

Prepared by Page 6 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Step 1: Open a MS Excel spreadsheet and copy the frequency distribution

table.
Step 2: Expand the table by adding
columns for midpoints X and
products of midpoints and
corresponding frequencies of class
intervals fX, as shown below.

L 𝑓𝑋

n
Step 3: Determine the mean using the summary values in the table above.
∑ JK
Recall that 𝑥= . Select a cell then enter the formula.
(

Then press ENTER.

Prepared by Page 7 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Thus, the mean grade of the hypothetical data is 78. By the definition of the
mean, 78 is the value about which the grades of 60 students are clustered.

CHECKPOINT
02 Estimate the mean of the hypothetical data.

Class Interval f
95 - 99 3
90 - 94 2
85 - 89 1
80 - 84 9
75 - 79 20
TOTAL 35

A1.3. WEIGHTED MEAN

You might want to compute your grade point average in a particular semester.
Using the idea which you have just learned for computing the mean may not work.
When will the idea of computing the mean for ungrouped data work? When is it not
going to work?

Example 5:
Consider the grades of Mr. A during Semester 1 below. Compute its mean.

Subject Grade Unit

PE 101 1.6 2.0
Math 101 2.2 4.0
Science 101 with Lab 3.0 4.5
Filipino 101 1.8 3.0
English 101 2.5 3.0
ProfEd101 2.0 3.0
Soc Sci 101 1.9 3.0
NSTP 1 1.6 3.0

If we compute for the mean by simply getting the arithmetic mean of the eight
(8) grades, we obtain a mean grade of 2.10.
However, considering the credit units which varies for each course, we resort
to the most appropriate way of getting the mean. The mean is obtained by adding
the products of the grade per course and its corresponding credit unit and then
dividing the sum by the total number of credit units.

Prepared by Page 8 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

You may do this manually, or with the use of a calculator or any software to
facilitate the computation.
Here is how to do it using the MS Excel.

Step 1: Open a MS Excel spreadsheet and

copy the table.

Step 2: Expand the table by adding a column for products of grades (wX)
and their corresponding credit units (w) for each course, as shown
below.

Step 3: Get the sum of the units (w) and wX, as shown below.

L𝒘 = L 𝒘𝑿 =

Step 4: Finally, divide ∑ 𝑤𝑋 by ∑ 𝑤 to obtain the desired mean. That is,

54.9 ÷ 25.5 = 𝟐. 𝟏𝟓𝟑 .

Thus, the mean grade of Mister A for the Semester 1 is 2.153. This type of
mean is called a weighted mean.
A mean grade of 2.153 indicates that 2. 153 is the value around which the
grades bunch together. Using the LNU’s rating scale, a mean grade of 2. 153
suggests that on the average the academic performance of Mister A defined by his
grades is __________.
In general, the weighted mean ( 𝑥T ) of a set of data (X) with corresponding
weights (w) is given by
∑ TK
𝑥T = ∑T
.

Prepared by Page 9 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

With respect to the previous example, the grades are the data and the credit
units are the weights.
You may have noticed that the arithmetic mean and the weighted mean of the
given data set are different. This is because the arithmetic mean considered each
grade having equal credit units (weights) while the weighted mean considered the
corresponding credit unit (weight) of each course.

The mean of grouped data is also a weighted mean where the frequencies of
class intervals are the weights to be multiplied its corresponding midpoints or class
marks.

The mean is a common measure of central tendency. It is applicable when

the level of measurement of the data is either interval or ratio. One important
characteristic of the mean is that it considers all the values in the data set.
However, because of this, it is also a disadvantage. The mean is susceptible to the
effect caused by extreme values in the data set. Thus, the mean is a less reliable
measure of averages with data sets having extreme values.

A. Below are the grades of Vincenzo in the previous semester.

Compute his mean grade.

Subject Grade Unit

EDUC 103 1.1 3.0
EDUC 104 2.0 4.0
EDUC 105 1.6 3.0
CHECKPOINT
03 EDUC 106 1.1 3.0
EDUC 107 1.4 3.0
EDUC 108 3.0 4.0
PE103 1.9 2.0
PROFED106 1.7 3.0
PROFED107 1.6 3.0

B. Compute for the mean of your grades in the semesters of the

previous year.

