You are on page 1of 93

MOI UNIVERSITY

SCHOOL OF BUSINESS & ECONOMICS


INTRODUCTION

• Business Research- The systematic and objective process of


gathering, recording and analyzing data for aid in making business
decisions.
• Systematic- not intuitive and haphazard, it is scientific.
• Objective- should be unbiased and devoid of personal interest.
• Importance- to facilitate decision making in all aspects of business
including finance, marketing, personnel, operations, production etc. BR
generates and provides necessary qualitative and quantitative
information upon which to base decisions.

Scope of BR
• Limited to one’s definition of “business”
• Although business researchers are specialized, the term business
research encompass all functional specialties.
• While researchers in different functional areas may investigate different
phenomena, they are comparable to one another because they use
similar research methods.
TYPES OF RESEARCH
• Broadly there are two types of research: basic or pure research and
applied research.
• Basic/ pure research- research that is intended to expand the
boundaries of knowledge itself or to verify the acceptability of a given
theory.
• The research does not directly involve the solution to a particular
pragmatic problem and its findings are not immediately implemented.
• Though basic research does not solve current problems, good theories
inform practice in the long run.
• Applied Research- research undertaken to answer questions about
specific problems or to make decisions about a particular course of
action or policy decision.
• The techniques and procedures utilized by basic and applied research
are similar. Both employ scientific method to answer the questions at
hand.
• Scientific method refers to techniques or procedures used to analyze
empirical evidence in an attempt to confirm or disprove prior
conceptions.
TYPES OF RESEARCH cont..
• Though there are two broad types of research, other types of research can
be derived from various classifications.
EXAMPLES
1. Based on reasoning approach, deductive vs Inductive research
deductive approach- research approach involving testing of a theoretical
proposition by the employment of a research strategy specifically designed
for the purpose of its testing.
Inductive approach- research approach involving the development of a theory as a
result of the observation of empirical data.
2. Based on the type of data collected quantitative vs qualitative research
quantitative research- based on measurement of quantity or amount and is
applicable to phenomena that can be expressed in terms of quantity.
qualitative research- applicable in behavioural science where the motive is to
uncover the underlying motives of human behaviour.
3. Based on level of abstraction conceptual vs empirical research
conceptual research is that related to some abstract ideas or theory. It is used by
philosophers to develop new concepts or reinterpret existing ones.
empirical research relies on experience or observation alone, often without due
regard for system or theory.
MANAGERIAL VALUE OF BUSINESS RESEARCH

• The prime managerial value of business research is reduction of


uncertainty by providing information that improve decision making
process.
• The decision making process associated with the development
and implementation of a strategy involves four interrelated stages:
1 Identifying problems/ threats or/ and opportunities.
2 Diagnosing and assessing problems or opportunities
3 Selecting and implementing a course of action.
4 Evaluating the course of action.
• BR by supplying managers with pertinent information, may play
an important role by reducing managerial uncertainty in each of
these stages.
NEED FOR BUSINESS RESEARCH
• A manager faced with more possible courses of action faces the initial
decision of whether or not research should be conducted.
• The determination of the need for research centres on:
1. Time constraints- conducting research systematically takes time, yet
some decisions are urgent and have to be made immediately leaving no
time for research. As a consequence decisions are made without
adequate information or thorough understanding of the situation.
2. Availability of Data- Where managers lack the information, research
should be considered. If data cannot be obtained, research cannot be
conducted.
3. Nature of decision- The value of business research will depend on the
nature of the managerial decision to be made. Routine tactical decisions
with low investment requirements may not warrant substantial research
expenditure.
4. Benefits vs cost- When deciding whether to make a decision without
research or postpone the decision in order to conduct the research, one
should consider the value of the information against the cost of research.
AN OVERVIEW OF THE RESEARCH PROCESS
• Business research can take many forms, but systematic enquiry is
the common thread.
• Like other forms of scientific inquiry, BR is a sequence of interrelated
and often overlapping activities.
• The pattern of the process is as follows:
1. Problem definition
2. Research design planning
3. Sample planning
4. Collecting the data
5. Processing and analyzing the data
6. Formulating conclusions and preparing the report.
FORMULATION AND IDENTIFICATION OF RESEARCH
PROBLEM
• Formulation and clarifying the research topic is the starting point of
your research project.
• Once you are clear about the problem, you will be able to choose the
most appropriate research design, data collection and analysis
techniques.
• However, properly and completely defining a business problem is
easier said than done. This is because when an opportunity or a
threat is discovered, managers may only have a vague insights about
a complex situation.

Generating Research Ideas


• If you have not been given an initial research idea, there is a range of
techniques that can be used to find and select a topic that you would
like to research.
• The techniques can broadly be classified into two categories: a)
rational thinking and b) creative thinking. Though you may choose
either of the two in generating research ideas, an integration of both
techniques is recommended.
Rational Thinking
• Examine your own strengths and interests.
• Look at past project titles
• Discussion
• Search the literature

Examining own Strengths and Interests


• Choose a topic in which you are likely to do well, and if possible, already have
some academic knowledge.
• Choose a topic from your own specialization. This will provide you with the
opportunity to display clearly your depth of knowledge and enthusiasm.

Looking at Past Project Titles


• Scan a list of past project titles for anything that captures your imagination.
• Note down titles that capture your attention and thoughts you have about the
title in relation to your research idea.
• Based on this think of new ideas in the same general area that will enable you to
provide fresh insights.
• NB. The fact that a project is in your library is no guarantee of the quality of
arguments and observations it contains.
Discussion
• Discussion with colleagues, lectures, friends, professionals etc. may
be good source of possible project ideas.
• Always note down discussed ideas.

