Diagrams

and Graphs

By:
Prajeet K. Timalsina
rd
Norvic Business College (3 Sem)
Introduction
• One of the most convincing and appealing ways in which statistical results may be presented is through diagrams and
graphs.
• Evidence of this can be found in newspapers, magazines, journals, advertisements, etc.
• There are numerous ways in which statistical data may be displayed pictorially such as different types of diagrams,
graphs and maps. Very often the problem is that of selecting the best out of several methods that may be available.
• This is a difficult task and requires a great deal of artistic talent and imagination on the part of the individual or
agency engaged in the preparation of diagrams and graphs.
• It is not practicable to discuss all the possible forms of charts here. An attempt is made in this chapter to illustrate
some of the major types of diagrams, graphs and maps frequently used in presenting statistical data.

DIAGRAMMATIC PRESENTATION OF DATA

Diagrammatic presentation of data is a technique of presenting the data visually in the form of diagrams.

Significance of Diagrammatic Presentation

Diagrams and graphs are extremely useful because of the following reasons:
1. Diagrammatic presentation of data eliminates the dullness of numerical data.
2. It gives bird's eye – view of the whole mass statistical data that have been collected about any problem.
3. It makes the comparison of data much easier.
4. It helps in establishing trends of the past performance.
5. It makes it possible to determine the values of the positional averages such an median, quartiles, mode etc.
6. It creates on the mind of an observer a long lasting impression of the relative magnitude of the numerical values
which can be easily remembered.
 Limitations of Diagrammatic Presentation
The diagrammatic presentation of data has the following limitations:

1. Diagrams provide only an approximate idea and as such where greater accuracy is needed diagrams will not be suitable.
2. It is very difficult to show the minor differences through diagrams.
3. Diagrams cannot show so many facts as a statistical table can show.
4. It is more difficult to understand two or three dimensional diagrams than the facts contained in a statistical table.

TYPES OF DIAGRAMS

Types of Diagrams

One Dimensional Two Dimensional

Diagrams Diagrams

 Simple Bar Diagrams 

Pie Diagram or Pie-Chart

Sub-divided Bar Diagrams

Percentage Bar Diagrams

Multiple Bar Diagrams
ONE DIMENSIONAL DIAGRAM
One dimensional diagram is a diagram which is prepared on the basis of only one dimension i.e. length. This type of diagram
takes the shape of bars. It may be noted that even though bar locks like a rectangle, it is not a rectangle because in a
rectangle both length and width are significant.

TWO DIMENSIONAL DIAGRAMS

Two dimensional diagram is a diagram which is prepared on the basis of two dimensions i.e. length and width. As the
product of length and width indicates the area, this type of diagram is also called area diagram. Pie-diagram (i.e Pie-chart) is
mainly used to show two dimensional diagram.

Simple Bar Diagrams

• Simple bar diagram is a one dimensional diagram in which bar is constructed to represent one value of a given variable.
• The length of various bars is in the ratio of the magnitude of the given data.
• As the width of the bars is not significant, width is uniform for all bars.
• It is generally prepared when the data indicates different values of a variable over a time period or when the data
represents different situations.
• Identical gap is left in between the different bars.
• The bars can be prepared either vertically or horizontally.
ILLUSTRATION 1
You are given the information regarding Human Poverty Index (HPI) of SAARC countries. Show the data using Simple Bar
Diagarm.

Country HPI Country HPI

Nepal 50.5 Pakistan 55.2

India 45.8 Sri Lanka 35.8

Bhutan 20.7 Bangladesh 60.3

Maldives 40.3 Afghanistan 48.5

Solution:
Simple Bar Diagram Showing HPI of Countries.

Y
70

60 60.3
55.2
50
50.5 48.5
Human Poverty Index

40 45.8 40.3

30 35.8

20
20.7
10

Banglades

Afganistan
Pakistan

Srilanka
Bhutan
Nepal

Maldives
India

Country
 Sub-divided Bar Diagram / Component Bar Diagram
• Simple Bar Diagram is useful to represent only one feature of variable at a time.
• But, there are some conditions when two or more features of variable have to be presented at a time, then sub-
divided bar diagram is considered as suitable approach.

Note: Cumulative table of variable should be constructed to draw sub-divided bar diagram.
ILLUSTRATION 2

Represent the data by means of sub-divided bar diagram;

Cost per scooter (in Rs.)

