CPU Business and Technology

College

Research Methods in ACFN

AcFn 3101

Under Gradate program

By: Dr. Abel G. (BA, MA, MBA, PhD)

Ass/Professor of Business Leadership

2

1. What is sampling?
and why sampling?
2. What are the basic
sampling design
and Methods for
sampling
 Sampling Methods
3

Population:
 Population is the entire mass of
observations from which a sample is to
be formed.
 It is the universe from which sample is

drawn.
 ….are of interest to the researcher
 A survey conducted based on the basis of

all the population is known as census

 Sampling Methods…….
4

Sample:
 A sample (n) is a subset of a population (N) to

which the researcher has selected with a due care

and intends to generalize the results of the study to
the entire population.
 Survey conducted on the basis of sample is sample

survey
 Sampling Frame: - A list of every individual in the

population
 Shows where we can get
 Frame is either constructed by the researcher or some
existing list of population is used
 Sampling Methods…..
5

 The main important characteristics of

sample :
 Goal-oriented: relate to the research
objectives
 Representative of the universe: Sample
must be adequate
 The sample size should be sufficiently
large
 A sample should be selected at random
 A sample should be economical. should be
achieved with minimum cost and effort.
 Viable in the context of budget
6

Advantages of Sampling
o Sampling reduces cost
o Sampling gives grater accuracy
o Sampling brings speed

o Sampling increases scope

o Sampling reduces work
o We can observe in detail
o Easy to manage
 Sampling Methods…..
7

Limitations of Sampling:
 If the sample is not true representative of
population then false inferences may
occur
 We cannot select a sample which can
represent the entire mass.
 That is, a sample always
possesses some error.
 Biased samples may lead to false
generalizations
 Very less population also give trouble
 Sampling Methods…..
8

There are two design sampling:

1. Probability Sampling:
 The researcher chooses samples from a

larger population using a method based

on the theory of probability.
 the sample is selected randomly from a

list that contains all members of the

population.
 Used in quantitative/mixed research
 Sampling Methods…..
9

2. Non Probability Sampling:

 All members of the population will not have
equal chance of being selected.
 The respondents are selected at the discretion of
researcher.
 Used in qualitative researches and when it is impossible
to use probability sampling.
 E.g. homeless people, migrants, top-managers,
expert employees etc..
 Can work well for exploratory studies and
mixed
 Cheaper and easier to carry out than
probability designs.
 Sampling Methods…..
10

Probability Sampling
1) Simple Random Sampling
 Every member of the population has the
same probability of being selected
 It is an unbiased
 Random number is used for selecting
sample for large sample size
 Lottery technique is also used for the
selection of sample
 An example - the list of names of 25
employees being chosen out of a hat from a
company of 250 employees
 Sampling Methods…..
11

 Researchers:
 prepare a list of all the population members

initially, and then each member is marked with a

specific number ( for example, there are nth
members, then they will be numbered from 1 to
N).
 From this population, researchers choose
random samples using two ways:
 Random number tables and random number
generator software.
 Sampling Methods…..
12

2) Systematic Sampling:
 It is sampling by regular intervals

 Population will be accurately listed (finite)

 It involves the selection of every Kth case from list

of group,
 Example:
 Every 10th person on a patient list or every 100 th
person from a phone directory….
 i.e. select 10 members from a list of 100 people,
arrange all names in a specific order and select
every tenth one after selecting the first randomly.
 Ex 2: a researcher wants to choose about 100
subjects from a total target population of 500 people.
Therefore, 500/100 (N/n)=5. Therefore, every 5 th
Systematic Sampling
 Sampling Methods…..
14

3) Stratified Sampling:
 To increase the precision and

representativeness stratification and

randomness are both combined in this method.
 The population is divided into smaller

homogeneous group (strata) and used the

random techniques to draw the sample.
 Stratification factors are age, sex designation,

religion race, class, managerial level, departments,

branches, profession, type of institution etc..,
 Sample can be selected proportionately as they

present in the universe (population).

