UNIT 15 ORGANIZATION AND GRAPHICAL

REPRESENTATION OF DATA
Structure
15.1 Introduction
15.2 Objectives
15.3 Nature of Data
15.4 Organization of Data
15.4.1 Frequency Distribution Table and Its Interpretation

15.5 Graphical Representation of Data

15.5.1 Need of Graphical Representation of Data
15.5.2 Types of Graphical Representations
15.5.3 Graphical Representation of Discrete Variable/ Ungrouped Data
15.5.4 Graphical Representation of Continuous Variable/Grouped Data

15.6 Let Us Sum Up

15.7 Unit End Activities
15.8 References and Bibliography
15.9 Answers to Check Your Progress

15.1 INTRODUCTION
While conducting educational research, statistic is used for analysis of
information draw conclusions or inferences. This process consists of three steps:
observations/collection of data or information, analysis of information/data
analysis and drawing inferences/conclusions. With the help of observations,
we obtain information either in the form of ideas or in numerical form. The
information that is in the form of ideas is qualitative in nature and that is numerical
form is quantitative in nature. Hence, we are likely to get either qualitative or
quantitative data. Qualitative data may either be analysed using qualitative
methods or may be converted into quantitative data through transforming the
ideas into numbers. And the information collected in terms of numerical figures
is known as the data. In this unit we shall discuss about nature methods of
organization and graphical representation of data.

15.2 OBJECTIVES
After going through this unit, you will be able to
• explain nature of data;
• describe the procedure of classification and tabulation of data ;

Note: Few sections of the Unit has been partially taken from Unit-13
‘Tabulation and Graphical Representation of Data’, BES-127 ‘Assessment
for Learning, B.Ed. IGNOU, 2017
279
Data Collection and • present data in frequency tables;
Analysis
• explain the need of graphical representation of data; and
• explain various methods of graphical representation of data like histogram,
pie charts, frequency polygon, cumulative percentage curve.

15.3 NATURE OF DATA

In the previous unit we have discussed about various types of data like primary
or secondary data; quantitative or qualitative data. By now, you may have
understood that quantitative data is collected by using various psychological
tools or tests and the data is in the form of raw scores. For example, if you
ask someone to rate the quality of food offered by a particular restaurant,
the respondent can rate it on the scale of 1 to 5. Say, the respondent rated it
as 5, then the obtained data is raw score. A raw score is simply unaltered
data from a test or observation. You may get a set of raw data which
is a collection of raw scores on the entire tool. Raw data does not have
any meaning by itself or it may not give any proper insight unless it is not
organized or transformed. For example, if a student has secured 45 marks in
physics examination, then 45 is a raw score obtained by that particular student
and the raw data set would be the raw scores obtained by the entire class. The
raw score 45 does not indicate anything like what grade he/she has earned,
what is the position secured in the class. For statistical treatment, we have
to convert raw scores into derived scores. Derived score is the numerical
description of an individual performance in terms of norms and thus helps
to compare performance which is obtained after transforming a raw score.
Common forms of derived scores are Z-score, T Score, Percentile etc. .

Apart from this on the basis of the nature of variable, quantitative data further
could be classified into two types: Continuous Data and Discrete Data.
• Continuous Data: This type data is one which is capable of any degree
of subdivision. Continuous data represents measurement and therefore
their values cannot be counted but they can be measured. The scores
of an intelligence quotient (I.Q.) test, achievement test and height or
weight of a person fall into continuous series. Suppose if you are asked
to measure your height with a meter rule, you might say you are 160 cm
tall. However, if you had a more accurate rule, you might actually find
you are 160.362 cm tall. This gap from 160 cm to 160.362 cm is in a
truly continuous series and the precision of measurement fulfils the gaps.
• Discrete Data: Discrete data is a count that involves only integers. The
discrete values can’t be subdivided into parts. A discrete series exhibit
the real gaps. For instanc, if in a class there are 45 boys and 18 girls, then
you know there is real gap between the two groups. So, this type of data
cannot be measured but it can be counted. The national census is another
example of discrete data.
On the basis of data organisation, data may be treated in two ways
-ungrouped and grouped.