Particulars
2005 2008

Raw Materials 4000 8000

Labours 6000 12000

Indirect Expenses 3000 7000

Other Expenses 2000 3000

15000 30000
 Solution:
Cumulative Table

Particular 2005 2008

Cost (Rs) Cum. Cost (Rs) Cost (Rs) Cum. Cost (Rs)
Raw Material 4000 4000 8000 8000

Labour 6000 10000 12000 20000

Indirect Expenses 3000 13000 7000 27000

Other Expenses 2000 15000 1000 30000
15000 30000

Sub-divided bar diagram

Indicators:
Y Other Expenses
Indirect Expenses
35000
Labour
30000
Raw Materials

25000
Cumulative Cost

20000

15000

10000

5000

O X
2005 2008
Year

Percentage Bar Diagram

• If sub-divided bar diagram is expressed in percentage, then it is known as percentage bar diagram.
 • For this, cumulative percentage table should be constructed.

ILLUSTRATION 3
Represent the following by sub-divided bar diagram on the basis of percentage;

Years
Particular
2002 2005 2008

1. Cost per unit

Wages 9 15 21

Materials 6 10 14

Overheads 3 5 7

Total Cost per unit 18 30 42

2. Sales Revenue per unit 20 30 40

3. Profit/Loss per unit 2 - (2)

Solution:
Form the table above, We can draw four components Viz: wages, matrials, overheads and profit or loss to construct
percentage bar diagram.
Computation Table
2002 2005 2008
 Particulars Cost Cum. % of Cost Cum % of Cum. Cost Cum. % of Cum
Cost Cum. cost Cost Cost cost Cost
Profit/Loss 2 2 10% - - - (2) (2) -5%
Wages 9 11 55% 15 15 50% 21 19 47.5%
Materials 6 17 85% 10 25 83.33% 14 33 82.5%
Overheads 3 20 100% 5 30 100% 7 40 100%
20 30 40

Percentage Bar Diagram:

Indicators:
Multiple Bar Diagram
• Multiple Bar Diagram is one dimensional diagram in which two or more bars adjoining each other are constructed to
represent the values of different variables or the values of various components of the same variable.
• Identical gap is left in between the bars of different sets. This diagram, facilitates comparison of the values of different
variables in a set and comparison of the values of the same variable over a period of time.
• If simple bar diagram is represented with two or more sets of inter-related data, then it is known as multiple bar diagram.

ILLUSTRATION 4
Construct multiple bar diagram to represent the data given below:
No. of students passed in
Year
1st Division 2nd Division 3rd Division
2002 20 60 80
2003 30 75 110
2004 40 100 90
Solution:
Multiple bar diagram showing passed no. of students.

120

100

80
of Students

60 1st Division
2nd Division
3rd Division
No.

40

20
 0
2002 2003 2004
Year

Pie-Diagram
• Pie diagram is a circular diagram whose area is proportionately divided among the various components of
a given variable.
• Under this, the circle is divided into different segments by radial lines (radius).
• In order to construct, the pie-chart, the given values are centered into the angles.
• So, it is also known as angular diagram.
• The total magnitude of segments of a set is considered to be equal to 360 o and the corresponding angle
at the centre for each segment should be calculated accordingly.
360o
Angle at the centre for one unit of an item = Total value
Note: Loss or deficit cannot be shown in pie-chart

ILLUSTRATION 5
The asset holding of commercial banks in 1990 is given as follows.
Represent the data into pie-chart.

Commercial Banks Asset Holdings (Rs. in Billions)

NBL 129
RBB 96
NABIL 13
INDOS 8
GRND 12
ADB 46

Solution:
Total assets holding = 129 + 96 + 13 + 8 + 12 + 46 = Rs. 304 billions
Taking Rs.304 billions = 3600
3600

 Rs. 1 billion = 304 = 1.180

Computation Table
Commercial Asset Holdings Angle at centre
Banks (Rs. in billions) (1.180 × Assets Holdings)
NBL 129 1.180× 129 = 1530
RBB 96 1.180× 96 = 1140
NABIL 13 1.180× 13 = 150
INDOS 8 1.180× 8 = 90
GRND 12 1.180× 12 = 140
ADB 46 1.180× 46 = 540
Pie-Diagram of asset holding of commercial banks in 1990

NBl

RRB

NABIL

INDOS

GRAND
 ADB

ILLUSTRATION 6
Construct the pie-diagram for the following data:

Population
Components Districts
1991 2001

Dolpa 25013 22071

Jumla 75964 69226

Mugu 36364 31465
 Solution:
Value of the item
In a pie-diagram, Angle at the centre = x 3600
Total value
Calculation of Angle at the centre