 The sample rectifies all problems that exist in
 Sampling Methods…..
15

 To illustrate
 Suppose that we want a sample of size n = 130 to be
drawn from a population of size N = 8000 which is
divided into three strata of size N1 = 4000, N2 = 2400
and N3 = 1600.
 Adopting proportional allocation, we shall get the
sample sizes as under for the different strata: For
strata with N1 = 4000, we have P1 = 4000/8000 and
hence

 n1 = n * P1 = 130 (4000/8000) = 65

 Similarly, for strata with N2 = 2400, we have n2 = n *P2 =

 Sampling Methods…..
16

4) Cluster Sampling: (Area Sampling)

 Applicable when the population is distributed over
geographically large area.
 Cluster sampling involves grouping the population and then
selecting the groups or the clusters rather than individual
elements for inclusion in the sample.
 Example: For instance, if you wish to sample city governments in the
state of Oromiya, rather than travel all over the state to interview key city
officials, you can cluster these governments based on their provinces,
randomly select a set of three provinces, and then interview officials from
every official in those provinces/counties.
 It is simple, economical way of selecting case from large
samples.
 Cluster sampling is less representative, biased, non-uniform
as compared to other methods and gives poor inferences.
 Sampling Methods…..
17

Non-Probability Sampling
1) Purposive Sampling:
 Investigator selects sample with specific propose

and leaves others of not interest.

 selecting a sample based on the basis of k’ge of

population, its elements and the purpose of the

study. E.g. key informants.
2) Quota Sampling:
 It is also like purposive or stratified sampling. It is non-
probability sampling method investigator judges about
his sample from each strata called 'Quota'.
 It is less expensive and quick process where investigator
has full of choice.
 It is again more biased, and sampling errors may
present.
 Sampling Methods…..
18

3) Convenience Sampling
 It is careless, unsystematic, accidental or
opportunistic sampling.
 Reliance on available subjects or haphazard
sampling. Example:
 Stopping a person on the street
 Selecting a student in a class
 It is only based on the convenience available to the
researcher.
4) Snowball sampling.
 In snowball sampling, you start by identifying a few
respondents that match the criteria for inclusion in
your study, and then ask them to recommend others
19
 Determination of Sample Size
20

 This refers to the number of items to be

selected from the universe to constitute a
sample.
 The size of sample should neither be excessively
large, nor too small. It should be optimum.
 An optimum sample is one which fulfills the
requirements of efficiency, representativeness,
reliability and flexibility.
 While deciding the size of sample, researcher must
determine the desired precision as also an
acceptable confidence level for the estimate.
 Selecting a representative sample – based on
Determination of Sample Size
considerations

 Nature of the population - Heterogeneous or

homogenous - Dispersion factor (or variability)
 Nature of study (qualitative or quantitative)
 Sampling design or type of sample
 Available finance and other resources (trained
investigators)
 Type of analysis to be employed.
 The level of precision needed.
Determination of Sample Size

 Rule of thumb for statistical measurement >

100 sample size (Dornyei 2011) or

Use this formula n= N__
1+NE² , (Slovin)
 where n is the sample size, N is the population
size and e is the margin of error to be decided by the
researcher.
 Example:
Table: Sample Size determination
Margin of error
Population 5% 3% 2% 1%
50 44 48 49 50
100 79 91 96 99
150 108 132 141 148
200 132 168 185 196
250 151 203 226 244
300 168 234 267 291
400 196 291 343 384
500 217 340 414 475
750 254 440 571 696
1000 28 516 706 906
2000 322 696 1091 1655
5000 357 879 1622 3288
10,000 370 964 1936 4899
100,000 383 1056 2345 8762
1000,000 384 1066 2395 9513
10,00000 384 1067 2400 9595
Source: Saunders at al. (2009, p. 281)
Determining sample size......