280 • Ungrouped Data: An ungrouped data is basically a list of numbers

 which you first gather from an experiment or research study by using Organization and
research tools. It is raw data, which is not sorted into categories or Graphical representation
of Data
classified, or otherwise grouped. Let us take an example, A teacher
administered achievement test on 20 students. Following are the scores:
25 33 36 28 35 35 25 45 23 20
21 36 45 33 34 35 33 33 45 40
This type of data is called Ungrouped data. This raw data is not giving
any insight to the researcher like who got highest marks or who got lowest
marks or who failed and so on. To get answers into such questions, we
may sort the data into groups or into class intervals.
• Grouped Data: Grouped is the data that has been bundled together in
categories or class intervals. When the sample is small, we normally
analyse the data in ungrouped form and if obtained data is large then it has
to be grouped. Let us understand through an example, Sanjay a science
teacher conducted a unit test for 70 students. If the teacher arranges
marks secured by each student in a serial order, it may be difficult to
identify how many students secured average marks or how many failed
and so on. But if, he converts the marks obtained into class intervals (for
example, students who scored marks in between 0-10, 10-20, 20-30 and
so on), and then represents them in a tabular form then the performance
can be easily recognized. This type of sequential arrangement of data
in a table is called frequency distribution. The term ‘frequency’ refers
to the number of cases or objects in a category or class. Or we can say
that frequency is the number of times a particular data point occurs in
the set of data. For example, suppose 8 students scored marks below 35 in
the term examination, then the ‘8’ represents frequency.

Check Your Progress 1

Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
1. How is derived data different from raw data?
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
2. Differentiate between continuous and discrete data.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
3. Compare between ungrouped and grouped data.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………... 281
Data Collection and
Analysis 15.4 ORGANIZATION OF DATA
Now that you are aware about the importance of organization and classification
of data, let us understand it further. The classification of scores is known as
frequency distribution and a table representing them is known as frequency
distribution table. Generally, the classification of data is done in two forms.
• Ungrouped frequency distribution
• Grouped frequency distribution
1) Ungrouped Frequency Distribution: This type of frequency distribution
is prepared into when you have responses from a small sample, i.e. in which
limited numbers are repeated. At first, the scores are arranged in ascending
or descending order then tallies are marked for each score.

Let us understand through the same example discussed as in the earlier section
15.3 where a teacher administered achievement test to 20 students. Following
are the scores:
25 33 36 28 35 35 25 45 23 20
21 36 45 33 35 35 33 33 45 40

Let us make the frequency distribution table for the above data. Table 15.1
shows frequency distribution table for ungrouped data.
Scores Frequencies
20 1
21 1
23 1
25 2
28 1
33 4
35 4
36 2
40 1
45 3
Table 15.1: Frequency Distribution Table for Ungrouped Data
2) Grouped Frequency Distribution: Grouped frequency distribution is a
table in which total range of data is classified into class intervals of such a
size .Generally, there are two ways to prepare class intervals :
• Exclusive Class Interval
• Inclusive Class Interval
1. Exclusive Class Interval: In an exclusive class-interval, upper scores of
the class-interval are not included in these class-intervals. For example, in
a class interval of 15-20, 20 is an upper score and it be excluded. This upper
score (i.e. 20 ) will be included in the next class-interval.
282
2. Inclusive Class Interval: In an inclusive class-interval, both the lower and Organization and
upper scores are included in class interval. This type is considered to be the Graphical representation
of Data
most convenient method.
Table 15.2 indicates two types of class intervals.

Exclusive Class Interval Inclusive Class Interval

35-40 35-39
30-35 30-34
25-30 25-29
20-25 20-24
15-20 15-19
10-15 10-14
5-10 5-9
0-5 0-4
Table15.2: Types of Class Interval

15.4.1 Frequency Distribution Table and Its Interpretation

To develop the frequency distribution, we need to follow certain procedures and
steps, which are explained below:
1. Calculation of range
2. Calculation of size of class interval
3. Indication of class intervals
4. Putting the tallies
5. Obtaining frequencies
6. Indication of frequency table