1991 2001
Districts
Population Angle at center Population Angle at center

Dolpa 25013 65.560 22071 64.720

Jumla 75964 199.120 69226 203.010
Mugu 36364 95.320 31465 92.270

Total 137341 3600 122762 3600

Square root 370.60 - 350.37 -

Radii 1.06 - 1 -

Pie Diagram of population in 1991 and 2001

Indicators
Dolpa
Mugu

Jumla

1991
By: Prajeet K. Timalsina 2001
CHOICE OF DIAGRAM
No single method is suitable for all types of data and there is no any hard and fast rule to select a suitable
diagram. It depends upon the situation and nature of data. But even, following suggestions are
recommended for selecting a suitable diagram, when the question is silent.

a) If only one attribute of a variable is to be shown in diagram, then simple bar diagram is
suitable.
b) If more than one attributes of a variable are to be shown in diagram, then sub-divided bar diagram
is suitable but when there is negative figure (i.e. loss or deficit), then percentage bar diagram is
more appropriate.
c) When a comparison between two or more interrelated variables are to be shown in
diagram, then multiple bar diagram is suitable.
d) If there is loss a deficit and more than 6 characteristics of a variable, then pie-chart should
not be constructed.

GRAPHICAL PRESENTATION OF DATA

• Graphical presentation of data is a technique of presenting the data visually in the form of graph.
• This method provides the quickest understanding of the actual situation to be explained by data in
comparison to tabular or textual preventions.
• It eliminates the dullness of the numerical data.
• It presents the data in a more impressive manner.

• Comparison of data is much easier if it is presented in the form of diagram and graphs.

Importance of Graphical Presentation of Data

 The technique of graph offers numerous advantages to the users.
Some of the major advantages are listed as under:
1. The graph presents the data in such a fashion, that it is easier for the user to understand.
2. It gives attractive presentation to statistical data as compared to tables. By looking at the graph it is
easier to notice the main features of data at a glance in trends and fluctuations.
3. It is time saving device.
4. It facilitates comparison of data relating to two different periods of time or to two different regions.
5. It does not require knowledge of mathematics on the part of the user to understand the message of
graph.
6. It is helpful to locate the median, mode and mean values of the data.
7. It is helpful in forecasting, interpolation and extrapolation of data.

Limitations of Graphical Presentation of Data

Although the technique of graph is a useful one but, it is not free from limitations. Some of its major
limitations are as follows:
1. It lacks complete accuracy about facts.
2. It depicts only few characteristics of data.
3. The graph cannot be used in support of some statement.
4. The graph is not the substitute to the tabulation in all the circumstances and for all purposes.
Difference between Diagrams and Graphs

The question is how to distinguish a diagram from a graph. Though there is no clear-cut line of
demarcation between the two, yet following points of difference may be noted:
 For constructing a graph we generally make use of graph paper whereas a diagram is generally
constructed on plain paper. In other words, a graph represents mathematical relationship (though not
necessarily functional) between two variables whereas a diagram does not.
 Diagrams are more attractive to the eye and as such are better suited for publicity and propaganda. They
do not add anything to the meaning of the data and, therefore, from the point of view of a statistician or
research worker they are not helpful in analysis. Graphs, on the other hand, are very much used by the
statistician and the research worker in analysis. In fact, these days it is difficult to find any research work
without the graphic support.
 For representing frequency distributions and time series, graphs are more appropriate than diagrams. In
fact, for presenting frequency distributions diagrams are rarely used.
TYPES OF GRAPHS
Major types of graphs are as follows:
1. Histogram
2. Frequency Polygon
3. Frequency Curve
4. Ogive or Cumulative Frequency Curve

Histogram

• It is the simplest method for representing continuous frequency distribution into graph.

• Under this method, classes are taken along with x-axis and frequencies are taken along with y-axis.

• Then we construct a simple bar diagram from class size up to height of frequency.

• We can determine the modal value with the help of histogram.

ILLUSTRATION 7
Represent the following data by means of histogram and locate mode.

Weekly wages (in Rs) 10-15 15-20 20-25 25-30 30-40 40-60 60-80
No. of workers 7 19 27 15 12 12 8
Solution:
Since, the width of each class is not equal. So, the given frequencies should be
adjusted as:
Weekly Wages (In Rs.) Width of Class Given frequency Adjusted Frequency
10-15 5 7 7
15-20 5 19 19
20-25 5 27 27
25-30 5 15 15
30-40  12 12÷2=6
10 (5 2)

40-60 20(54) 12 12÷4=3

60-80 20(54) 8 8÷4=2
Now,
Constructing Histogram and locating Mode:

35

30
27

25
No. of Workers

20 19

15
15

10
7 6
5 3
2
0
5 10 15 20 25 30 35 40 45 50 55 60 65 70 75 80 X

Mode = 22
Weekly wages (in Rs.)
Frequency Polygon
• Frequency polygon can be defined as the line of frequency drawn from the upper mid-point of class-
interval.