25

Chapter 6:
Data collection and
Types of data
 Chapter Contents
26

Data collection and Types of data

Data collection techniques
Designing a questionnaire
Conducting interview
Conducting Focus group
discussion
 Data collection
27

 Data collection is the systematic process of

gathering information from various sources to address
research questions, test hypotheses, and evaluate
outcomes.
 It involves measuring information on variables of
interest in a pre-established, systematic way.
 It is a critical step in research, analysis, and decision-
making processes
 Primary data is original data collected directly by the
researcher for a specific research purpose
 Secondary data is information that has already been
collected and published by others
 Data collection is crucial in research for several
reasons, each contributing to the integrity, validity, and
applicability of the study's findings. Here are some key
reasons why data collection is essential:

 Foundation for Research Findings

 Informed Decision-Making
 Hypothesis Testing
 Understanding Trends and Patterns
 Generalizability
 Quality Assurance
 Primary and Secondary Data
Sources
29

 Primary  Secondary
 Questionnaires  Textbooks
 Interviews  Journal papers
 Observation
 Conference papers
 Participant
 Magazine articles
 Government &
observation industry reports
 Informal  Web pages
conversations  Acts of Parliament
 Structured group  Company reports
discussions
 The most common Useful to collect
30

data collection instrument quantitative

information

1. Survey
Questionnaire

Should contain 3 elements:

• Introduction – to explain the objectives
• Instructions – must be clear, simple language & short
• User-friendly – avoid difficult or ambiguous questions
Steps To An Effective Survey
Questionnaire
31

Prepare your survey questions

(Formulate & choose types of questions, order them, write instructions, make copies)

Select your
respondents/sampling
Random/Selected
Administer the survey
questionnaire
(date, venue, time )
Data collected

Analyze and interpret data collected

(Statistical analysis-frequency/mean/correlation/% )
 Rules of designing a questionnaire
32

Prepare a cover letter in which you:

 Introduce yourself
 Describe the main objectives of the study
 Explain the relevance of the study
 Convey general instructions
 Indicate that participation is voluntary
 Assure respondents of the anonymity of the
information they provide
 Provide a contact number in case they have
any questions
 Thank them for their participation in the study
 CPU COLLEGE
Department of xx
Questionnaires Filled managers and employees
33
Dear respondents,
 The questionnaire is prepared to gather data necessary for conducting study on
‘XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX )’ for partial fulfillment
of MBA. Thus, your opinion and views are valuable so as to establish clear picture
of the issue under the study and for its successful completion. The information you
provide will be used only for academic purpose and assessed by the researcher
alone, so cooperate honestly with no fear, as your response kept strictly
confidential and anonymous. Please try to respond to every question as per the
instruction there of and if you face any problem or confusion you can contact the
researcher through the address indicated here.
 Thanks in advance for your relevant answers and cooperation!!
 xxx(The student researcher)
 Address: phone: -----------------
 E-mail: -----------------------
 NB: No need to write your name
  To fill questions with choices (part I and all tables), please check
tick mark ( ) under the number of your choice. And write your answer
clearly on space provided for open ended questions.
34
 Measuring Employee attitude towards…
35
36
 Rules of designing a
37
questionnaire
Formulating effective questions
1.Avoid jargon, slang and
abbreviation
Do you think that high control practices
enhances voluntary compliance? (WRONG)

How do you compare high commitment HRM wit

High control HRM? (WRONG)
 Rules of designing a
questionnaire
38

Formulating effective questions

2.Do NOT use ambiguous questions

3.Avoid emotional language, use neutral

language.
What do you think about a policy to pay
murderous terrorists who threaten to
steal the freedoms of peace-loving
people?(WRONG)
 Rules of designing a
questionnaire
39

4. Do NOT ask double-barrelled Qs

How often and how much VAT do you pay each
year?

5. Do NOT ask leading questions

Tax administration in the country is very
poor, isn’t it?