So now let us understand it with the help of an example. Following are the
scores obtained by 35 students on an intelligence test and are shown below:
55 62 73 44 67 78 79 90 56 67 78 108
65 69 79 75 98 58 72 85 86 82 97 74
99 103 106 88 100 92 88 56 49 77 42
In order to make the frequency distribution, the following procedures need to
be carried out:
1. Calculation of Range: Range is the difference between the highest score
and the lowest score in the set of data. In the above case ‘108’ is the highest
score and ‘42’ is the lowest score.
Therefore, Range= Highest Score-Lowest score
Range= 108-42=66
2. Calculation of Size of Class Interval: To calculate the size of the class
interval, first finalise the number of classes in which you want to represent
your data. The number of classes will depend on the size of data, larger the
283
Data Collection and data more the number of classes or vice versa. For calculating the size of a
Analysis class interval, you may use the following formula;
Size of the Class Interval=Range/Numbers of classes desired
From the above example, it can be deduced:
(Note: here we decide to take seven classes by observing the size of data)
Size of class interval= 66/7= 9.4≈10
Commonly used size of class intervals is 5 and 10 as they are easier to work
in the calculation.
3. Indication of Class Intervals: Once the size of a class interval is decided,
then the class intervals having the lowest to highest scores are arranged
either in ascending or descending order. So in order to write the class
interval, the lowest score, higher score and size of class interval is used.
If the lowest score is close to term i.e. 10, 15,……30, 35, 40, 45…., the
class interval can be started from these terms rather than actual scores.
In the above case, the lowest score is ‘42’ ( which is near to 40) and size of
class interval is ‘10’ and hence the first class interval would be 40-50. The
next class interval would be 50-60, 60-70 and so on.
4. Putting the Tallies: After the class intervals are arranged, you may start putting
tallies against each class intervals. For this the number of cases occurring in
each class interval is noted and is denoted by using tallies. At this point, the
style of putting tallies is to be paid attention. In order to put tallies, we may
start from 1 and go up to 4, then after the fifth tally we mark it by drawing
diagonal line as shown below. In the above example, the number of cases
appearing in each class interval is represented using tallies as shown below:

Tally 1 Tally 2 Tally 3 Tally 4 Tally 5

I II III IIII
5. Obtaining Frequencies: The marked tallies are counted separately for
each class interval. In this example, the total number of tallies against each
class interval is given below in table 15.3 :
6. Indication of Frequency Table: The final step is to check the total number
of tallies to get the total number of cases, ‘N’. This is found out by adding
all the frequencies. In this case, the total frequency (∑f) is 35, wherein ‘∑’
stands for summation and ‘f’ for frequency. Final frequency table is shown
below in table 15.3.

Class-Interval (x) Tallies Frequencies(f)

100-110 IIII 4
90-100 5
80-90 5
70-80 IIII 9
60-70 5
50-60 IIII 4
40-50 III 3

284 N= ∑f=35
Table 15.3 : Frequency Distribution Table
On the basis of the frequency distribution table one can say that 19 students Organization and
have an average I.Q level (i.e. 60-70, 70-80, 80-90) whereas only 4 students Graphical representation
of Data
have very high I.Q. (i.e.100-110).

Activity 1
Analyze the frequency distribution table 15.3. Note down the interpretation
that can be made out of it.
………………………………………………………………………………
……………………………………………………………………………......
……………………………………………………………………………......

Check Your Progress 2

Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
4. Enumerate the ways for preparing class intervals.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
5. Discuss the steps involved in development of frequency distribution
table.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...

15.5 GRAPHICAL REPRESENTATION OF DATA

Many a times, numerical data is complex and difficult to interpret and
understand. For example, in the above case, the marks scored by students have
been converted into frequency distribution. But at times frequency distribution
may not serve the purpose as it is not visually appealing and is complex. So, a
more interesting and attractive kind of representation came into practice and
that is the graphical form of data representation. In graphical representation
the data is represented as geometric figures which can be easily interpreted and
understood by anyone. But the geometric picture needs to be drawn keeping into
account the proportion and measurements of data. Thus, it is possible to visualize
and transform numerical data to picture or graphic format drawn considering a
reasonable proportion. Graph represents the numerical data in geometric figures
drawn on scales.

15.5.1 Need of Graphical Representation of Data

The graphical representation is important due to the following reasons:
• Graphical representations are attractive.
• It helps in easy visualisation.
285
Data Collection and • It facilitates trouble-free interpretation and judgements.
Analysis
• It gives a bird’s eye view of the entire data.
• It is easy to construct.

You may notice that, although we said graph is a form of pictorial/diagrammatic

representation, these two are different. Now let us look at the major differences
between graph and diagram in figure 15.1.

