Chapter 3:

Data Collection & Presentation

1
3.1. Data Collection
Data collection – is the process of gathering and
measuring data on variable of interest, in an
established systematic fashion that enables one to
answer stated research question.
Sources of data:
1) Primary data sources – data which are
originally collected by researcher for the first
time
2) Secondary data sources – published &
unpublished sources

2
3.2. Methods of Collecting Data
1) Direct observation – involves counting the data of
interest in person
2) Personal interview – involves contacting the desired
people (respondents) in person and inquiring their
opinion concerning the area of interest
3) Telephone interview – contacting the desired people
through telephone lines
4) Written questionnaire – written questions are mailed
to individuals to fill in and send back their answers

3
Strength & Weakness of Data Collection Methods

Strength Weakness
Direct Avoids biases Not possible to directly observe
observation or count
Personal High rate of response Time consuming; cost of
interview training interviewers
Telephone Reduces the cost of Respondents may not have
interview individual contact telephone lines; or may not be
available to telephone calls

Written Possible to contact large Problem of getting respondents

questionnaire number of respondents; to fill & return questionnaires
within short time and in
a reduced cost

4
3.3. Classification of Data
 Data classification – is a systematic grouping
of units according to their common
characteristics.
 Objectives of data classification
 To simplify and make data more concise,
meaningful or comprehensible
 To bring out points of similarity &
dissimilarity
 To compare characteristics
 To prepare data for tabulation

5
…classification of data..(Cont’d)

Based on nature of variable Based on source of

 Quantitative data – collection
quantitative features  Primary data
 Qualitative data –  Secondary data
qualitative attributes
 Discrete data – exact Based on source of
numerical value (whole presentation
number)  Grouped data –
 Continuous data – within a presented in a group
certain range  Ungrouped data –
 Temporal & spatial data presented individually

6
Two Methods of Data Presentation
(a). Tabular Presentation
• Orderly and logical arrangement of data in
a table
(b). Diagrammatic or Graphic Presentation
a) Histogram
b) Frequency polygon
c) Bar chart
d) Pie chart

7
3.4. Frequency Distribution
(1). Tabular Presentation of Data
 Frequency distribution – is a table in which the values of a
variable are grouped into classes, together with the number of
observed values falling into each class.
 Grouped frequency – the number of observed values that belong
to a class is called its frequency
 Cumulative frequency - is the sum of the class and all classes below it
in a frequency distribution. We add up a value and all of the values that
came before it.
Example:

8
Examples: Constructing Frequency Distribution

1) A survey was taken in Bole Sub-City of Addis Ababa where in

each of 20 homes, people were asked how many cars were
registered to their households. The results were recorded as
follows: 1, 2, 1, 0, 3, 4, 0, 1, 1, 1, 2, 2, 3, 2, 3, 2, 1, 4, 0, 0
a). Construct a frequency distribution.
b). Construct the cumulative frequency distribution
2) Below are the favorite colors of 10 second graders. Construct
frequency table
Red Blue
Yellow Red
Green Red
Red Green
Blue Red

9
Constructing Grouped Frequency Table
Key Concepts:
 Class Limits: the values which determine the upper and lower
limits of a class.
 Lower Class Limit = smallest data value that can be included
in the class
 Upper Class Limit = largest data value that can be included in
the class
 Class Interval is the numerical width of any class in a particular
distribution
 Class Interval = Upper Class Limit (UCL) – Lower Class
Limit (LCL)
 The upper extreme value of the first class interval and the lower
extreme value of the next class interval will not be equal.

10
…key concepts (Cont’d)

 Class Width (Size) = (Max Value – Min Value)/C = Range/C

where Max value = refers to the maximum value in
dataset; Min value = refers to minimum value,
C = refers to number of classes
 Usually this yields a number with several decimal places.
 In such cases, we should round up this number to the
accuracy of the original data.
 Note that always round up!!

11
…key concepts (Cont’d)

 Class Boundary
 There is a space between the upper limit of one class and
the lower limit of the next class. The halfway points of
these intervals are called class boundaries.
 Class boundaries are the data values which separate
classes
 Usually applicable for continuous variable
 They are not part of the classes or the datasets
 In class boundary, the upper extreme value of the first
class interval and the lower extreme value of the next
class interval will be equal.

12
 Class Limit vs. Class Boundary
Class Limit Class Boundary
15 – 19 14.5 – 19.5
20 – 24 19.5 – 24.5
25 – 29 24.5 – 29.5
30 – 34 29.5 – 34.5

 Mid-Value or Class Mark

• Class mark is the mid-point or average of LCL and UCL or
LCB and UCB
• Mid-Point = (LCL +UCL)/2 or (LCB+UCB)/2

13
Rules for Forming Grouped Frequency Distributions
1) There is no hard and fast rules for the number of classes one should
use.
2) The number of classes to use depends largely on how many
measurements or observations we have.
3) Make sure that each observation falls into one and only one class.
4) Do not use too few classes or too many classes
5) Whenever possible, we make classes over equal ranges, that is, equal
class width for all classes. Reason: to have meaningful comparisons
between different classes and represent diagrammatically with greater
ease and utility.

Class Width = (Max Value – Min Value)

# of Classes

14
Example
The price of 20 items (to the nearest Birr) is given below
46 62 60 47 38 48 51 53 42 60
67 46 54 42 43 38 38 54 46 51
a) Construct a grouped frequency distribution with five classes.
b) Determine the class boundaries and the class marks
c) What is the relative frequency of the 3rd and 5th class?

15
3.5. Graphical Presentation of Data
 Graphs or charts of a frequency distribution are useful
because they emphasize and clarify the inherent
characteristics of and patterns that are not so readily visible in
frequency tables.
a) Histogram – consists of a set of rectangles having heights
equal to the class frequencies and bases equal to the class
width.
 It is used to chart continuous frequency distribution.
 Usually the markings on the horizontal scale (X-axis) are
the class boundaries and the markings on the vertical
scale (Y-axis) is the class frequencies.

16
…graphical presentation …(Cont’d)
b) Frequency polygon
 A line graph of class frequencies plotted against
class mark.
 Classes with zero frequencies are added at both
ends of the distribution to connect the graph with the
horizontal scale
 Frequency polygon can also be obtained by
connecting the mid-points of the tops of the
rectangles in a histogram by straight lines.

17
…graphical presentation …(Cont’d)
c) Bar Charts – are constructed when the data are either
discrete or qualitative
Difference between Histogram and Bar Chart
Histogram Bar Chart

 A two-dimensional (area)  One dimensional diagram in

diagram where both the width which only length (height of
(base) and the length (height the bar) matters while width is
of the rectangle) are arbitrary
important
 The bars (rectangles) are  Proper spacing is given
adjacent to each other between different bars
 The class frequencies are  Class frequencies are
represented by the area of represented by the heights of
the rectangles the corresponding bars

18
d) Pie Chart

 A circle divided into portions that represent the relative

frequencies or percentages of population or a sample
belonging to different categories.
Steps to construct pie chart:
1) Express each of the component values as a percentage
of the respective total.
2) Since the angle at the center of the circle is 360 degree,
the total magnitude of the various components is taken to
be equal to 360 degree, and each component part is to
be expressed proportionately in degrees. 1 % of total
value = 360/100 is 3.6 degree

19
…Pie Chart…(Cont’d)

20
Example: Pie Chart
Quarterly sales of Abyssinia Coffee PLC for the year 2020
were the following. Present this data using
a) Bar chart, and
b) Pie chart

Quarter Sales (in thousands of Birr)

I 90
II 360
III 120
IV 150

21
END OF CHAPTER 3

22