6. Do NOT ask presumptuous questions

How much tax penalty do you pay each
year?
 Rules of designing a
40
questionnaire
7. Avoid prestige bias(prime minister,
doctor, professor, expert…)
People might agree with influential personalities
(Mayor, Prime Minister, etc.) and tend to disagree
with less popular personalities.
\
Most doctors say that cigarette smoke causes
lung disease for those near a smoker. Do you
agree?
8. Do NOT confuse beliefs with reality.
Do you rate a teacher higher if the teacher
tells many jokes?
 Rules of designing a
41
questionnaire
9. Avoid asking questions that are
beyond respondents
capabilities.
Do you think the new tax proclamation
is effective in enhancing voluntary
compliance?
 Rules of designing a
42
questionnaire
10.Avoid asking about intentions in
the distant future.

11. Avoid overlapping response

categories.
Years of experience 5-10, 10-15, 15-20
 Basic Types of survey questions:
43

1. Open-ended 2. Close-ended
Questions Questions
 Free-response  Dichotomous

(Text Open End) question

 Multiple-choice
 Fill-in relevant
 Likert Scale
information
 Rank
44
More….
 Closed-ended:
 Researcher structured responses

 Greater uniformity of response

 Pre-coded, hence can be directly entered to

statistical software
 More popular

 Open-ended:
 Self-expressed respondents’ responses

 Less uniformity in responses

 Cannot be directly entered into statistical software;

 Less popular with researchers


45

Advantages of Closed questions

The response choices can clarify question

Respondent are more likely to answer about

sensitive topics.

Easier, quick, and less costly to analyze

46

Disadvantages Closed questions

They can suggest ideas that the respondent
would not otherwise have_different
experiance
Respondents with no opinion or no
knowledge can answer anyway.
Misinterpretation of a question can go
unnoticed
Respondents may be frustrated because
their desired answer is not a choice.
They force respondents to give simplistic
responses to complex issues.
47

Advantages open questions

They permit an unlimited number of possible
answers.
Respondents can answer in detail and can qualify
and clarify responses.
Unanticipated findings can be discovered.
They permit adequate answers to complex issues.
They permit creativity, self-expression and
richness of detail.
They reveal a respondent's logic, thinking
process and frame of reference.
48

Disadvantages of Open questions

• Different respondents give different degrees
of detail in answers_ difficulty in analysis
• Response may be irrelevant or buried in
useless detail.
• Comparisons, Codingand statistical analysis
become very difficult.
• Questions may be too general for respondents
who lose direction
49

Mode of dissemination
 Self-administered
 Mail survey
 Web survey
50 Effective way Involves verbal
of gathering and non-verbal
information communications

2. INTERVIEW

Can be conducted
• face to face,
• by telephone,
• online or through mail
 Steps To An Effective Interview
51

Prepare your interview schedule

Select your subjects/ key informants

Conduct the interview

Analyze and interpret data collected from the interview

Types…

 There are three most common types of

interview:
1. Structured Interview
2. Semi-structured Interview
3. Unstructured Interview
 Structured Interview
Uses series of structured questions
 Involves face to face interaction with the

enumerator/ researcher
 Used in quantitative/qualitative researches
Semi-structured Interview
A set of general questions
 The schedules are flexible and can be
updated after each interviews
 Probing is crucial (i.e. asking for an
elaboration of the responses of the
interviewee using when, who, how, etc.
questions)
 The interviewee need to feel comfortable
and relaxed (informal)
 Unstructured Interview
 The researcher tries to get the holistic
understanding of the interviewee's point
of view or situation.
 The respondent is free to talk with less
directional influence.
 But need more expertise to control and
more time for analysis
 It is purely qualitative
 Using tape recorder is important though
not always
 Tips on interviews
 Begin with an explanation of who you are and what the
survey is about and ensure confidentiality.
 Try to achieve rapport with the respondent: be friendly
and look as if you are enjoying the interview and are
interested in what they have to say.
 Be aware of the importance of body language in face-
toface interviews.
 Interviewees are more at ease with someone who is like
them in terms of ethnicity, class, sex, speech and dress
code.
 Dress in a similar manner to your interviewee if possible;
 Eg. if interviewing a nomadic community in their locality they
are unlikely to be wearing a suit: T-shirt and shorts would be
more suitable.
 Tape-recording or note taking.
 Observe verbal &
non-verbal communication, Need to keep
56
surrounding atmosphere, careful records of
culture & situation the observations