Figure 15.1: Major Differences between Graph and Diagram

When a researcher aspires to convert his/her data into graphical format, he/she
needs to keep in mind the following points:
1. Draw two perpendicular lines. The point where two lines intersect is called
‘origin’ and is represented using ‘0’ (zero).
2. The horizontal line is called ‘X’ axis. The ‘x-axis is called abscissa(base).
3. The vertical line is called ‘Y’ axis. The y-axis is called ordinate (height).
4. The ordinate/height of the graph must be 75% of the abscissa/base. This is
called 75% rule. But there is flexibility to dilate between 60% to 80%.
5. The graph generally has four quadrants as shown in figure 15.2. But
educationists/psychologists usually use the (++) quadrants to utilize
maximum space of the graph paper.

Figure 15.2: Drawing a Graph

15.5.2 Types of Graphical Representations
After having an understanding about the concept of graphical representation Let
us now discuss various types of graphical representation. It is based on the type
of data available for the presentation. You may have various types of graphical
286
representations for continuous and discrete variable. Organization and
Graphical representation
1) Discrete variable in which nominal data are obtained. This type of ungrouped of Data
data is presented by the following graphical presentations:
i. Bar Graph or Bar Diagram
ii. Circle Or Pie Graphs/Diagram
iii. Line Graph
2) Continuous variable is one in which frequency distribution tables are
prepared or data can be organised into class intervals. This type of grouped
data is used in the following graphical presentation:
i. Histogram or Column diagram
ii. Frequency Polygon
iii. Cumulative Frequency Graph
iv. Cumulative Frequency Percentage Curve or Ogive

Check Your Progress 3

Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
6. Write any four importance of graphical representation of data.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
7. Write any three differences between graphs and diagram.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...

15.5.3 Graphical Representation of Discrete Variable/ Ungrouped

Data
Usually, we use Line, Bar and Pie graphs are used for discrete data. Discrete
data cannot be organized into class intervals, Since, it is available in the form
of raw score it is called ungrouped data. Line, bar and pie graphs are used for
analyzing pattern, trends and for comparison purpose. Now let us discuss about
line, bar and pie graph graphs in details.
1. Bar Graph

By now, you know that the data for discrete variable are obtained on nominal
scale or in terms of frequency rather than score. The frequencies are presented
in the form of bar diagram, (rectangles with similar width) as used in bar graphs.
You usually get the data in the form of frequencies, when you collect data by
using a questionnaire, interview techniques or a rating scale. The following are
287
Data Collection and the steps used for constructing a bar graph:
Analysis
• Select x-axis and y- axis on the graph paper. Generally, the x axis is the
horizontal line and y-axis is the vertical line in the graph.
• The intersection of the x-axis and y-axis is the origin (marked as ‘0’) of the
graph.
• Choose a convenient scale for both the axis’s.
• Mark the corresponding values against each variable on x-axis and y-axis
and draw them as bars having equal widths.

Let us discuss here with an example and apply these steps to draw the bar graph.
Consider a school, having the following number of girls in various sections of
a particular grade:

S.No Class No. of Girls

1 8A 25
2 8B 20
3 8C 30
5 8D 15
6 8E 10

Here, the number of girls studying in various sections of grade eighth is given.
In order to draw bar graph, number of girl students is taken on the y-axis and the
corresponding grades are selected on the x axis. The resulting bar graph is given
below in figure 15.3:

Figure 15.3: Bar Graph Showing Number of Girls Per Section

The next question is to how to interpret the bar graph. In this case, we can say
that, the class 8C has greatest number of girls compared to rest of the classes
and 8E has the least number of girls. What else can we infer? The difference in
number of girls among classes 8E and 8C is 20. There are many more inferences
that you can draw from the bar graph. Why don’t you try it as an activity?
288
 Organization and
Activity 2 Graphical representation
of Data
Draw other inferences from the bar-graph other than the ones already
drawn above.

.....................................................................................................................

.....................................................................................................................

.....................................................................................................................

Let’s take another example. A researcher conducted a study on students’

perception towards various modes of teaching -learning. He/she administered a
questionnaire to 200 higher secondary school students. Following data received
on students’ perception on various mode of learning.

Modes of Teaching -Learning F2F Distance Online Blended

Rural Area Students 120 37 12 31

Urban Area Students 72 33 36 59

To represent the data given in the above example in a bar graph, we select
two axes on the graph paper. Against the x-axis ‘modes of learning’ and y-axis,
‘number of students (rural and urban areas)’ are marked. The resulting bar graph
is given below:

Figure 15. 4 : Bar Graph Showing Students Preferences on Teaching-

Learning Modes

On the basis of this graph, we can say that face-to-face mode (f2f) is more
preferred by rural area students as compared to urban area students. Whereas
online mode is more preferred by urban area students as compared to rural area
students.
289
Data Collection and
Analysis Activity 3
In figure 15.4, bar graph shows students preference on various teaching-
leaning mode. Analyze the graph and draw inference other than the ones
that is already discussed.