Prepared by Page 10 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

A2.1 MEDIAN FOR RAW DATA

The median is the middle value in a data set arranged in either ascending or
descending order. It is the referred to as the middle value when all the values have
been ranked. Because ranking of values in a data set is applied to get the median,
the median is an appropriate measure of central tendency when the level of
measurement of the variable is at least ordinal.

To find the median of a group of values, you follow the steps below.
Step 1. Arrange the data /values / scores in either ascending or descending order.
Step 2. Consider the following cases.
Case 1. The total number (n) of values or scores is odd.
(=0
The median is the W 3
X 𝑡ℎ value or score.

Illustration 1. The median of the scores arranged in ascending order:

2, 4, 7, 8, 12, 15, 20 is 8.
Solution
Because there are 7 scores in the data set, n = 7. Note that 7 is an odd
number. This means that the data set has an odd number scores. And
data set with odd number of values has a middle value or score which is
called the median.
(=0 C=0
So, 3
= 3
= 4 . Thus, the median is in the 4th value, and that is 8.

2, 4, 7, 8, 12, 15, 20
middle score
Now, What does a median of 8 mean?
Because 8 is the median, it is the middle value in the arranged data set
with the same number of scores above and below it. In the case of the
example, 3 scores are above 8 and 3 scores are below 8.

Case 2: The total number of values or score is even.

For a data set with even number of values, there will be two
values in the middle. The median is the mean between these two
(
middle values. That is, the median is the mean of the W 3 X 𝑡ℎ and the
(
W 3 + 1X 𝑡ℎ values.

Illustration 2. The median of the scores arranged in ascending order: 2, 4,

7, 8, 12, 15, 20, 21 is 7.5.

Prepared by Page 11 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Solution
Because there are 8 scores in the data set, n = 8. Note that 8 is an even
number. This means that the data set has two middle scores.
( ? ( ?
So, 3
→ 3 = 4 and 3
+ 1 → 3 + 1 = 4 + 1 = 5. Thus, the median is the

mean between the 4th and the 5th values, which in this case are 8 and 12,
respectively. middle scores
2, 4, 7, 8, 12, 15, 20, 21
The mean between 8 and 12 is 10. Why? Thus, the median is 10.

What does a median of 10 mean?

Because 10 is the median, it is the middle value in the arranged data
set with the same number of scores above and below it. In the case of the
example, 4 scores are above 10, and 4 scores are below 10.

Example 6:
Find the median of the scores of twelve students in a 50–point test.
12, 35, 10, 38, 45, 44, 42, 50, 40, 41, 39, 37

You may follow the steps I have introduced to you to find the median. But for
this example, I will share with you my practice. This I apply especially during
exams or any circumstance when time is limited As a matter of practice, especially
time is limited to determine the median.
Step 1. Determine the number of values/scores in the data set and apply
the formula for locating middle score/s.
It is given in the item that there are 12 scores and 12 is even. So,
( 03
the middle scores are 3 𝑡ℎ → 3
𝑡ℎ = 6𝑡ℎ and
( 03
W 3 + 1X 𝑡ℎ → W 3 + 1X 𝑡ℎ = (6 + 1)𝑡ℎ = 7𝑡ℎ scores.

Thus, the middle scores are the 6th and 7th scores.
Step 2. Arrange the values in increasing order. List the values up to the
middle scores only, instead of writing all the scores in the data set.
10, 12, 35, 37, 38, 39, 40 middle scores

Thus, the median is 39.5 which is the mean of 39 and 40. This
indicates that half of the number of scores are above 39.5 while the other half is
below 39.5. In case this, 6 scores are above 39.5 and 6 scores are below 39.5 when
scores are arranged in increasing order.

Prepared by Page 12 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

While the mean is affected by extreme values in a data set, the median is not.
The median is a more reliable measure of central tendency for data sets which are
skewed. (Skewness will be discussed in the succeeding lesson)
For data sets with large number of values, MS Excel and other software may
be used in finding its median. Let us consider the data at the beginning of our
lesson.

Mathematics Science
95 97 90 66 97 82 83 77 88 94 88 72
87 70 74 76 79 86 96 68 87 68 75 82
65 72 77 76 74 89 91 73 74 78 70 79
71 79 78 83 69 75 72 95 77 92 82 80
85 77 81 89 96 99 79 93 71 75 85 65
68 70 71 94 95 97 73 67 68 69 70 86

Example 7:
Using the data above, find the median of the scores of 36 students in Science.