3. Observations

Can be done through observing discussions,

observations of habits, rituals,
review of documentation,
experiments
 Observations

57
Steps To An Effective Observation
58

Determine what needs to be observed

(Plan, prepare checklist, how to record data)

Select your participants

Random/Selected

Conduct the observation

(venue, duration, recording materials, take photographs )

Compile data collected

Analyze and interpret data collected

59
 4. Conducting a Focus Group
60
Discussion(FGD)
 A group interview with 6 to 12 participants
and marked by guided group discussion,
question and answer, interactive
dialogue, and other activities.
 Create groups strategically-Consider if
complementary or argumentative interactions
would be more appropriate for the research.
 Assign a HOST, MODERATOR, FIELD NOTE
61
 Cont.
 Opening FGD:
 Help participants to relax

 Introduce the purpose, confidentiality &

anonymity
 Negotiate the length of the FGD & ask

participants to respect it
 Asking questions:
 Start with general and easy questions

 Then move to more personal and sensitive

questions
 Keep an eye contact

 Make sure that no one dominates

Cont.

Seeking response:
 Gather as many diverse opinions as possible
 Encourage those who are nervous to share

their ideas
 Some people might approach you after the

discussion to give you an information that they

were not comfortable sharing in the FGD, take
a note of that
 Wrapping up:
 Thank participants
 5. Documentary Research
 The systematic use of published and unpublished
materials for investigation
 Documentary research involves studying existing
information recorded in media, texts, and physical items.
 There are three types of documentary research:
 Collecting and analyzing the works of others-

generating information from previous writers in the field

in question (meta analysis and systematic review).
 Use of Archival Sources- using public and private

organizational records (archives) as sources of

information. E.g. letters. Minutes, etc.
 Reanalysis of data sets- reanalyzing the data collected

by other researchers or organizations. E.g. reanalyzing

the census data set, analyzing crime statistics, etc.
 Cont.

 Issues to be considered in documentary research:

 Reliability of data-who, how, when the data collected.

 Suitability of the data

 Adequacy of the data-in terms of accuracy and

sufficiency
 Advantages of Documentary research
 Data readily available

 Easy to do

 Inexpensive and economical:

 Disadvantages
 Accuracy of the information is always questionable

 Limited/incomplete data
 Data out of context
 Official statistics are not always exhaustive.
Improving Data Quality

 Plan data collection carefully thinking of

reliability, validity and objectivity.
 Triangulation: use more than one method
to answer your research question (validity).
 Train interviewers/observers.
 Do a pilot-study (practicability).
 Data Collection Tools and methods
Document
s/
Archived
data
[personal/
official]

Questionnai
Intervie
re
ws
Observation

Focus
groups

67
Chapter 7: Citation and Referencing: Validity and
Reliability

When to cite?
 Cite the work of those individuals whose ideas,
theories, or research have directly influenced
your work. (Background information, support or
dispute your thesis, or offer critical definitions,
literature review, ……)
 Citation of an article implies that you have personally
read the cited work.
 When citing aim to cite one or two of the most
representative sources for each key point.
 But, in literature you need to include a more
comprehensive list of citations
 Plagiarism
 Authors should not present the work of another as if it were
their own work.
 When paraphrasing, quoting an author directly, or describing
an idea that influenced your work, you must credit the source.
 All of the following are considered plagiarism:
 Turning in someone else's work as your own
 Copying words or ideas from someone else without giving credit
 Failing to put a quotation in quotation marks
 Giving incorrect information about the source of a quotation
 Changing words but copying the sentence structure of a source without
giving credit
 Copying so many words or ideas from a source that it makes up the
majority of your work, whether you give credit or not (see our section on
"fair use" rules)
 How to avoid plagiarism?
70

 Mentality፡ Don’t even think of copying other’s work.