.....................................................................................................................

.....................................................................................................................

.....................................................................................................................

2. Circle or Pie Graphs/Diagram

Another device for presenting a discrete data is the pie-diagram. The pie-
diagram/pie graph is known as circle graph as we represent the statistical
data as a circular figure considering weightage given to the proportions of
data. The percentage is shown by circle in terms of angle. The angle of a
circle at the center is 3600, which is converted into percentage i.e. 360 is
equal to 10 percent and 1 percent is equal to 3.600 . The circle is shown for
100 frequency of a set of data. To construct a pie-diagram one should have
the knowledge of angle measurements and percentages. Let us understand it
with the help of an example.

Example: In a school, 180 students appeared in the higher secondary

examination. 25 students failed, 35 passed in first division, 65 in second
division and 55 in third division.

Let us try to put these details into a pie-diagram. To do so, you should have
the knowledge that the value of a circle is 2π (2 pie). 2π is equal to 2×1800
= 3600.Thus, the whole circle represents 3600. . Thus, we will represent the
total sample i.e. 180 through a circle having 3600. Let us see how it is done.

Angle for I division = (360X35)/180 = 70o

Angle for II division = (360X65)/180 = 130o

Angle for III division = (360X55)/180 = 110o

Angle for fail = (360X25)/180 = 50o

Type of Result I II III Fail Total

Division Division Division
In Frequency 35 65 55 25 180
In Degree of 70 130 110 50 360
angles

In this way a scale for pie diagram is prepared. Now it is very easy to divide a
circle into degrees to shown result in the visual presentation. The pie-diagram
is shown in figure 15.5:
290
 Organization and
Graphical representation
of Data

Figure 15.5 : Pie Graph

The pie diagram indicates that the second division and third division students
are approximately equal. Whereas first division and failed students are also
approximately equal. Pie diagram is easily understandable but is relatively
difficult to prepare as it is a geometric figure.
Check Your Progress 4
Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
8. What is bar- graph.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
9. What is pie-graph? Describe the procedure for preparing pie-graph.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
10. Develop pie-graph and bar graph for the following data. Which one you
find most suitable for the following data and why?
S.No Year No of Students of Students Passed
in Class 12th
1 2017 700
2 2018 820
3 2019 600
4 2020 500
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
.…………………………………………………………………………...
291
Data Collection and 3. Line Graphs
Analysis
Line graphs are one of the common mode of representation of statistical data.
A line graph is commonly used to display change over time as a series of data
points connected by straight line segments on two axes. The line graph therefore
helps to determine the relationship between two sets of values, with one data set
always being dependent on the other set. The data pertaining to the variables will
be marked on two axes namely the x-axis and y-axis by choosing appropriate
scales. Let us illustrate line graph through an example. Below, are given the
details of absentees in a particular class.

Day Mon Tue Wed Thu Fri Sat

Absentees
2 5 3 7 1 4

Table 15.4 : Data for Line Graph

To represent the data given in the table 15.4 in a line graph, we select two axes
on the graph paper. Against the x-axis ‘day’ and y axis, ‘absentees’ are marked.
After that, appropriate scale is decided. In this case, as the number of absentees
ranges from 1 to 7, we may choose I square of the graph as 1 along y-axis.
Similarly against x-axis, each square can be chosen as a day. Then after, the
data of absentees pertaining to each day are marked. The resulting line graph is
given below:

Figure 15.6 : Line Graph Showing Absentees in a School

Line graphs are useful in that they show data variables and trends very clearly
and can help to make predictions about the results of data not yet recorded. They
can also be used to display several dependent variables against one independent
variable. So, more than one line will be drawn. To get better understanding let’s
take an example.

