LectureNotes@simeyoous@yahoo.

com

PRESENTATION OF DATA

1.1 TOPIC OBJECTIVES

By the end of this topic, the learner should be able to:

1) construct various tables for a data set;
2) interpret the data presented in tables;
3) identify advantages and limitations of each type of table.
4) represent data on pictograms;
5) represent data on simple and compound bar charts; and
6) Illustrate data on line graphs, histograms and frequency polygon and curves.

1.2 INTRODUCTION

Any observation collected in respect of any characteristic or event is called data. The data convey
little meaning when considered alone. However, when it is minimized, processed/analyzed and then
presented systematically it is converted to information. The information is then used for evaluation,
planning and decision making

Whenever data is presented pictorially or graphically it gives a better visual impression. Statisticians
must organize, explore and summarize data for easy interpretation. Tables, Pictograms, charts, and
graphs are used to present data for various purposes.

Presentation of Data

Tabular Graphical

Simple table Frequency distribution For quantitative data For qualitative data
table
1. Histogram 1. Bar chart
2. Frequency polygon 2. Pictogram
3. Normal distribution curve 3. Pie chart
4. Line graph 4. Map diagram
5. Cumulative distribution curve
6. Lorenz Curve
7. Scatter diagram
LectureNotes@[email protected]

1.3TABLES

A table is a layout of information or data in form of columns and rows. They are the simplest form
of data display. Some of the possible reasons for which a table may be constructed are to:

• Present the original figures in an orderly manner;

• show a distinct pattern in the figures;
• summarizes the figures for easy interpretation; and
• publish salient figures which other people may use in the future statistical studies.

1.3.1. Principles of table design

The principles to construct a table so that it achieves its objective in the best way possible are as
follows:

 The tables should be numbered e.g table 1, table 2 etc.

 A title must be given to each table, which should be brief and self-explanatory
 Simplicity. A table with too much details or which is too complex is harder to understand. It
is better to show only a little that is understood than to show all having nothing understood.
 Comprehensive explanatory title indicated above the body of the table.
 The source must be stated. All figures come from somewhere and a statement of the source
must be indicated below the table.
 Units of measurement must be clearly stated. Where big figures are involved, it is possible to
reduce their number by indicating in the title or in the headings the number of thousands, or
other multiples of ten each figure represents.
 Double counting of figures should be avoided because it creates misleading presentation.
 The headings to columns and rows should be unambiguous. Use short headings to remove
ambiguity.
 Figures should be approximated before tabulation to reduce unnecessary details in the table.
The number of decimal places retained should be uniform.
 The arrangement of data in a table may be chronological, alphabetical or according to
magnitude to facilitate comparison.
 Totals should be shown where appropriate. They are used in a table for one of the following
purposes: - To give the overall total
- Indicate that preceding figures are sub-divisions of the total.
- To indicate that all items have been accounted for.
 Most of the people find a vertical arrangement better than a horizontal one because, it is
easier to scan the data from top to bottom than from left to right
 Foot notes may be given, where necessary, providing explanatory notes or additional
information.
LectureNotes@[email protected]

1.3.2 Simple Tables

Measurements of single set are presented using simple tables. When characteristics with values are
presented in the form of table, it is known as simple table

Example 1

The workers in a certain company were appraised and given either of the ratings: good, very good,
fair, and extremely good. The table shows the number of workers in each rating.

Table 1.1 Workers ratings

Rating Number of workers (frequency)

Fair 5
Good 14
Very good 8
Extremely good 3
Total 30
Source: ABC Co. 2012

Example 2
Table 1.1 Infant mortality rates of selected countries in 2004

Name of country Infant mortality rate(%)

Pakistan 90
Bangladesh 60
Sri Lanka 26
India 60
Source: World Health Organization

1.3.3 Frequency Distribution tables

Cases where one variable appears more than one times, frequency distribution tables are used. These
tables show the items and the number of times each item appears. A frequency distribution table can
be constructed running horizontally or vertically. The data is arranged in order of size either
increasing or decreasing.