Searching The Literature


• Three types of literature are good sources of research ideas a)
articles in academic and professional journals, b) reports, c) books.
• Of particular use are articles in in academic journals. These articles
contain both considered review of the state of knowledge in that
topic area and pointers towards areas where further research need
to be undertaken.
• Reports may also be of use. Recent reports are up to date and often
contain recommendations for further work.
• Books by contrast are less up to date than other written sources.
They however, contain a good overview of research that has been
undertaken, which may suggest ideas to you.
Creative Thinking
• Keeping a notebook of ideas
• Exploring personal preferences using past projects
• Relevance trees
• Brainstorming

Keeping a notebook of ideas


• This involves noting down any interesting research ideas as you think
of them and what sparked off your thought.
• These ideas can then be pursued using more rational thinking
techniques later.

Exploring Personal Preferences Using Past Projects


• Raymond (1993) suggested a system of generating possible ideas by
exploring past projects from your university:
1) Select six projects that you like.
2) For each of these six projects note down your first thoughts in
response to three questions:
a) What appeals to you about the project?
Creative Thinking cont..
b) What is good about the project?
c) Why is the project good?
3) Select three projects that you do not like.
4) For each of these three projects note down your first thoughts in response to
three questions.
a) What do you dislike about the project?
b) What is bad about the project?
c) Why is the project bad?
• You now have a list of what you consider to be excellent and what you consider
to be poor projects.
• By examining those projects you will begin to understand those project
characteristics you consider important and with which you feel comfortable.
You will also have identified those you are not comfortable with and which
should be avoided.
• These can be used as parameters against which to evaluate possible research
ideas.
Creative thinking cont..
Relevance Trees
• Here you start with a broad concept from which you generate further,
usually more specific topics.
• Each of these topics forms a separate branch from which you can
generate further more detailed sub branches.
• As you proceed down the sub branches more ideas are generated
and recorded.
• These can then be examined and a number selected and combined to
provide a research idea.

Brainstorming
• Best undertaken with a group of people though it can be done
individually.
• Moody (1983) suggested the following brainstorming procedure:
1) Define your problem (ideas you are interested in) as precisely as
possible.
2) Ask for suggestions relating to the problem.
Brainstorming cont..

3) Record all suggestions observing the following rules:


- No suggestion should be criticised or evaluated in any way before
all ideas have been considered.
- All suggestions, however wild, should be recorded and considered.
- As many suggestions as possible should be recorded.
4) Review all the suggestions and explore what is meant by each.
5) Analyze the list of suggestions and decide which appeal to you most
as research idea.
TURNING RESEARCH IDEAS INTO RESEARCH
PROJECTS
Writing Research Questions
• One of the key criteria of your research success will be whether you have
a set of clear conclusions drawn from the data you have collected.
• The extent to which you can do that will be determined largely by the
clarity with which you will have posed your initial research questions.
• Defining research questions is however not a straightforward matter.
• At all costs avoid the following type of questions:
- with “yes” or “no” answer
- that are too easy to answer
- that are too difficult to answer
- that will not generate new insights.
• Questions that do not generate new insight raises the question of the
extent to which you have consulted the relevant literature.
• Though replication of research is acceptable, it is not legitimate to display
your ignorance of literature.
TURNING RESEARCH IDEAS INTO RESEARCH
PROJECTS cont..
• It is a useful starting point in the writing of the research questions to
begin with one general focus question that flows from your research
idea. This may lead to several more detailed questions or the
definition of research objectives.

• Though writing research questions may be your own concern, work


closely with your research supervisors in crafting research
questions to avoid the pitfalls of the questions that are too easy or
too difficult or have been answered before.

• Discussing your area of interest with your project supervisors will


lead to your research questions becoming much clearer.
EXAMPLES OF RESEARCH IDEAS AND DERIVED
RESEACH QUESTIONS
I. Job recruitment via internet
Q. How effective is recruiting for new staff via internet in comparison
with traditional methods?
I. Advertising and share prices
Q. How does the running of a TV advertising campaign designed to
boost the image of the company affect its share price?
I. Strategic capabilities and firm performance
Q. In what ways does strategic capabilities comprising of marketing,
marketing linking, IT, technology and management, affect firm
performance?
I. The future of stock brokers in Kenya
Q. Given the recent closures of stock brokers in Kenya, what
strategies are players in the capital markets putting in place to
ensure future viability of stock brokers?
WRITING RESEARCH OBJECTIVES
• Your research may begin with a general focus research question that
then generates more detailed research questions, or you may use
general research question as a base from which you write a set of
research objectives.
• Objectives are more generally acceptable to the research community as
evidence of researcher’s clear sense of purpose and direction.
• It is generally acceptable that research objectives leads to greater
specificity than research or investigative questions.
• Most researches conducted at Moi University, combine both research
questions and objectives.
• NB. The way research objectives are cast determines the research
design, conceptual framework and data analysis techniques.
PHRASING RESEARCH QUESTIONS AS RESEARCH
OBJECTIVES
Q. Why have organizations introduced team briefing?
O. To identify organization’s objectives for team briefing schemes.
Q. How can the effectiveness of team briefing schemes be measured?
A. To establish suitable effectiveness criteria for team briefing schemes.
Q. Has team briefing been effective?
O. To describe the extent to which the effectiveness criteria for team
briefing have been met.
Q. How can the effectiveness of team briefing be explained?
O. a) To determine the factors associated with the effectiveness criteria
for team briefing.
b) To estimate whether some of those factors are more influential
than others.
Q. Can the explanation be generalized?
O. To develop an explanatory theory that associates certain factors with
the effectiveness of team briefing schemes.
NB. Relevant theory should inform your definition of research questions
and objectives.
RESEARCH PROPOSAL
• Writing a research proposal is crucial part of research process.
• Research proposal is required when applying for research funding, or
seeking approval to carry out research from an academic panel/
committee.