Example: Discipline wise pass percentage of result of high school are as follows
(results is given in pass percentage):
Year Humanities Science Commerce
2017 56 78 70
2018 58 80 90
2019 59 85 72
292
 Organization and
2020 60 89 98 Graphical representation
2021 61 90 76 of Data

In the sample results are recorded year wise in different disciplines. There are
three disciplines in the school, therefore three lines are drawn.The resulting line
graph is given below in figures 15.7

Figure 15.7: Line Graph for Discipline Wise Result of High

School Passed Students

This presentation indicates that there is a progressive trend in science results

while in humanities result have an upward trend. There is a great fluctuation in
the results of commerce students as shown by the visual presentation of the data.
Check Your Progress 5
Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
11. What is a line -graph? Higher secondary exams results of a school
are given in the following table ( results is given in pass percentage).
Develop a line-graph.

S.No Year No of Students of Students Passed

in Class 12th
1 2017 89
2 2018 92
3 2019 94
4 2020 98
5 2021 99

15.5.4 Graphical Representation of Continuous Variable/Grouped

Data
Continuous variable is one that is organized in frequency table and class interval.
It is called grouped data. The graphical presentation - histogram, frequency
polygon and ogive are prepared for continues data/grouped data. Let us discuss
the procedure for each of them.
293
Data Collection and 1. Histogram or Column Diagram
Analysis
We have studied the bar graph and the process followed in constructing
them. Histogram is essentially a bar graph of a frequency distribution. Bar
graph is used for discrete data but histogram is used for continuous data
where the statistical data is arranged in class intervals. Here, the frequency
is represented using vertical adjacent rectangles. Generally, the class
interval is depicted on ‘x’ axis and frequency on ‘y’ axis. Thus, the base
of the rectangle represents the class interval and height its frequency. You
may conclude that histogram is the graphical representation of grouped
data in the form of vertical bars (equal width) whose area is proportional
to the frequency represented. It is to be noted that, histograms cannot be
constructed with open end classes.
Now, let us discuss the process followed in the construction of a histogram.
For that, the data is given in the Table 15.5.

Class Interval Frequency(f) Limits

30-34 8 29.5-34.5
25-29 5 24.5-29.5
20-24 3 19.5-24.5
15-19 6 14.5-19.5
10-14 2 9.5-14.5
5-9 3 4.5-9.5

Table 15.5 : Data for Histogram

To construct a histogram using the frequency distribution given above the

following process is followed.

• First the limits of the class intervals are calculated. To compute limits,
both lower limit and upper limit of each class interval is found out. For
example, the lower and upper the limits of class interval 5-9 is 4.5 and
9.5 respectively and the class interval is written as 4.5-9.5.
• The lower limit and upper limits are plotted on the x-axis
• The frequencies are plotted on the y-axis.
• Thereafter, each class interval is depicted using adjacent rectangular
bars of equal width.
• Keep in mind to select appropriate scales for both x-axis and y-axis.
• While constructing a histogram, 75% rule is followed i.e. the height of
the figure should be approximately 75% of its width.

The histogram for the above frequency distribution is presented in

Figure15.8 :

294
 Organization and
Graphical representation
of Data

Figure 15.8 : Histogram

2. Frequency Polygon

Frequency polygon is a line graph representation of statistical data/frequency

distribution. It is a closed figure with many sides. To construct a frequency
polygon, the mid points of histogram are joined together and the two end sides
are connected to the base line(x axis). As the end points are touching each other
than they form a closed figure and hence the name frequency polygon. Now,
let us look at steps followed in construction of a frequency polygon using the
same data discussed in the previous section. The same data is reproduced in
Table-15.6.

Class Interval Frequency(f) X(Mid -Point)

30-34 8 32
25-29 5 27
20-24 3 22
15-19 6 17
10-14 2 12
5-9 3 7
Table 15.6 : Data for Frequency Polygon
• To draw a frequency polygon, first of all, the mid points of class interval are
found out and are represented using the letter ‘X’.
• The mid points of class intervals are represented on x -axis.
• The frequency of class intervals are indicated on y- axis
• Then the corresponding frequency is plotted against each midpoint in the
graph and is connected using straight lines.
• Finally, the start point and end point of the frequency polygon are connected
to ‘0’ on the x- axis. This can be achieved by adding a lower limit and higher
limit (add an extra class interval at the lower/higher limit). This helps to
construct a closed polygon.

The frequency polygon for the given frequency distribution( Ref:table15.6) is

given in figure-15.9. 295
Data Collection and
Analysis

Figure 15.9 : Frequency Polygon

The histogram and frequency polygon are constructed on same

graph on same scale. The area covered by histogram and polygon
is equal. Mid points of bars of histogram is joined and its ends are
also joined to the axis by adding one class interval at upper end
and at lower end of the distribution.