Step 1. Open a MS Excel spreadsheet and

copy the table.

Step 2. Choose a cell where you want the median to be placed. Enter the
formula =MEDIAN() and place the cursor inside the parenthesis,
then highlight all the values to be included in the computation.

Press ENTER to
show the median.

median

Prepared by Page 13 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Thus, the median of the scores of 36 students is 77.5. This suggests that
77.5 is the middle score. It separates the total number of scores into half. In this
case, 18 scores are above 77.5 and 18 scores are below 77.5.

A. Compute for the median grade of the group of students in

CHECKPOINT
Mathematics.
04
B. In which subject did the group of students obtain a higher
median grade?

A2.2. MEDIAN FOR GROUPED DATA

To compute for the median of grouped data, we shall use the formula below.
Since there is no widely accepted symbol for median, in this material, we shall use
Md to denote median.
&
abc
𝑀𝑑 = 𝐿𝐿 + _ ` J d (𝑤)

where, LL = true lower limit or lower class boundary of the median class
Fb = the sum of frequencies below the median class (or the less
than cumulative frequency (<cf ) directly below the median
class
f = frequency corresponding to the median class
w = class width or class size
n = number of cases
*Note: The explanation on how the formula was derived is not the primary
concern of this course unlike in a Statistics course. So, it will not be discussed here.

Class Interval f
95 - 99 3
Example 8: Compute for the median 90 - 94 2
85 - 89 1
of the hypothetical data below. 80 - 84 16
75 - 79 20
70 - 74 12
65 - 69 6
TOTAL 60

Solution Class Interval f <cf

Step 1. Expand the table 95 - 99 3 60
by adding a column for <cf . 90 - 94 2 57
85 - 89 1 55
80 - 84 16 54
75 - 79 20 38
70 - 74 12 18
65 - 69 6 6

Prepared by Page 14 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Step 2. Determine the median class.

The median class is the class interval containing the median. It is the
class interval containing the value where one-half of the cases or the total
number of values would fall below it.
We note that there are 60 cases and one-half of it is 30,
0 ( ><
that is 3 (𝑛) = 3
→ 5
= 30. Looking at the <cf, 30 is between 18 and 38. So,

the median class is 75 – 79.

median class

Step 3. Determine the quantities required by the formula and substitute

these to the formula to get the median.
Now, considering the median class we have,
LL = 74.5; Fb = 18; f = 20; w=5
So,
& gh
abc a0? 03
𝑀𝑑 = 𝐿𝐿 + _ ` J d (𝑤) → 𝑀𝑑 = 74.5 + f ` 3< i (5) = 74.5 + W3<X (5) = 74.5 + 3 = 77.5

Thus, the median (Md) is 77.5. This indicates that 77.5 is the middle
value where 30 grades/scores are above it and 30 grades/scores are below it.

Let us note that the median is the most appropriate measure of central
tendency when the middlemost score is desired. In addition, it is not affected
by extreme values in the data set.

Consider the IQ levels of 20 students reported as follows.

Compute for their median IQ score.
IQ f
CHECKPOINT
05 119 – 127 4
110 – 118 10
101 – 109 6

Prepared by Page 15 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

A3.1. MODE FOR RAW DATA

Another measure of central tendency is the mode. The mode is defined as the
value or the score that occurs most often in a data set. By its definition, we already
are given the idea how to find it in a given data set. Just like the median, there is
no common symbol for mode. For this material, we shall denote mode with Mo.

Example 9: Below are the ages (in years) of 10 Grade 7 students. What is
the mode of the data set 13, 11.5, 12.5, 11.75, 11.5, 12, 11.5,
13.25, 12, 11

Solution
Step1. Arrange the values in increasing order.
Arranging the ages of the students from the lowest to the highest we
have: 11, 11.5, 11.5, 11.5, 11. 75, 12, 12, 12.5, 13, 13.25.
Step 2. Determine the frequency of each distinct value and the value with
the highest frequency shall be declared as the mode.
From the data set we see that there are 3 students who are 11.5
years old, 2 are 12 years old, and one for each of the other ages. So,
the value that appears most frequently is 11.5.

Thus, the mode of the data set composed of the ages of 10 Grade 7 students is
11.5. This means that the age that appears most frequently in the data set is 11.5.
This indicates that on the average the ten (10) Grade 7 students are 11.5 years old.