THE IMPORTANCE OF RESEARCH PROPOSAL

1. Organizing your ideas- clarifies thoughts and helps you organize


your ideas into a coherent statement of your research intent.

2. Convincing your audience- convinces the audience that what you


propose to do, can actually be done and completed within the
proposed time frame.

3. Contracting with your client- Form part of the contract, where


research is being done for commercial purposes.
CONTENT OF AN ACADEMIC RESEARCH PROPOSAL
1. Title
• First attempt at the report title. It may change as your research work
progresses.
• The title should closely mirror the content of your proposal.
• A good research title should capture independent variable (IV)
dependent variable (DV) relationship.

2 Background
• Give a description about the study concepts as captured by the title
as well as the concept’s relationships.
• As you describe the concepts, demonstrate your knowledge of the
relevant literature by citing notable authorities.
• Clarify where your proposal fits within the existing literature.

3. Statement of the Problem


• Should capture four salient issues in prose form:
ACADEMIC RESEARCH PROPOSAL cont..
3. Statement of the Problem cot..
a) Importance of the study- demonstrate to the reader why you feel the
research you are planning is worth the effort.
b) Symptoms of the problem- delineate how the problem has manifested
itself in a manner the reader feels indeed a study is warranted.
c) Knowledge gap- Show a clear link between the previous work done in
the field of your interest and where it departs from the content of your
proposal.
d) Issues to be addressed- Point out the issues the study wishes to
address.
• NB The above should be done within one page.

4. Research Questions and Objectives


• The statement of the problem should lead smoothly into your research
questions and objectives.
• These should leave the reader in no doubt as to precisely what is that your
research seeks to achieve.
ACADEMIC RESEARCH PROPOSAL cont..
4. Research Questions and Objectives cont..
• Ensure that your objectives are precisely written and will lead to
observable outcomes.
5. Significance of the study
• Briefly demonstrate the significance of the study to the relevant users e.g.
academia, industry, government policy makers etc.
6. Scope of the study
• Delineate the limits of your study. In a nutshell say what your study will
include and what it will not include.
7. Organization of the Study
• You may briefly describe the chapters of your proposal and what is
contained in each.
8. Methodology
• Details precisely how you intend to achieve the objectives of your study.
• It addresses the issue of research design, data collection and data
analysis.
ACADEMIC RESEARCH PROPOSAL cont..

8. Methodology cont..
• Research design explains the general way in which you intend to
carry out the research. Will it be on a survey, interviews (case study),
examination of secondary data or a combination of methods?
• It is essential to explain why you have chosen your approach. Your
explanation should be based on the most effective way of meeting
your research objectives.
• The research design therefore, gives an overall view of the method
chosen, and the reasons for that choice.
• Under data collection, you specify your population of interest,
describe sampling techniques as well as specify sample size. You
also specify how data will be collected and the instruments to be
used for data collection.
• Finally, you should specify data analysis techniques, depending on
your research objectives.
• Where there are ethical issues, include a statement outlining how you
will address and adhere to ethical guidelines.
ACADEMIC RESEARCH PROPOSAL cont..
9. Time Scale
• This will help you and your reader to decide on viability of your research
proposal.
• Divide your research plan into stages. This will give you a clear idea as
to what is possible in the given time scale.
• Use a gannt chart to produce a time plan schedule.

10. Budget
• Conducting research costs money. This may be for travel, subsistence,
collecting data, analysis etc.
• Think through expenses involved and ensure you can meet them.

11. References
Include references of all materials cited in the body of the proposal.
• Use one referencing format consistently. Common referencing formats
include, Harvard, APA, Chicago etc.
ACADEMIC RESEARCH PROPOSAL cont..

12. Appendices
• Attach appendices that are relevant to the study e.g. questionnaire,
interview guide etc.
13. Declaration
• Indicated by Roman page i. The candidate declares that the proposal
is her/ his original work and has not been presented before in any
institution for examination.
• It is signed by both the candidate and the two supervisors.
14. Dedication and Acknowledgement
• If the researcher wishes to dedicate the study to someone they can
do so in the second Roman page ii and acknowledge support given in
Roman page iii.
15. Abstract
• Also indicated by Roman paging and gives a summary of the
research objectives, methodology and expected results.
16. Table of Contents, List of Tables & List of Figures
MOI UNIVERSITY RESEARCH FORMATTING
• Font- 12, Times Roman, one page double spacing, Right hand bottom
paging.
• No page number on the title page.
• Roman paging on material before Introduction.
• Arabic paging from Introduction onwards.
• Harvard citation format.
• Margins- 1” top, bottom, right, 1.5’’ left
LITERATURE REVIEW
Importance of Literature review
• Helps you to generate and refine research ideas.
• Critical literature review is part of the research project (in Moi University
it forms part of the academic proposal). It helps you demonstrate
awareness of the current state of knowledge in your subject, its
limitations, and how your research fits in the wider context.
• Helps to refine further research questions and objectives.
• To highlight research questions that have been looked implicitly in
research to light.
• To discover explicit recommendations for further research. These can
provide you with a superb justification for your own research questions
and objectives.
• It helps you to avoid repeating work that has already been done.
• To discover and provide an insight into research approaches,
strategies and techniques that may be appropriate to your own
research questions and objective.
LITERATURE REVIEW cont..