Example 3

In a certain Institute, tutors are paid an hourly rate and the amount depends on their experience.
The table shows how many tutors are paid each rate.
LectureNotes@[email protected]

Table 1.2 Hourly rate payment for Tutors

Hourly rate (KSh) 8,000 10.000 15,000 20,000

Number of tutors (frequency) 4 12 7 2

Source: Field survey 2001

In most case when dealing with a lot of data, the data is first split up into convenient groups (class
interval) and the number of items (frequency) which occur in each group is shown in adjacent
columns. Hence it is a table showing the frequency with which the values are distributed in different
groups or classes with some defined characteristics. In this case, the following guidelines should be
followed:

 The class interval should not be too large or too small

 The class interval should be equal and uniform throughout the classification.

Example 4

Table1.3 Age distribution of University Students

Age Number of Students

O-9 0
10-19 1650
20-29 4400
30-39 120
40-49 50
50-59 20
Source : JOOUST 2011

1.4 BAR GRAPHS/CHARTS

• The data presented is categorical

• Data is presented in the form of rectangular bar of equal breadth.
• Each bar represents one variant /attribute.
• Suitable scale should be indicated and scale starts from zero.
• The width of the bar and the gaps between the bars should be equal throughout.
• The length of the bar is proportional to the magnitude/ frequency of the variable.
• The bars may be vertical or horizontal.
LectureNotes@[email protected]

1.4.1 Simple Bar Charts/Diagrams

In a simple bar chart, a separate bar for each class is drawn to a height proportional to the class
frequency. You can identify the figure that each bar represents at the base of the bar or you can use
a key to show that a color or shade indicates a particular item. One of the most important points to
remember when drawing Simple bar charts is that you must start the scale from zero.

1.4.2 Multiple bar Charts/Diagrams

• Also called compound bar charts
• More than one sub-attribute of variable can be expressed
LectureNotes@[email protected]

1.4.3 Component Bar Charts/diagram

When there are many categories on X-axis and they have further subcategories, then to
accommodate the categories, the bars may be divided into parts, each part representing a certain
item and proportional to the magnitude of that particular item
LectureNotes@[email protected]

1.5 HISTOGRAMS

A histogram is a graphical representation of a grouped frequency distribution. It is a graph, including

vertical bars, with no space between them. The class-intervals / boundaries are plotted along the
horizontal axis and the respective class frequencies on the vertical axis using suitable scales on each
axis. For each class, a bar is drawn with base as width of the class and height as the class frequency.

Used for Quantitative, Continuous Variables i.e variables which have no gaps e.g age, weight, height,
blood pressure, blood sugar etc.
LectureNotes@[email protected]

1.6 FREQUENCY POLYGON

Frequency polygon is an area diagram of frequency distribution over a histogram. It is a linear

representation of a frequency table and histogram, obtained by joining the mid points of the
histogram blocks. Frequency is plotted at the central point of a group

Frequency polygons can always be used in place of histogram, but are particularly useful when there
are many classes in the distribution; or if two or more frequency distributions need to be compared
LectureNotes@[email protected]

1.7 CUMMULATIVE FREQUENCY CURVE

A cumulative frequency curve also known a Ogive is drawn with the cumulative frequency plotted
against the upper boundaries of the relevant interval. This kind of curve allows you to read off
numbers below (or less than) a specified value.

To draw a cumulative frequency, curve the points are joined with a smooth curve. These curves can
be used for estimation purposes. Example : The frequency table below shows marks of candidates in
an exam

Marks 10-20 20-30 30-40 40-50 50-60 60-70 70-80 80-90

Frequency 2 8 12 18 28 22 6 4

Required: Draw a ‘less than’Ogive curve for the following data.

Steps to draw an Ogive:

 Obtain the cumulative frequencies

 Draw and label the horizontal to represent class boundaries and vertical to represent the
cumulative frequencies.
 Plot the points having the actual upper boundaries and the cumulative frequencies,(20,2),
(30,10), (40,22), (50,40), (60,68), (70,90), (80,96) and (90,100)
 Join the points plotted by a smooth curve.
The curve should be joined to a point on the horizontal axis representing the actual lower boundary
of the first class.(i.e. 10,0)

A more than ogive is illustrated below:

LectureNotes@[email protected]

1.8 LORENZ CURVE

A Lorenz curve is composed of a cumulative percentage frequency curve of the less than type. A
Lorenz curve plots cumulative percentage frequency against cumulative percentage class totals. A
class total for any frequency distribution class is the total value of all items belonging to the class.
Class totals are estimated using: Class total=class mid-point x class frequency
LectureNotes@[email protected]

A Lorenz curve has a horizontal axis that begins at 0% and ends at 100% and a vertical axis that
begins at 0% and ends at 100%.