Set in your mind that you need to acknowledge
things/info/ ideas that you get from others.
 Citation & Referencing፡ Learn and master the
correct citation and referencing styles. If unsure,
consult the lecturers or make use of the manual/guide.
 Avoid poor paraphrasing: make sure that you change
the words and the way the sentence is put together.
1. You can also be accused of plagiarism if you only
change someone's words very slightly
 Keep track of the sources you consult in your
research.
 List every source you have used and double
check your reference list against the citations
 How to avoid plagiarism?
… cont’d
71

 Make good quality notes, don’t just copy

 Be consistent!

 Plan in advance

 Do a little bit every day

Importance of Referencing

You must have a reference, enables to:

1. Shows the breadth of your research.
2. Strengthen your academic argument.
3. Show the reader the source of your information.
4. Allow the reader to consult your sources
independently.
5. Allow the reader to verify your data.
6. Avoid Plagiarism, ensure completeness,
correctness, and help to support arguments
 Styles of Referencing

73

 Currently, commonly referencing style is

APA
 The American Psychological Association
(APA) Style,
 The Harvard Style And
 It is important to apply chosen style
strictly and consistently
 Styles of Referencing…..
74

1) APA Style

 The American Psychological Association (APA)

citation style is the most commonly used format for
manuscripts in the social sciences.
 APA regulates:
1. Stylistics
2. In-text citations
3. References
75

In-text Quotation
 Narrative citations occur when the information

being quoted is incorporated into the text as part of

the sentence for example,
“Aman (2019) states that......"
 Parenthetical citations are when the

author(s) name and publication date both appear in

brackets, either within, or at the end of the sentence,
for example,
(Aman, 2019).
 For direct quotation
(Haile, 2019,p.132) or (Haile, 2019:132)
 Styles of Referencing…..

 If you are paraphrasing from a source, you are

encouraged but not required to include the page
number.
 Introducing citation with a “signal phrase’ that
includes the author
 Example: According to Solomon (2019) policy
implementation is xxx.
 Introducing citation with the author and page
number
 Example: According to Solomon (2019) policy
implementation seems to be weaker because it was
not outlined and planed properly (P.112).
 Styles of Referencing…..

 If the author’s name is not in the signal phrase,

enclose it in parentheses at the end of the
information.
 Example. Example: policy is implementation is xxx

(Solomon, 2007).
 If you have used a direct quote, give the page
number as well.
 Example. “Policy implementation seems to be
weaker because it was not outlined and planed
properly” (Solomon, 2007, P.112).
 Styles of
78
Referencing…..
The work has two authors
 Give both authors in the body of the paper or in parentheses.
Use “&” between the names in the parentheses. Give the date
(and page number for a quotation).
Example: We can identify students with high linguistic
intelligence as those who learn best by speaking, hearing or
seeing words (Beachner & Picket, 2018).
Or
 According to Beachner and Picket (2018) students with high
linguistic intelligence tend to “think in words rather than
pictures” (p. 17).
 Styles of Referencing…..
79

A group or organization is the author

 Use the name of the organization in place of the
author. Example:
Narrative: First use in text
 According to World Health Organization (WHO, 2020)……

Narrative: Subsequent uses

WHO (2020) states that………….
According to MoE (2009) xxxxxxx
Parenthetical: First use in text
……………………….(World Health Organization [WHO], 2020)
Parenthetical: Subsequent uses
……………………….(WHO, 2020)
Gardening can help kids develop social skills, develop bonds in
 Styles of Referencing…..
80

Two or more works have the same author and the

same publication year.
 Label the works a, b, etc. after the year and include

those letters in the in-text documentation.