Critical Literature Review


• In the context of literature review “critical” refers to the judgement
you exercise. It describes the process of providing detailed and
justified analysis and commentary on the merits and faults of the
key literature within your chosen area.
• According to Dee (2000) critical literature should:
• Refer to work by recognized experts in your chosen area.
• Consider and discuss work that supports and work that opposes
your ideas.
• Make reasoned judgements regarding the value of others work to
your research.
• Support your arguments with valid evidence in a logical manner.
• Distinguish clearly between fact and opinion.
LITERATURE REVIEW cont..
Critical Literature Review cont..
Content of Critical Review
• Key academic theories within your chosen area.
• Demonstrate your knowledge in the chosen area is up to date.
• Show how your research relates to previous published research.
• Assess the strengths and weaknesses of previous work, including omissions or
bias, and take these into account in your arguments.
• Justify your arguments by referencing previous work.
• By fully acknowledging the work of others you will avoid charges of plagiarism
and associated penalties.
NOTE
• When drafting your review, focus on your research questions and objectives.
Ask how far the literature goes in answering your research questions and how
your review relates to your objectives.
LITERATURE REVIEW cont..
Justification of Critical Literature Review
• Knowledge doesn’t exist in a vacuum, and your work only has value in relation
to other peoples’. Your work and your findings will be significant only to the
extent that they are the same as, or different from other peoples work and
findings.
• Critical literature review will therefore form the foundation on which your
research is built.
• In some research projects, literature is used to help you to identify theories and
ideas that you will test using data. This is known as deductive approach in
which you develop a theoretical or conceptual framework which you
subsequently test using data.
• Other research projects you explore your data and develop theories from them
that you subsequently relate to the literature. This is known as inductive
approach, and although your research has a clearly defined purpose with
research questions and objectives, you do not start with any pre determined
theories or conceptual frameworks.
• Under inductive approach when you write your critical review, you need to show
how your findings and theories you have developed relate to the work that has
been done before, thereby demonstrating that you are familiar with what is
already known about your research topic.
STRUCTURE OF CRITICAL REVIEW

• Although there is no structure that your critical review should take,


the following guidelines are important:
1. Start at a more general level before narrowing down to your
specific research questions and objectives.
2. Provide a brief overview of key ideas.
3. Summarize, compare and contrast the work of key writers.
4. Narrow down to highlight the work most relevant to your research.
5. Provide a detailed account of your findings of this work.
6. Highlight the issues where your research will provide fresh
insights.
7. Lead the reader into subsequent sections of your project report
which explore these issues.
• Critical literature review should link together different ideas found
in the literature into coherent and cohesive argument which set in
context and justify your research.
• Should relate to the research questions and objectives showing a
clear link between them and empirical work to follow.
SOURCES OF LITERATURE
• Literature sources can be divided into two categories: Primary
(published and unpublished), secondary and tertiary.
• Primary sources- Reports, Theses, Conference papers, Institutional
reports, Government publications, Unpublished dissertations and
manuscripts.
• Secondary- Newspapers, Books, Journals, Internet.
• Tertiary- Indices, Abstracts, catalogues, Encyclopaedias, Dictionaries,
Bibliographies and citation indexes.
• The different categories of literature resources represents flow of
information from the original source.
• As information flows from primary to secondary to tertiary sources, it
becomes less detailed and authoritative but more accessible.
• Primary literature sources (a.k.a. grey literature) are the first
occurrence of a piece of work.
• Secondary literature sources are the subsequent publication of
primary literature.
• Tertiary literature sources (a.k.a. search tools) are designed to either
help to locate primary or secondary literature or introduce a topic.
• Most research projects make greatest use of secondary data.
CONDUCTING LITERATURE SEARCH, OBTAINING
AND EVALUATING LITERATURE

• Literature review is conducted using a variety of approaches:


1. Searching using tertiary literature sources.
2. Obtaining relevant literature referenced in books and journal
articles you have already read.
3. Scanning and browsing secondary literature in your library.
4. Searching using the internet.
• Once obtained, the literature must be evaluated for its relevance
to your research questions and objectives.
• In evaluating literature two questions are often asked: How do I
know what am reading is relevant? AND How do I know when I
have read enough?
• Although there are no ways of answering these questions the
following advise is helpful:
1. Read all literature that is closely related to your research
questions and objectives.
CONDUCTING LITERATURE SEARCH, OBTAINING
AND EVALUATING LITERATURE cont..

2. Make notes about the relevance of each item as you read it and
the reasons you came to your conclusion.
3. Check with your supervisors what constitutes acceptable amount
of reading in both quantity and quality.
4. When further searching provides mainly references to items you
had already read, it may imply you have now read enough.