Because of its nature, the mode is appropriate when the level of

measurement of the data is nominal. An advantage of the mode is that, it is easily
obtained compared to mean and median. So, when quick answer is needed, use
mode. However, Petilos (n.d.) pointed out some drawbacks related to the use of
mode as a measure of central tendency. Firstly, because the mode drastically
changes from sample to sample, it is the most unstable measure of central
tendency. Second, when all the values in a data set are unique, no mode can be
declared from the data. This is the reason why the mode is recommended only
when the sample is large. Third, there are instances when there are two or more
values that have the same number of occurrences in a data set. These values are
considered the modes of the distribution or data set. Lastly, since there is no
formula that can be manipulated for further analysis of the data, unlike the mean,
the mode is not common in inferential statistics. The mode is called a terminal

Prepared by Page 16 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

statistic for the reason that its usefulness is generally limited to descriptive
statistics.
A distribution that consists of one mode is unimodal. A distribution with two
modes is bimodal. A distribution that has three modes is trimodal. A trimodal
distribution is also considered as multimodal. In fact, a distribution with more than
two modes is multimodal.
MS Excel can also be utilized in finding the mode of a data set.

Example 10.
Grades in Science
Find the mode of the data set 83 77 88 94 88 72
at the right. Describe the 96 68 87 68 75 82
distribution in terms of its 91 73 74 78 70 79
72 95 77 92 82 80
number modes. 79 93 71 75 85 65
73 67 68 69 70 86

Solution
Step 1. Open a MS Excel spreadsheet and
copy the table.

Step 2. Choose a cell where you want the

mode to be placed. Enter the formula =MODE() and place the cursor
inside the parenthesis, then highlight all the values to be included in
the computation.

Press ENTER
to show the
mode.

mode

Prepared by Page 17 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Thus, the mode of the scores of 36 students is 68. This suggests that 68 is
the grade that appears the most number of times in the data set.

A. What is the mode of the data set below?

B. Describe the distribution in terms of its number of modes.

Grades in Mathematics
CHECKPOINT 95 97 90 66 97 82
06 87 70 74 76 79 86
65 72 77 76 74 89
71 79 78 83 69 75
85 77 81 89 96 99
68 70 71 94 95 97

A3.2. MODE FOR GROUPED DATA

For grouped data, a “crude mode” or exact mode may be determined. A
crude mode is an approximate value of the mode while the exact mode is a more
accurate value of the mode. The crude mode is the class mark or midpoint of the
class interval with the highest class frequency, and such class interval is called the
modal class.
To compute for the exact mode, we use the formula
k'
𝑀𝑜 = 𝐿𝐿 + Wk X (𝑤)
' =k`

where, LL = true lower limit or lower boundary of the modal class

d1 = absolute difference between the frequencies of the modal
class and the lower class interval (interval scores lesser than
the mode)
d2 = absolute difference between the frequencies of the modal
class and the higher class interval (interval scores greater
than the mode)
w = class width or class size

Class Interval f
Example 11: Compute for the crude and 95 - 99 3
exact mode of the hypothetical 90 - 94 2
85 - 89 1
data at the right.
80 - 84 16
75 - 79 20
70 - 74 12
65 - 69 6
TOTAL 60

Prepared by Page 18 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

Solution
The crude mode can be obtained by inspection. The modal class is 75 – 79, and
its midpoint is 77. Thus, the crude mode of the distribution is 77.

To find the exact mode, Follow the steps below.

Class Interval f
Step 1. Identify the modal class. 95 - 99 3
A modal class is a class 90 - 94 2
85 - 89 1
interval with the highest
80 - 84 16
frequency. In our case, the 75 - 79 20
modal class is 75 – 79. 70 - 74 12
65 - 69 6
TOTAL 60

Step 2. Find the values of the quantities required in the formula and substitute
k'
these values in the formula, 𝑀𝑜 = 𝐿𝐿 + Wk X (𝑤)
' =k`

With reference to the modal class, LL = 74. 5, d1 = |20 – 12|=8

d2 = |20 – 16|=4, w=5
So,
k' ?
𝑀𝑜 = 𝐿𝐿 + Wk X (𝑤) → 𝑀𝑜 = 74.5 + W?=7X (5) = 74.5 + 3.33 = 77.83
' =k`

Thus, the exact mode of the distribution is 77.83.

Consider the IQ levels of 20 students reported as follows.