 Be sure the same labels are applied in the references

page.
Example:
Schachner (2017a) or (Schachner, 2017a)
Schachner (2017b) or (Schachner, 2017b)
Reference lists
Journal Articles
Anderson, M. (2018). Getting consistent with consequences. Educational Leadership,
81 76(1), 26-33

Konishi, C. & Hymel, S. (2014). An attachment perspective on anger among

adolescents. Merrill-Palmer Quarterly, 60(1), 53-79.
Pambreni, Y., Khatibi, A., Azam, S., & Tham, J. J. M. S. L. (2019). The influence of total
quality management toward organization performance. Management Science
Letters, 9(9), 1397-1406.
Periodicals
Author, A.A., Author, B.B., & Author C.C. (year). Title of Article. Title of periodical, xx, pp. x –
y.
News paper
Schwartz, J. (1993, September 30). Obesity affects economic, social status. The Washington
Post, pp. A1 – A4.
 If online,
Schwartz, J. (1993, September 30). Obesity affects economic, social status. The New York
Times. Retrieved from http://www.nytimes.com
For a chapter in a book
Author, A. A., & Author, B. B. (2012). Title of chapter. In A. Editor, B. Editor, & C.
Editor (Eds.), Title of book (pp. xxx – xxx). Location: publisher.
Or
Author, A. A., & Author, B. B. (2012). Title of chapter. In A. Editor, B. Editor, & C.
Editor (Eds.), Title of book (pp. xxx – xxx). Location: publisher. Retrieved from
 Reference book
Creswell, J. W. (2014). A concise introduction to mixed methods research.
SAGE publications.
82
Prasad, L. M. (2020). Principles and practice of management. Sultan Chand
& Sons.
Saunders, M., Lewis, P., & Thornhill, A. (2016). Research methods for
business students. Pearson Publications
Cowie, H. (2019). From birth to sixteen: Children's health, social, emotional and
linguistic development (2nd ed.). Routledge
VandenBos, G. R. (Ed.). (2007). APA dictionary of psychology. Washington, DC: American
Psychological Association.
Doctoral Dissertation and Master’s Theses
A) If available from a database
Author, A. A. (2009). Title of Doctoral dissertation or master’s
thesis (Doctoral dissertation or master’s thesis). Retrieved
from Name of database. (Accession or Order No.)
For unpublished dissertation or thesis.
Author, A. A. (2003). Title of Doctoral dissertation or master’s thesis
(Unpublished doctoral dissertation or master’s thesis). Name of
Institution, Location.
 Key differences between Harvard and APA styles

83
 Chapter 8
Data Preparation, Analysis and
Interpretation
 Data Preparation For Analysis

85

Step 1: Questionnaire Checking

 Questionnaire checking involves a check of

all questionnaires for completeness and

interviewing quality.
 Often these checks are made while
fieldwork is still underway.
 If the fieldwork was contracted to a data–

collection agency, the researcher should

make an independent check after it is over.
86

A questionnaire returned from the field may be

unacceptable for several reasons.
 Parts of the questionnaire may be incomplete

 The pattern of responses may indicate that the

respondent did not understand or follow the

instructions.
 The responses show little variance.

 For example, a respondent has checked only 4s

on a series of 7-point rating scales.

 The returned questionnaires are physically
incomplete: one or more pages are missing.
 The questionnaires are answered by someone who

does not qualify for participation.

 Step 2: Editing
87
 Editing is the review of the questionnaires with the
objectives of increasing accuracy and precision.
 It consists of screening questionnaires to identify
illegible, incomplete, inconsistent, or ambiguous
responses.
 Responses may be illegible if they have been poorly
recorded.
 Unsatisfactory Responses are commonly handled
by returning to the field to get better data, assigning
missing values, or discarding unsatisfactory
respondents.
 Returning To The Field: The questionnaires with
unsatisfactory responses may be returned to the field,
where the interviewer(s) re-contact the respondents.
 Step 3: Coding
88

 Coding is assigning a code, usually a number, to each

possible response to each question.
 For example, the sex of respondents may be coded as
1 for Females and 2 for males.
 Do You Have A Currently Valid Passport?
1. Yes 2. No: For this question, a “Yes “response is coded 1, and
a “No” response 2.
 A record consists of related fields, such as sex,
marital status, age, household size, occupation, and so
forth.
 This means that codes are assigned before fieldwork is
conducted.
 If the questionnaire contains unstructured questions,
codes are assigned after the questionnaires have been
 Step 4: Transcribing
 Transcribing data involves transferring the coded data
90
from the questionnaire or coding sheets onto the disks or
magnetic tapes or directly into computers by
keypunching.
 Besides keypunching, the data can be
transferred by using mark sense forms, optical
scanning, or computerized sensory analysis.