RECORDING LITERATURE
• In addition to taking notes you should also record bibliographic
details, brief summary of content, and supplementary information.
• Though some project reports require you include a bibliography,
i.e. all relevant items you consulted, Moi University requires a list
of references for those items referred to directly in the text ( Use
Harvard format).
THEORY BUILDING
• Theory- a coherent set of general propositions used to explain the
apparent relationships among certain observed phenomena.
Theories allow generalizations beyond individual facts or situations.
• Theory development is essentially a process of describing
phenomena at increasingly higher levels of abstraction.
• The things we observe can be described as concepts.
• A concept is a generalized idea about a class of objects; an
abstraction of reality and it is the basic unit of theory development.
• Concepts are the building blocks for a theory e.g. in organization
theory, “leadership”, “productivity”, “morale”, etc are concepts. In
strategy theory, “competitive advantage”, “capabilities”,
“competences”, “drivers” etc are concepts. In theory of finance,
“asset”, “premium”, “price” etc are concepts.
• Concepts abstract reality i.e. concepts are expressed in words that
refer to various objects or events e.g. “asset” is an abstract term that
in reality refer to a specific furniture, motor vehicle or machinery.
• Concepts however, may vary in degree of abstraction and it is
possible to discuss concepts at various levels of abstraction.
THEORY BUILDING cont..
• Moving up the ladder of abstraction, the basic concept becomes
more abstract, wider in scope and less amenable to measurement.
• Note. Ladder of abstraction- organization of concepts in sequence
from the most concrete and individual to the most general.
• The basic or scientific business research operates at two levels: on
an abstract level of concepts (and propositions) and on empirical
level of variables (and hypothesis).
• Abstract level- in theory development, the level of knowledge
expressing a concept that exists only as an idea or a quality part
from an object.
• Empirical level- level of knowledge that is verifiable by experience
or observation. At an empirical level we experience reality, i.e. we
observe or manipulate objects or events.
• Researchers are concerned with the observable world or reality.
Theorists translate their conceptualization of reality into abstract
ideas. Thus theory deals with abstraction. Things are not the
essence of theory but ideas. Only when we explain how concepts
relate to other concepts do we begin to construct theories.
KEY TERMS IN THEORY BUILDING
PROPOSITIONS
• Concepts are the basic units of theory development. However, theories require
an understanding of relationships among concepts.
• Propositions are statements concerned with the relationships among concepts.
It explains the logical linkage among certain concepts by asserting a universal
connection between concepts.
• A proposition states that every concept about an event or thing either has a
certain property or stands in a certain relationship to other concepts about the
event or thing.
• In abstraction scale concepts are at one level of abstraction. Investigating
propositions requires that we increase our level of abstract thinking. When we
think about theories we are at the highest level of abstraction because we are
investigating the relationship between propositions. Theories are networks of
propositions.
CONSTRUCTS
• A construct is an image or idea specifically invented for a given research and/ or
theory building purpose.
• We build constructs by combining the simpler concepts, especially when the
idea or image we intend to convey is not directly subject to observation.
KEY TERMS IN THEORY BUILDING cont..
SCIENTIFIC METHOD
• Set of prescribed procedures for establishing and connecting theoretical
statements about events and analyze empirical evidence in an attempt to
conform or disapprove prior conceptions.
• There is no consensus concerning exact procedures for scientific method
but basically it includes empirical testability.
• Empirical means verifiable by observation, experimentation or
experience.
• The process of empirical verification cannot be divorced from theory
development.
PROPOSITIONS AND HYPOTHESIS
• Research literature disagrees about the meanings of the terms
proposition and hypothesis.
• A proposition as earlier defined is a statement about concepts that may
be judged as true or false if it refers to observable phenomena.
• When a proposition is formulated for empirical testing it is called a
hypothesis. As a declarative statement a hypothesis is of a tentative and
conjectural nature.
KEY TERMS IN THEORY BUILDING cont..
CONCEPTUAL FRAMEWORK
• Graphical depiction of Interrelationship between concepts and constructs.
• It is the basis of hypothesis, where the hypothetical constructs are presumed to
exist but must wait further testing so as to make inferences from the data.
OPERATIONAL DEFINITIONS
• Definition stated in terms of specific testing and measurement criteria. In
research it serves the same purpose as definitional.
• The terms must have empirical referents (i.e. must be countable, measurable, or
observable).
• The definition must specify characteristics and how they are to be observed.
• Operational definitions may vary depending on purpose and the measure you
choose.
• While operational definitions are needed in research they also present some
problems. They are narrow measures of concepts and constructs and the
measurement may vary from one researcher to another.
• Where constructs have few referents you may formulate operational measures
that are not true labels.
RESEARCH DESIGN
• There are many definitions of research design, but no one definition imparts
the full range of important aspects.
Examples
1. The research design constitutes the blue print for collection, measurement,
and analysis of data. It aids the scientist in the allocation of his limited
resources by posing crucial choices: Is the blue print to include experiments,
interviews, observation, the analysis of records, simulation or some
combination of these? Are the methods of data collection and research
situation to be highly structured? Is an intensive study of a small sample more
effective than a less intensive study of a large sample? Should the analysis be
primarily quantitative or qualitative? (Philip, 1971).
2. Research design is the plan and structure of investigation so conceived as to
obtain answers to the research questions. The plan is the overall scheme or
programme of the research. It includes an outline of what the investigator will
do from writing the hypotheses and their operational implications to the final
analysis of data. A structure is the framework, organization, or configuration of
..the relations among variables of a study. A research design expresses both
the structure of the research problem and the plan of investigation used to
obtain empirical evidence on relations of the problem.
RESEARCH DESIGN CONT..
• The definition differ in detail but together they give essentials of
research design.
• The research design is:
- an activity and time based plan.
- always based on the research question/ objectives.
- guides the selection of sources and types of information.
- framework for specifying the relationships among study variables.
- outlines procedures for every research activity.
• Before settling on a research design one is guided by research
philosophy, research approaches and time horizons. The design
chosen on other hand determines the method of data collection.
RESEARCH PHILOSOPHY
• Depends on the way we think about knowledge development, which
indirectly affects the way we do research.
• There are three views about research: (1) positivism (2) interpretivism
(3) realism.
Positivism
• The researcher assumes the role of an objective analyst, making
detached interpretations about collected data.
• Emphasize is put on highly structured methodology to facilitate
replication and on quantifiable observations that can be analyzed
statistically.
• It assumes that the researcher is independent of and neither affects nor
is affected by the subject of the research.
• Common in physical science and today it is also employed in social
science like business.
RESEARCH PHILOSOPHY cont..
Interpretivism
• Critiques of positivism argue that in social world e.g. business and
management, things are so complex as to be theorized by finite
laws as in physical science.
• Rich insights into this complex world are therefore lost if the
complexity is reduced entirely to a series of law like generalizations.
• According to interpretivists, it is necessary to explore the subjective
meanings motivating peoples action in order to be able to
understand them through the process of social constructionsm.
• Social constructionsm views reality as being socially constructed
and therefore people place interpretations on situations in which
they find themselves, and these interpretations affect their actions
and the way they socially interact with others.
• Interpretivist therefore seeks to understand the subjective reality of
those that they study, in order to be able to make sense of and
understand their motives, actions and intentions in a way that is
meaningful for those research participants.
RESEARCH PHILOSOPHY cont..
Realism
• Based on the belief that a reality exists that is independent of human
thoughts and beliefs.
• This implies that there are large scale social forces and processes
that affect people without their necessarily being aware of the
existence of such influences on their interpretations and behaviours.
• Realism therefore shares some philosophical aspects with
positivism e.g. those aspects related to external, objective nature of
macro society. It also recognises that people are not objects to be
studied in style of natural science.
• Realism as applied to study of human subjects, recognises the
importance of understanding peoples socially constructed
interpretations and meanings, or subjective reality, within the
context of seeking to understand broader social forces, structures or
processes that influence and perhaps constrain the nature of
peoples views and behaviours.
Note: Business research rarely falls into one of the approaches. It is
often a mixture between positivist and interpretivist, perhaps
reflecting the stance of realism.
TYPES/ CLASSIFICATIONS OF RESEARCH DESIGN
• Different research design often reflects the classification criteria used by
different authors.
• No simple classification system defines all variations of research
design.
Category Example
options