IQ f
119 – 127 4
110 – 118 10
CHECKPOINT 101 – 109 6
07

A. Find the crude mode.

B. Compute for the exact mode of the distribution.

Prepared by Page 19 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

The mode of grouped data may be computed also using the “empirical rule”.
This allows us to compute for the value of the mode when the value of the mean and
median are known. The rule is given by the formula,

Mo = 3(median) – 2(mean)

Example 12. Suppose that the median and mean of a grouped data is 77.5
and 78, respectively. Compute the mode of the grouped data
using the empirical rule.

Solution
Given: mean = 78 median = 77.5
So, the mode is
Mo = 3(77.5) – 2(78) = 76.5

Thus, the mode of the grouped data using the empirical rule is 76.5.

Prepared by Page 20 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

REMEMBER THIS!

MEAN is also known as arithmetic average.

Characteristics
• value around which the other values in the data set are clustered
• used when data are interval or ratio and there are no extreme values in
the distribution or data set
• most stable and less variable from sample to sample
• useful in inferential statistics since it can be further manipulated
mathematically
• may be different from the actual values in the data set or distribution
• easily affected by extreme values

MEDIAN is also known as the middle score.

Characteristics
• value in which the number of scores/values above it is equal to the
number of scores or values below it
• used when data are ranks or ordinal and distribution is skewed or there
are extreme values
• less stable from sample to sample
• not affected by extreme values because it is a positional measure
• may not be an actual value in the data set
•
MODE is also known as typical score.
Characteristics
• value that occurs most frequently in the data set/distribution
• used when data are frequency counts and quick estimate of the typical
score is needed
• can be done by ocular inspection
• may not be unique
• interpretation is difficult when the distribution is NOT unimodal
• may not exist at times
• not affected by extreme scores
• most unstable measure especially when the number of values is small

Prepared by Page 21 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

EXERCISES

A. Find the mean, median and mode of the following set of data.
98 90 88 69 86
80 82 96 87 100
84 90 76 78 88
73 71 99 70 74
88 66 68 82 94
82 78 74 81 86
98 74 76 73 68
79 67 74 96 65
83 86 77 79 79
99 72 93 89 96

B. Find the mean, median and mode of the data below.

class interval f
95 - 99 2
90 - 94 3
85 - 89 5
80- 84 6
75 - 79 8
70 -74 13
65 -69 8
60 -64 3
55 - 59 2

C. Explore this!
1. Find the mean of the following scores: 70, 68, 90, 60, 65, 72, 65.
2. Suppose 10 is added to each of the scores, what is the new mean?
3. Compare the mean in #1 and #2.
4. Suppose that the mean of a data set is 57 and 8 is added to each of the
scores in the data set, what is its new mean?

Prepared by Page 22 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

ANSWERS KEY

Checkpoint 01: A. 𝑥 = 78.84

B. Mathematics
Checkpoint 02: 81.14
Checkpoint 03: A. 𝑥 = 1.76
B. Answers will vary.
Checkpoint 04: A. Md = 79
B. Mathematics
Checkpoint 05: Md = 113.1
Checkpoint 06: A. Mo = 97
B. unimodal
Checkpoint 07: A. crude mode = Mo = 114
B. exact mode = Mo = 114.1

EXERCISE A. mean = 82. 02

median = 81. 5
mode = 74

EXERCISE B. mean = 75.7

median = 74.12
mode = 72
EXERCISE C. 1. mean = 70
2. new mean = 80
3. new mean is 10 more than the original mean
4. new mean = 65

Prepared by Page 23 of 24
 UNIT 1: UTILIZATION OF ASSESSMENT DATA

References

Gabuyo, Y. A. and Dy, G. C. (2013). Assessment of Learning II. Rex Book Store,
Inc.

Kubiszyn T. and Borich G. D. (2013). Educational testing and measurement:

classroom application and practice. John Wiley and Sons, Inc.

Levin, Jack A., et al (2017). Elementary Statistics in Social Research, 12th ed. New
York: Pearson Education, Inc.

Measures of Central Tendency. Retrieved April 10, 2021 from

https://statistics.laerd.com/statistical-guides/measures-central-tendency-mean-
mode-median.php

Nitko, A. J. and Brookhart, S. M. (2014). Educational assessment of students, 6th ed.

Pearson Education Limited.

Petilos, Gabino P. (n.d). Statistics: Concepts and Procedures. Unpublished book.

Prepared by Page 24 of 24