Chapter 2
Charts and Graphs
Learning Objectives
Understand the concept of frequency distribution.
Construct bar chart, pie chart, histogram, frequency
polygon, ogive, stem-and-leaf plot, Pareto chart, and
scatter plot.
Frequency Distribution
Frequency distribution is a tabular
summary showing the frequencies of
observations in each of several non-
overlapping classes.
The first step in the construction of a
frequency distribution is to find the
range for the given data.
The second step in this process is to
get the number of class intervals.
There is no fixed rule to obtain this.
As a of rule of thumb, the number of
class intervals should be not less
than 5 and not more than 15.
The third step is to determine the
width of the class interval.
Table 2.2: Sales of a Pharmaceutical Company
for the Past 10 Years (Ungrouped Data)
For the data shown in Table 2.2, the decision
to construct five class intervals has already
been taken and the range of the distribution
is 17.5. So, the desired width of the interval
is = 17.5/5 = 3.5.
For convenience (and practicality also), the
width of the interval is rounded off as 4.
The lowest sales value is 72.2 and the highest sales value is
89.7. So, a researcher can start the distribution from 72 and
can end the distribution at 90. Table 2.3 depicts the grouped
data in the form of a frequency distribution.
Table 2.3: Frequency Distribution of the Sales of a
Pharmaceutical Company in the Past 10 Years (Grouped
Data)
The class midpoint is the value
halfway between the lower and the
upper class limits. Table 2.4 exhibits
the frequency distribution of the
sales of a pharmaceutical company
with class midpoint.
Relative Frequency and Cumulative Frequency
Relative frequency is the
proportion of the total
frequencies for any given
class interval of any
frequency distribution.
Cumulative frequency
distribution is the proportion
of observations with values
less than or equal to the
upper limit of any class
interval. Table 2.5 shows the
relative frequencies and
percentage frequencies.
Table 2.6 exhibits the
computation of cumulative
frequencies.
Table 2.6: Frequency distribution of sales of a pharmaceutical
company in the past 10 years (with class midpoint,
relative frequency, and cumulative frequency)
Graphical Presentation of Data
Some of the basic and most widely used methods of
presenting data in graphs and charts are as follows:
Bar chart
Pie chart
Histogram
Frequency polygon
Ogive
Stem-and-leaf plot
Pareto chart
Scatter plot
Bar Chart (Example 2.1)
A bar chart is a graphical
device used in depicting
data that have been
summarized as frequency,
relative frequency, or
percentage frequency.
Figure 2.1: Bar chart of frequency versus
class interval for the data given in Table
2.3 (for Example 2.1)
Pie Chart
A pie chart is a circular representation of data when a
circle is divided into sectors with areas equal to the
corresponding component. These sectors are called slices
and represent the percentage breakdown of the
corresponding components.
Pie Chart (Example 2.2): A shoe manufacturing company has
collected data on its sales in different shoe size categories.
Table 2.7 shows the sales of different shoe size categories.
Construct a pie chart using the data in Table 2.7.
Pie Chart (Example 2.2 Contd.)
Figure 2.15: Pie chart of sales versus
category size for the data given in
Table 2.7 (Example 2.2)
Histogram (Example 2.3)
A histogram can be defined as a set of rectangles, each
proportional in width to the range of the values within a class and
proportional in height to the class frequencies of the respective
class interval.
Figure 2.23 : Histogram for the data given
in Table 2.3 (Example 2.3)
Frequency Polygon (Example 2.4)
A frequency polygon is a graphical device for understanding the shape of a distribution.
Figure 2.31 : Frequency polygon for the data given in
Table 2.3 (Example 2.4)
Ogive (Example 2.5)
Ogive is a cumulative frequency curve or a cumulative frequency polygon.
Figure 2.41: Frequency polygon for the data given in Table 2.6
(Example 2.5)
Pareto Chart
Pareto chart is a graphical technique of displaying a
problem cause.
It is a special type of vertical bar chart in which the
categorized responses are plotted in the descending rank
order of their frequencies and combined with a cumulative
polygon on the same graph.
The main focus of the Pareto chart is to separate the “vital
few” from the “trivial many.”
Pareto Chart (Example 2.6) : Sibbal Hotel Group conducted a
customer satisfaction survey of 340 customers who attended a special
dinner arranged at the hotel. The survey group prepared a
questionnaire that was divided in two parts: satisfaction reasons and
dissatisfaction reasons. Sibbal Hotel Group has decided to focus on the
reasons of dissatisfaction rather than on satisfaction factors to
improve its quality of service. The following observations regarding
categories of dissatisfaction were made (Table 2.9).
SPSS output for Pareto chart (Example 2.6)
Stem-and-Leaf Plot
Stem-and-leaf plot can be constructed by separating the digits
of each number into two groups, one as a stem and the other
as a leaf.
This plot is mainly used for examining the shape and spread of
data.
After separating the data, the left-most digit is termed as the
stem and is the higher valued digit. The right-most digit is
termed as the leaf and is the lower valued digit.
For example, take the number 54. The stem-and-leaf plot
separates this number into two digits, 5 and 4. 5 which is a
higher valued digit is termed as the stem and 4 which is a
lower valued digit is termed as the leaf.
Stem-and-Leaf Plot (Example 2.7): The following data
reveals the scores obtained by 40 employees during
evaluation of a training programme. Scores (out of 100) are
as shown below:
Scores obtained by 40 employees during the evaluation of a training program
SPSS output for Stem-and-leaf plot (Example
2.7)
Scatter Plot
The scatter plot is a graphical presentation of the
relationship between two numerical variables.
It generally shows the nature of the relationship between
two variables.
The application of a scatter plot is very common in
regression, multiple regressions, correlation, etc.
Scatter Plot (Example 2.8): Chhattisgarh become a new state in 2000. The
property prices in the state capital, Raipur, are zooming up. The real estate
business has an edge over other business streams. Bhilai, an important
industrial town of Chhattisgarh is also experiencing the same phenomenon.
Table 2.10 shows the escalation of property prices (average price in major
locations) in Raipur and Bhilai in the past 7 years in different quarters. From
Table 2.10, construct a scatter plot. Figures are in rupees per square feet.
Figure 2.54 : Scatter plot for the data given in Table 2.10 (Example
2.8)