1.The degree to which the •Exploratory study


research questions have •Formal study
been structured and the
immediate objective of the
study.
2. Method of data collection •Monitoring
•Interrogative/ communication

3. Researcher control of •Experimental


variables •Ex post facto
RESEARCH DESIGN cont..
4. The purpose of the study •Descriptive
•Causal (explanatory)

5. Time Dimension •Cross sectional


•Longitudinal

6. The topical scope •Case study


•Statistical study (survey)

7. The research environment •Field setting (Quasi experiment)


•Laboratory research
•Simulation
8. The subject perceptions •Actual routine
•Modified routine
EXPLORATORY RESEARCH DESIGN
• Initial research conducted to clarify and define the nature of the
problem.
• It ensures that a more rigorous, more conclusive future study will not
begin with an inadequate understanding of the nature of the problem.
• The findings discovered through exploratory research would lead the
researcher to put emphasize in learning more about the particulars of
the findings in subsequent conclusive studies.
• Conclusive research, answers questions of fact necessary to determine
a course of action which is not the purpose of an exploratory study.
• Usually exploratory research provides greater understanding of a
concept, crystallizes problem rather than providing precise
measurement or quantification. It is therefore, largely qualitative.
• Exploratory research may be a single research investigation or a
series of informal studies intended to provide background information.
RESONS FOR CONDUCTING EXPLORATORY
RESEARCH
1. Diagnosing situation- Helps diagnose the dimensions of the
problems so that successive research projects will be on target.
2. Concept testing- testing something that acts as a proxy for a new or
revised program, product or service.
3. Discovering new ideas- Exploratory research is often used to
generate new ideas.

CATEGORIES OF EXPLORATORY RESEARCH


1. Experience survey- an exploratory technique in which individuals who
are knowledgeable about a particular research problem are surveyed.
2. Secondary data analysis- preliminary review of data collected for
another purpose to clarify issues in the early stages of research effort.
3. Pilot study- any small scale exploratory research project that uses
sampling but does not apply rigorous standards.
4. Focus group interview- an unstructured, free flowing interview with a
small group of people.
DESCRIPTIVE RESEARCH DESIGN
• It is concerned with finding out who, what, where, when or how much.
• E.g. research on strategy is descriptive when it measures, the types of
strategy, their characteristics, when they are used, who uses them, the
extent to which each is used and where they are used.
• However, the moment we try to answer the question of why does one
strategy produce better results or how one strategy relates with other
aspects of business, the design changes to causal (explanatory).
Descriptive design does not therefore, explain relationships.
• Many authors dismiss descriptive design by asking so what if you
describe a phenomena? Implying the design does not help you
establish relationships and make discoveries.
• However, descriptive research design is important because by
describing a phenomena, a basis for other discoveries is made. E.g. it is
after describing what different strategies are, you begin to infer
relationships that may exist between them and other business aspects.
DESCRIPTIVE RESEARCH DESIGN cont..
Statistics in Descriptive Research
• Measures of central tendency (mean, median, mode).
• Measures of dispersion (Standard deviation, variance, range).
• In complex descriptive designs, cross tabulations and bivariate correlations
may be used to describe relationships, although this does not imply causation.
• The above measures can be at one point in time or over along period of time
as in longitudinal studies.