• There are two ways for constructing frequency polygon.

 Frequency polygon with histogram
 Frequency polygon without histogram

• The frequency polygons under both ways can be illustrated below:

Frequency Polygon With Histogram

Frequency Polygon
Frequency

X
0
10 20 30 40 50 60 70
Class Size
Frequency Polygon Without Histogram

Frequency Polygon

Frequency

0 X
10 20 30 40 50 60 70
Class Size
ILLUSTRATION 8
Draw histogram and show the frequency polygon from the following data.

Variable(Less than) 10 20 30 40 50 60 70
Frequency 4 12 20 32 60 66 66
Solution:
In order to draw the frequency polygon, we should construct the histogram and for the construction of histogram
the given cumulative frequency distribution should be converted into the normal frequency distribution as:

Variable Frequency
0–10 4

10–20 12–4=8
20–30 20–12=8
30–40 32–20=8
40–50 60–32=28
50–60 66–60=6

60–70 66–66=0

ILLUSTRATION 6
Now,

Histogram and Frequency Polygon

Y
30
28

25
Frequency

20
10 8 8 8
15

6
5 4

0
0 X
10 20 30 40 50 60 70 Class interval
Frequency Curve

• It is the limiting form of the frequency polygon. The major difference between frequency polygon and
frequency curve is the way of drawing line.
• The frequency polygon is drawn with straight line and the frequency curve is drawn with free hand.
• If the no. of observation (total frequency) is very large and class interval is relatively smaller then,
frequency curve is more suitable than that of frequency polygon.
• Frequency curve can be illustrated below:
ILLUSTRATION 9
Prepare a histogram, a frequency polygon and frequency curve from the following data:

Class interval 0-6 6-12 12-18 18-30 30-36 36-42

Frequency 4 8 15 20 12 2
Solution:
Since the width of the class 18-30 is double than that of the width of the rest. So, the class 18-30 should be divided into
two parts 18-24 and 24-30 with frequency of 10 each class.

Y Indicator:
16 15 Frequency Polygon
Frequency Curve
14
12
12 10
Frequency

10 8

6
4
4 2
2
X
0 6 12 18 24 30 36 42
Class Interval
By: Prajeet K. Timalsina
Ogive / Cumulative Frequency Curve

• A graphical presentation of cumulative frequency distribution is called ogive.

• For the construction of ogive, class intervals are taken along with x-axis and cumulative frequency (CF) should be
taken along with y-axis.
• Particularly it is useful for graphic computation of median values as well as other partition values like quartiles,
deciles and percentiles.
• There are two types of ogives. They are as follows:
1. Less than Ogive: For the construction of less than ogive, we need to construct less than cumulative
frequency table.
2. More than Ogive: For the construction of more than ogive, we need to construct more than cumulative
frequency table.

Note: If the question is asked for ogive only, then it is recommended to construct less than ogive.
 ILLUSTRATION 10

From the data given below construct less than and more than ogives and then locate median.
Earnings (in Rs) No. of staffs
100 – 200 5
200 – 300 15
300 – 400 22
400 – 500 30
500 – 600 16
600 – 700 12
700 – 800 15
Total 115

Solution:
For the calculation of less than & more than ogives, we need to construct cumulative frequency table as:
Less than cumulative Frequency Table More than cumulative Frequency Table
Class CF Class CF
Less than 200 5 ↓ More than 100 110+5 = 115 ↑
Less than 300 15+5=20 More than 200 95+15 = 110
Less than 400 20+22=42 ↓ More than 300 73+22 = 95 ↑
Less than 500 42+30=72 More than 400 43+30 = 73
Less than 600 72+16=88 ↓ More than 500 27+16 = 43 ↑
Less than 700 88 +12 = 100 More than 600 15+12 = 27
Less than 800 100+15 =115 ↓ More than 700 15 ↑
Now, Y Cumulative Frequency Curves (Ogives)

Y
120

120 115 115

110

110 110 Less than ogive

100

100 Less than ogive

100
90 95
88
90
80
80
70
(OF)

70 73
60 72
of Stafs (OF)No.oStaffs

60
50
50 43
40 42
No.