3. Cumulative Frequency Graph

Another method of representing grouped and continuous data is through

cumulative frequencies. In cumulative frequency graph, the frequencies are
added and the resulting cumulative frequencies are plotted in the graph. Let us
represent the data given in table 15.7 in a cumulative frequency graph.

Class Interval Frequency(f) Upper Limit Cumulative

Frequency
30-34 8 34.5 24
25-29 5 29.5 16
20-24 3 24.5 11
15-19 6 19.5 8
10-14 2 14.5 2
5-9 0 9.5 0
( Extra Class Interval)

Table 15.7: Data for Cumulative Frequency Graph

To draw the cumulative frequency graph, an extra class interval is added at
the lowest limit whose frequency is 0. Thereafter, the frequencies are added
and thus the cumulative frequencies are found out. Then these frequencies are
represented on the graph. The final frequency polygon is given in Figure-15.10.
296
 Organization and
Graphical representation
of Data

Figure 15.10 : Cumulative Frequency Graph

4. Cumulative Frequency Percentage Curve or Ogive.

Cumulative Frequency Percentage Curve or Ogive is drawn by following

similar procedure used for drawing cumulative frequency graph. But an extra
step is followed. Here the cumulative frequencies are expressed in terms of
cumulative percentages. Thus, cumulative frequency percentage graph is a form
of representation of statistical data in terms of cumulative percentages. Let us
take the example given above and draw the corresponding cumulative frequency
percentage graph.

Class Interval Frequency(f) Upper Cumulative % of

(N=24) Limit Frequency Cumulative
Frequency
30-34 8 34.5 24 100

25-29 5 29.5 16 66

20-24 3 24.5 11 45

15-19 6 19.5 8 33

10-14 2 14.5 2 8
5-9 0 9.5 0 0
( Extra Class
Interval)

Table 15.8 : Data for Ogive

297
Data Collection and
Analysis

Figure 15.11 : Ogive

Check Your Progress 6

Note: a) Write your answers in the space given below.
b) Compare your answers with those given at the end of the Unit.
12. Write the differences between bar graph and histogram.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
……………………………………………………………………………
13. Differentiate between frequency polygon and histogram.
…………………………………………………………………………
…………………………………………………………………………
……………………………………………………………………….…..
……………………………………………………………………………

15.6 LET US SUM UP

In this unit you have studied about the nature of data, methods of organization
of data, various types of graphs for data organization and presentation of data.
It was already explained to you that in educational researches, statistic is used
to collect, organize and interpret data. Data can be categorized a number of
ways i.e. quantitative and qualitative data, raw and derived scores, continuous
and discrete data, grouped and ungrouped data. When data is arranged into
class intervals with frequency, is called grouped data. The arrangement of data
in a table in a sequential manner is called frequency distribution. The term
‘frequency’ refers to the number of cases or objects in a category or class. To
develop the frequency distribution, we need to follow certain procedures and
steps like: calculation of range, decide the number of class interval, calculation
of size of class interval, indication of class intervals, putting tallies, totalling the
number of tallies and checking the number of frequencies.

298 Data can be presented with the help of graphical presentations. The graphical
presentation catches one’s eye and holds the attention when most careful Organization and
statistical analysis fails to reveal the nature of distribution. There are various Graphical representation
of Data
types of graphical representation for discrete/ ungrouped data and continuous/
grouped data. Discrete data cannot be organized into class intervals and data
in the form of raw score is called ungrouped data. Line, bar and pie graphs
are used for presenting discrete data. These graphical presentations are used
for analyzing patterns, trends and comparison purposes. Histogram, frequency
polygon and ogive are prepared for continuous data/ungrouped data.