Step 5: Data Cleaning

 Data cleaning includes consistency checks and
treatment of missing responses.
 Although preliminary consistency, checks have
been made during editing, the checks at this
stage are more thorough and extensive, because
they are made by computer.
 Every research uses data analysis.
 Although collecting data is important, there is no
point in the collection itself.
 One cannot simply collect data and present it as

research.
 Research data is not ‘self-explanatory’.

 Analysis is required
 Analysis is the most rewarding part of a research
project.
 There is excitement as you finally understand the

significance of your data

 Data analysis is not a single ‘thing’ or
process;
 It is a collection of methods that we can
apply to the data we have collected.
 Analysis is the process of working with the data to
describe, discuss, interpret, evaluate and explain it in
terms of the research questions or hypothesis.
 ANALYSIS means the ordering, manipulating, and
summarizing of data to obtain answers to research questions.
 Its purpose is to reduce data to intelligible and interpretable
form so that the relations of research problems can be studied
and tested
 It ranges from very simple summary statistics to extremely
complex multivariate analyses.
 Some of the primary purposes of analysis are to:
 Measure
 make comparisons
 Explore
 make forecasts
 Test hypotheses
 Explain
 examine relationships
 Construct concepts and theories.
93
 INTERPRETATION gives the results of analysis,
makes inferences pertinent to the research relations
94
studied, and draws conclusions about these relations
 There are two kinds of statistics:
 DESCRIPTIVE STATISTICS – allows the
researcher to describe the population or
sample used in the study.
 INFERENTIAL STATISTICS – draws inferences
from sample data and actually deals with
answering the research questions postulated
which are, in some cases, cause and effect
relationship.
95
96
97
98
Inferential Statistics: Pearson Correlation
 The Pearson correlation coefficients are appropriate for interval –and –
ratio scaled variables, and the spearman rank or the Kendall’s Tau
coefficients are appropriate when variables are measured on an ordinal
scale.
 Any Bivariate correlation can be obtained by clicking the relevant
menu, identifying the variables, and seeking the appropriate parametric
or nonparametric statistics.
 The Chi-Square Test- is Independence determines whether there is an
association between categorical variables (i.e., whether the variables
are independent or related). It is a nonparametric test. This test is also
known as: Chi-Square Test of Association
 Example: a scientist wants to know if education level and marital status are
related for all people in some country.
 T-test - A t-test is a type of inferential statistic used to determine if
there is a significant difference between the means of two groups
 Bi-variate Regression
 Multi-variate Regression.
 Bivariate Regression Analysis involves analysing two variables to establish the
strength of the relationship between them. The two variables are frequently
denoted as X and Y, with one being an independent variable (or
explanatory variable), while the other is a dependent variable (or
outcome variable).
10
0
10
1
The format of the research
report
 Preliminary Pages: anything before chapter one.
Contains:
 Ch 1-3 of the
Title pages, declaration page, approval,
acknowledgment, acronyms, abstract,research
TOC, list of
tables/figures/boxes, etc.
proposal.
 Main body:
NB: Language
 Chapter 1: Introduction
changes from
 Chapter 2: Literature review
future to
 Chapter 3: Methodology
past/present
 Chapter 4: Data Analysis and interpretation
tenses
 Chapter 5: Main findings,
Conclusion and Recommendations
 List of References and
 Annexes – data gathering instruments, summary of raw
data in a table, pages of documents, results tables, etc.
104