40
30
30 27 More than ogive
20
20 More than ogive
20
10
15
10 5
X
O
100 200 300 400 500 600 700 800
O Earnings (in Rs) X
100 200 300 400 500 600 700 800
Earnings (in Rs)

Median = 451.67

Median = 451.67
More Illustration
ILLUSTRATION11
Prepare a histogram and frequency polygon from the following data:
Class-interval 0-5 5-10 10-15 15-2525-30 30-35
Frequency 8 16 30 40 24 4
Solution:
Since the width of the class 15-25 is double than that of the width of the rest. So, the class 15-25 should be divided by two
parts 15 – 20 and 20 - 25 with frequency of 20 each class.

Histogram and frequency polygon

30 Histogram
30

24
25
Table

20
20
16
Frequency

15
Frequency Polygon
10
8

4
5

5 10 15 20 25 30 35
Class Interval
By: Prajeet K. Timalsina
ILLUSTRATION12
Draw the cumulative frequency curve for the following data:

Age No. of person in group A No. of person in group B

30-35 10 15

35-40 15 25

40-45 25 30

45-50 40 50

50-60 30 20

60-70 10 10

43
Solution:
Since the question is asked for ogive only. So, we need to construct less than ogive for the given data.
Less than cumulative frequency Less than cumulative freq.
Distribution for group A Distribution for group B
Age (Yrs) No. of persons (f) Age (Yrs) No. of persons (f)

Less than 35 10 Less than 35 15

Less than 40 25 Less than 40 40

Less than 45 50 Less than 45 70
Less than 50 90 Less than 50 120
Less than 60 120 Less than 60 140
Less than 70 130 Less than 70 150

Less than ogives

140 150
140
130
120
120
120
For Group B For Group A
100
90
No. of Person

80 70

60
40 50
40

20 15 25

10
0
35 40 45 50 55 60 65 70 Age
By: Prajeet K. Timalsina
ILLUSTRATION 13
Draw Ogive and locate the value of median from the following:
Wages in '000 Rs. No. of employees
50 or more 65

60 or more 57
70 or more 47
80 or more 31
90 or more 17
100 or more 7
110 or more 2
120 or more 0
Find the number of employees having wages between 63,000 and 75,000

By: Prajeet K. Timalsina

 Solution:
Construction of normal frequency distribution:
Wages Class ('000) 50–60 60–70 70–80 80–90 90–100 100–110 100–123

No. of Employees 8 10 16 14 10 5 2

Since, the question is asked to draw ogives, so we need to construct less

than and more than cumulative frequency table as:
Less than CF table More than CF Table
Wages Frequency Wages Frequency
Less than 60 8 More than 50 65
Less than 70 18 More than 60 57
Less than 80 34 More than 70 47
Less than 90 48 More than 80 31
Less than 100 58 More than 90 17
Less than 110 63 More than 100 7
Less than 120 65 More than 110 2
By: Prajeet K. Timalsina
 Now, Drawing ogives and locating median:

70 65 65
63

60 58 Less than ogive

57

50
47 48
No. of Employees

40 34

31
30
18
17
20
8
10 7 2 More than ogive

0
50 60 70 80 90 100 110 120

Median=79.06 Wages Class

Finding the number of employees having wages between 63,000 & 75,000

63 n=? 75

50 60 70 80 90 100 110 120

n=10 n=16

(70 – 63) (75 – 70)  16

 Required no. of employees = (70 – 60) 10+ (80 – 70)
= 7 + 8 = 15 employees
By: Prajeet K. Timalsina
ILLUSTRATION14
From the following income distribution

Income (Rs. 000) 0-10 10-20 20-30 30-40 40-50 50-60

No. of Persons 5 10 18 23 7 6
Construct an ogive and find the number of persons having income between Rs. 20,000 and 50,000
from ogive curve.
Solution:
Since the question is asked to construct an ogive. So, we construct the less than ogive and for that
less than cumulative frequency table should be constructed.
Income cFf.
Less than 10 5
Less than 20 15
Less than 30 33
Less than 40 56
Less than 50 63
Less than 60 69
By: Prajeet K. Timalsina
 Construction of less than ogive:
69
70  Less than ogive
63 
60
56 
50

40
33 
30

20 15

10 5

O
10 20 30 40 50 60

Finding the number of persons

Base Amount = Rs. 20 and Rs. 50 (in 000)
Number =?

18 23 7

0 10 20 30 40 50 60

Therefore, required no. of person having income between Rs. 20 and Rs. 50 = 18 + 23 + 7 = 48 persons.

By: Prajeet K. Timalsina

50