15.7 UNIT END ACTIVITIES

1. On a creativity test 35 students have scored the following marks Prepare
frequency distribution table for on 5 size of class-interval.:
67 76 54 22 67 45 48 56 85 55 74
73 59 46 29 40 25 44 77 54 66 27
74 23 55 65 73 83 88 44 38 39 68
44 56
2. Indicate the need and importance of graphical presentation in statistical
treatment. Enumerate kinds of graphical presentations.
3. Prepare bar diagram for the following data.
Result CBSE MP Board UP Board AP Board
Pass 83 78 68 95
Fail 17 12 32 5
4. Differentiate between frequency polygon and histogram. Prepare a
histogram, frequency polygon, cumulative frequency polygon and
cumulative percentage frequency polygon for the following distribution .
X 10-14 15-19 20-24 25-29 30-34 35-39 40-44
f 2 5 6 9 5 4 3

15.8 REFERENCES AND BIBLIOGRAPHY

• Best. J. W. (1977). Research in Education. Englewood Cliffs, New Jersey:
Prentice Hall Inc.
• Garrett, H. E. (1956). Elementary Statistics. Longmans, Green and Co.,
New York.
• Guilford, J. P. (1965). Fundamental Statistics in Psychology and Education.
McGraw Hill Book Company, New York.
• Hannagan, T. J. (1982). Mastering Statistics, The Macmillan Press Ltd.,
Surrey.
• IGNOU (2017). ‘Tabulation and Graphical Representation of Data’ in
‘Analyzing and Interpreting Learner’s Performance’ (Block-4). BES-128
:Assessment for Learning .New Delhi
• Lindgren, B. W. (1975). Basic Ideas of Statistics, Macmillan Publishing
Co. Inc., New York. 299
Data Collection and • Tate, M. W. (1955). Statistics in Education, The Macmillan Company, New
Analysis York.

15.9 ANSWERS TO CHECK YOUR PROGRESS

1) A raw score is simply unaltered data from a test or observation and derived
score is the numerical description of an individual performance in terms
of norms and thus help to compare performance which is obtained after
transforming a raw score.

2) Continuous data is one which is capable of any degree of subdivision.

Continuous data represents measurement and therefore their values cannot
be counted but they can be measured. Discrete data is a count that involves
only integers. The discrete values can’t be subdivided into parts. A discrete
series exhibit the real gaps.

3) An ungrouped data is basically a list of numbers which you first gather

from an experiment or research study using research tools. Grouped is the
data that has been bundled together in or class intervals. When the sample
is small, we normally analyze the data in ungrouped form and if obtained
data is large then it has to be grouped.

4) Steps for development of frequency distribution table:

• Calculation of range
• Calculation of size of class interval
• Indication of class intervals
• Putting tallies
• Totalling the number of tallies
• Checking the number of frequencies

5) In an exclusive class- interval, upper scores of the class-interval are not

included in these class-interval. For example, in a class interval of 15-20,
20 is a upper score and it can be excluded. This upper score (i.e. 20 ) will
be included in the next class- interval. In an inclusive class-interval, both
the lower and upper scores are included in class interval. This is the most
convenient method.

6) The graphical representation is important due to the following reasons:

• Graphical representations are attractive and beautiful.
• It helps easy visualisation.
• It facilitates trouble-free interpretation and judgements.
• It gives a bird’s eye view of the entire data.
• It is easy to construct.

300
7) Organization and
Graphical representation
of Data
Graph Diagram
• Constructed on graph paper. • Constructed on plain/normal
paper.
• Generally used by researchers for
research purposes. • Generally used for publicity
• It is drawn on two axes. • There is no restriction of axis
• Does not have many dimensions • Has many choices and is
as it is independent of choices independent

8) Data for discrete variable are obtained on nominal scale or in terms of

frequency rather than score. The frequencies are presented in the form of
bar diagram, (rectangles with similar width) as used in bar graphs.
9) The pie-diagram/pie graph is known as circle graph as we represent the
statistical data as a circular figure considering weightage given to the
proportions of data. The percentage are shown of circle in terms of angle.
The angle of a circle at the center is 3600, which is converted into percentage
i.e. 360 is equal to 10 percent and 1 percent is equal to 3.600. The circle is
shown for 100 frequency of a set of data.
10) Self-exercise
11) Line graphs are one of the common mode of representation of statistical
data. A line graph is commonly used to display change over time; as a series
of data points connected by straight line segments on two axes. The line
graph therefore helps to determine the relationship between two sets of
values, with one data set always being dependent on the other set.
12) Histogram is essentially a bar graph of a frequency distribution. Bar graph
is used for discrete data but histogram is used for continuous data where the
statistical data is arranged in class intervals.
13) Frequency polygon is a line graph representation of statistical data/
frequency distribution. It is a closed figure with many sides. To construct
a frequency polygon, the mid points of histogram are joined together and
the two end sides are connected to the base line (x axis). As the end points
are touching each other then they form a closed figure and hence the name
frequency polygon.

301