The purpose of such a curve is to demonstrate relative proportions of values represented along the
horizontal versus values represented along the vertical axes.

Example: The data below shows the income distribution of 5 households

Adrian $ 90.00

Bob 15.00

Cathy 70.00

Derek 200.00

Eddie 125.00
A Lorenz curve may be obtained as follows:

1 Arrange in ascending order: 3Find % age income 4 Find % age Cum income

Bob $15.00
3% 3%

Cathy 70.00
14% 17%

Adrian 90.00
18% 35%

Eddie 125.00
25% 60%

Derek 200.00
40% 100%

2 Find total income 500.00

Lorenz Curve
L LED
120
Cumm Percent of Income

100

80

60

40 Lorenz
20
curve
0
0 20 40 60 80 100 120
Cumm Percent of Households
LectureNotes@[email protected]

Interpretation of Lorenz curve

The aim of a Lorenz curve is to show how the total value of the measurement of some economic
variable is shared out among the subjects or items involved. The aim is realized by comparing a
Lorenz curve with the line of equal distribution (LED). The further away the Lorenz curve is from
the LED, the less equally the commodity involved is distributed. Standard situations where Lorenz
curves are used (and often quoted) a’e distributions of incomes (both before and after tax) personal
wealth, turnover of companies, GNP of countries and similar monetary data

Uses of Lorenz curves;

They are used to show inequalities in connection with matters, such as:

 incomes in the population;

 tax payment of individuals in the population;
 industrial efficiencies;
 industrial outputs;
 examination marks; and
 customers and sale

1.9 NORMAL FREQUENCY DISTRIBUTION CURVE

 Frequency polygons may take many different shapes, but many naturally occurring
phenomena are approximately distributed according to the symmetrical, bell-shaped normal
or Gaussian distribution.
 In normal distribution curve, the three measures of central tendency are identical
 approximately 68% of the distributions falls within ±1 standard deviation of the mean
 approximately 95% of the distributions falls within ± 2 standard deviation of the mean
 approximately 99.7% of the distributions falls within ±3 standard deviation of the mean men
and women (each gender forms its own distribution around a different midpoint).
 Asymmetrical distribution are called skewed distributions. The three measures of central
tendency differ. Mode is highest point on curve, the mean is pulled up or down by the
influence of a relatively small number of very high or very low scores and the median lies
between the two.
 n Positively (or right) skewed distributions and negatively (or left) skewed distributions can
be identified by the location of the tail of the curve:
-Positively skewed distributions have a relatively large number of low scores and a small
number of very high scores.
-Negatively skewed distributions have relatively large number of high scores and a small
number of low scores.
LectureNotes@[email protected]

1.10 LINE DIAGRAM/GRAPH

A line graph represents the data concerning one variable on the horizontal and other variable on the
vertical axis. It uses points and lines to show change over time. It is plotted from a set of points and
then joined by a line. Different data sets can be plotted on the same graph but a key must be used to
identify each data set.

Line diagrams are used to show the trend of events with the passage of time.

The line graphs below shows trend of profit for a certain company for six years and unemployment
rates for the last 10 years respectively
LectureNotes@[email protected]

1.11 SCATTER DIAGRAM/PLOT

This is a plot of points on the Cartesian plane that shows the general shape and trend as either being
a straight line or curve or none at all. It is used to show the existence of association or relationship
among variables
LectureNotes@[email protected]

1.12 PIE CHART

Pie chat is Most common way of presenting qualitative data The value of each category is divided
by the total values and then multiplied by 360 and then each category is allocated the respective
angle to present the proportion it has.

It is often necessary to indicate percentages in the segment as it may not be sometimes very easy
virtually, to compare the areas of segments.
LectureNotes@[email protected]

1.13 PICTOGRAMS

This is a popular method of presenting data to those who cannot understand orthodox charts. Small
pictures or symbols are used to present the data,e.g a picture of a doctor to represent the population
of physician. Fraction of the picture can be used to represent numbers smaller than the value of
whole symbol

1.14 STATISTICAL MAPS

When statistical data refers to geographic or administrative areas, it is presented either as statistical
map or dot map. The shaded maps are used to present data of varying size. The areas are shaded
with different colours or different intensities of the same colour, which is indicated in the key.
LectureNotes@[email protected]