CAUSAL (EXPLANATORY) RESEARCH DESIGN


• A causal research design is a type of non experimental investigation in which
researchers seek to identify cause- and- effect relationship by forming groups
of individuals/ objects in whom the independent variable is present or absent-
or present at several levels- and then determining whether the groups differ in
the dependent variable.
CAUSAL (EXPLANATORY) RESEARCH DESIGN cont..
• In this design the presumed cause is called the independent
variable (IV) or the predictor and the presumed effect is called the
dependent variable (DV) or the criterion. E.g. if we hypothesis that
quality products will have a significant effect on a company’s
performance, quality product is the independent variable and quality
product is the dependent variable.
• Though in experimental design causation is demonstrable in a
stricter sense, in business research the cause- effect relationship is
less explicit.
• In business research, we are more interested in understanding,
explaining, predicting and controlling relationships between
variables, than we are in discerning causes.
• The identification of IV and DV is often obvious, but at times the
choice is not clear. Where there is no clarity, check the degree to
which each variable may be altered. The relatively unalterable is the
independent. Check also the time order between the variables. The
independent variable precedes the dependent variable.
• The researcher can decide to include one or several independent
variables in the design. Similarly, the researcher can choose to
include one dependent variable or several.
• The initial step in causal research design is to speculate about the
causes or effect of the phenomenon that interests you.
CAUSAL (EXPLANATORY) RESEARCH DESIGN cont..
• Your speculations can be based on previous research findings and
theory as well as your own observations of the phenomenon.
• After the possible causes of or effects of a phenomena have been
identified, they should be incorporated in the statement of the
problem, research hypothesis, questions or objectives.
• Note: Causal design confirms or disapproves hypothesized
relationships. Where hypothesis are specific that mathematical form
of the relationship between predictor and criterion variables is
determinable, and the parameters and their strength can be estimated
by multivariate analysis, a causal design is recommended.
• Data Collection and Analysis Under Causal Design
• Data can be collected through many methods including, standardized
tests, questionnaires, interviews and observation. The data must be in
quantifiable form.
• The first step in a causal design, is to conduct exploratory data
analysis by computing descriptive statistics. The may include
measures of central tendency e.g. mean, mode, median and
measures of dispersion e.g. variance and standard deviation. Others
may include kurtosis and skew ness.
CAUSAL (EXPLANATORY) RESEARCH DESIGN cont..
Data Collection and Analysis Under Causal Design cont..
• The next step is to conduct correlations tests between variables to
establish or ascertain the nature and the magnitude of relationships.
• Finally, test the model for significance through inferential statistics.
The choice of significance test, depends in part on whether the
researcher is interested in comparing groups with respect to each
group mean scores, variance or median, or with respect to rank
scores or category frequencies.
• Selection of an appropriate test also depends on whether the
assumptions underlying the test being considered are satisfied or at
least not grossly violated.
CASE STUDY RESEARCH DESIGN
• Place more emphasize on a full contextual analysis of fewer events or
conditions and their relationships.
• It relies on detailed qualitative data usually analyzed through thematic
or conceptual content analysis.
• An emphasis on details provides valuable insights for problem solving,
evaluation and strategy.
• The details are secured through multiple sources of information
including, in depth interviews, observations and review of secondary
data.
• Although case studies are at times dismissed, as scientifically worthless
because of low external validity, they are significant since the unit of
study is part of the universal.
• Thus, a single well designed case study can provide a major challenge
to theory and provide a source of new hypothesis and constructs.
SURVEY RESEARCH DESIGN
• There is no consensus whether survey is a research design or method
of data collection.
• Survey research involves use of questionnaires or interviews to collect
data from sample that has been selected to represent a population to
which the findings of the data can be generalized.
• For generalizability, the data analysis is quantitative and sampling
should be free from bias.
• Since survey relies on questioning respondents, the quality and quantity
of information secured depends heavily on the ability and willingness of
respondents to cooperate.
• Even if respondents participate, they may not have the knowledge
sought or may not have opinion on the topic of concern. At times
respondents may express some opinion even when they do not have
one. This makes it difficult for researchers to know how true or reliable
the answers are.
• Respondents may also interpret questions differently from what was
intended or even at times intentionally mislead the researcher by giving
false information.
• Despite, these weaknesses, communicating with research subjects is a
principal method of management research.
VARIABLES
• In practice the term variable is used as a synonym for construct or
property being studied. It is also a symbol for which we assign
numerals or values.
• The numerical value attached to a variable is based on its
properties.
Independent and Dependent Variables
• According to Cooper and Schindler (2001), There is nothing very
tricky about the notion of independence and dependence. But there
is something tricky about the fact that the relationship of
independence and dependence is a figment of the researchers
imagination until demonstrated convincingly. Researchers
hypothesize relationships of independence and dependence. They
invent them, and then they try by reality testing to see if the
relationships actually work out that way.
VARIABLES cont..
Defining independent and dependent variables

Independent Dependent
• Presumed cause • Presumed effect
• Stimulus • Response
• Predicted from • Predicted to
• Antecedent • Consequence
• Manipulated • Measured outcome
• Predictor • Criterion
VARIABLES cont..
Moderating Variables (MV)
• In each relationship there is at least one independent variable (IV) and
a dependent variable (DV).
• It is normally hypothesized that in some way the IV “causes” the DV to
occur.
• For simple relationships, all other variables are considered extraneous
and are ignored.
• However, in actual study situations, such simple one- on- one
relationship needs to be conditioned or revised to take other variables
into account.
• Often one uses another type of explanatory variable known as
moderating variable.
• A moderating variable is a second independent variable that is included
into a study because it is believed to have a significant contributory or
contingent effect on the originally stated IV- DV relationship. E.g. one
may hypothesize Market strategy (IV) will lead to high corporate
performance (DV), especially if the organization has acquired requisite
internal capabilities (MV) and is operating in an attractive industry.
VARIABLES cont..
Extraneous Variables (EV)
• In a given relationship an infinite number of variables may exist that
may affect the relationship. These are called extraneous variables and
most are either assumed or excluded from the study.
• In most cases these infinite number of extraneous variables have little
or no effect on a given situation. Others may be important but, their
impact occurs in such a random manner has to have little effect.
Intervening Variables (IVV)
• The factor that theoretically affects the observed phenomenon but
cannot be seen, measured or manipulated, its effect must be inferred
from the effects of the independent and moderator variables on the
observed phenomenon. E.g. The introduction of a four day work week
(IV) will lead to higher productivity by increasing job satisfaction (IVV).
DATA COLLECTION METHODS AND PROCEDURES
• There are two types of data, i. e. primary data and secondary data.
• The primary data are those that are collected for the first time, and
thus have original character.
• The secondary data are those that have been collected by someone
else and which in most cases have already been passed through
statistical process.
• The researcher has to decide the kind of data best suited for the
research at hand and the best method of collecting such data.

COLLECTING PRIMARY DATA


• Primary data is obtained either through observation, interviews or
questionnaire.
Observation Method
• Done through either participant or structured observation.
• Participant observation is qualitative and derives from the work of
social anthropology.
• Structured observation is quantitative and is more concerned with
frequency of observed actions.
COLLECTING PRIMARY DATA Cont..
Observation Method cont..
• Data collected through participant observation can be categorised
as primary, secondary and experiential.
• Primary observations are those where you note what happened or
what was said at the time by keeping a diary of events.
• Secondary observations are statements by observers of what
happened or what was said and involves observers interpretations.
• Experiential data are those data on your perceptions and feelings as
you experience the process you are researching.
• The data collected under participant observation will of course
depend on the research questions and objectives.
• The data is classed as descriptive observation and narrative
account.
• The descriptive observation forms the basis of narrative account.
• Data analysis under participant observation is on spot and
commonly employs an approach called analytic induction.
• Participant observation is high on ecological validity but may suffer
researcher bias.
COLLECTING PRIMARY DATA Cont..
Interview Method
• An interview is a purposeful discussion between two or more people. It may be
used to gather data in line with your research objective and questions, or clarify
your problem.
• The main types of interviews include semi- structured, in- depth and group
interviews. Structured interviews refer to researcher administered
questionnaires a.k.a. quantitative research interviews.
• Semi- structured interviews and in-depth interviews are non standardized and
are often referred to as qualitative research interviews.
• In semi-structured interviews the researcher will have a list of themes and
questions to be covered, although these may vary from interview to interview.
This means given the circumstances of the organization some questions may
be omitted while in other circumstances additional questions are posed.
• The data is audio recorded or notes are taken.
• In-depth interviews are unstructured and explore in depth a general area of
interest.
• There is no predetermined list of questions although you need to have a clear
idea about the aspects you want to explore.
COLLECTING PRIMARY DATA Cont..
Interview Method cont..
• The interviewee may be given opportunity to talk freely on the topic
area (informant interview) or the interviewer directs the interview
and the interviewee responds to questions of the researcher
(respondent interview).
• While structured interviews are mainly applied in descriptive and
explanatory research semi-structured and in-depth interviews are
employed in exploratory and case study research.
Data Quality
• A number of data quality issues can be identified in relation to use of
semi-structured and in-depth interviews, related to: reliability, forms
of bias, validity and generalizability.
• Lack of standardization and interviewer bias may lead to concerns
about reliability.
• There is also an issue of generalizability of findings from
qualitatively based interview studies, although the validity of such
studies is not raised as an issue.
COLLECTING PRIMARY DATA Cont..
Group Interviews and Focus Group
• The role of the researcher under group interview is to ensure that all
participants have the opportunity to state their points of view and
answer your question and that these data are captured.
• Group interviews can also be used to identify key themes that will
be used to develop items that are included in a survey
questionnaire.
Focus Group (focus group interview)
• A group interview that focuses clearly upon a particular issue,
product, service or topic and encompasses the need for interactive
discussion among participants.
QUESTIONNAIRE METHOD
• A questionnaire is a data collection technique in which each person is asked
to respond to the same set of questions in a predetermined order.
• The design of a questionnaire differs according to how it is administered and
in particular the amount of contact you have with respondents.
• Types of questionnaires include, self administered questionnaires, internet
mediated questionnaires, intranet mediated questionnaires, Postal/ mail
questionnaires, drop- and- pick questionnaires, telephone questionnaires.
• Apart from research questions and objectives, the choice of your
questionnaire will also depend on:
 Characteristics of the respondents from whom you wish to collect data;
 Importance of reaching a particular person as respondent;
 Importance of respondents answer’s not being contaminated or distorted;
 Size of sample you require for your analysis, taking into account the likely
response rate;
 Types of questions you need to collect your data
 Number of questions you need to ask to collect your data
QUESTIONNAIRE METHOD Cont..
• Unlike in interviews, where you can prompt and explore issues further
questions you ask in questionnaires need to be defined precisely prior
to data collection.
• This implies the time you spend planning precisely what data you need
to collect, how you intend to analyze them, and designing your
questionnaire to meet these requirements is crucial if you are to answer
your crucial questions and meet your objectives.
• Construct questions in line with the literature review for all the study
variables. Where similar studies have been done, you may adopt the
research questions used in the questionnaires employed.
• The type of questions in the questionnaire while depend on the
research design, whether the data is required for description purpose or
to test a theory.
• In explanatory research design, where you are required to test a given
theory, you need to define the theories you wish to test as relationships
between variables prior to designing your questionnaire. This is
achieved by careful review of literature.
QUESTIONNAIRE METHOD Cont..
Questionnaire Design
• The design of each question should be determined by the data you
need to collect.
• When designing individual questions researchers may;
- adopt questions used in other questionnaires
- adapt questions used in other questionnaire
- develop their own questions
• Adopting or adapting questions may be necessary if you wish to
replicate or to compare your findings with another study. It also allows
assessment of reliability.
• Be careful when adopting questions to avoid adopting poor questions.
Always recognise authors of adopted questions and where the
questions are under copyright seek author’s permission.
• Most types of questionnaires include a combination of open ended and
closed questions. While open ended questions allow respondents to
give answers in their own way, closed ended questions give
respondents alternatives they are asked to choose from.
QUESTIONNAIRE METHOD Cont..
TYPES OF QUESTIONS
1. Open questionnaires
Used widely in interviews. In questionnaires they are used if you are
unsure of the response, such as in an exploratory research when you
require detailed answers or when you want to find out what is
uppermost in a respondent’s mind.
2. List Questions
Offers the respondent a list of responses, any of which they can
choose. The list of responses must be defined clearly and
meaningfully.
3. Category Questions
Designed so that each respondent’s answer can fit only one category.
Such questions are useful if you need to collect data about behaviour
or attributes. Have a maximum of five categories and arrange them in
logical order so that it is easy to locate the response category that
corresponds with the respondent’s answer. The categories should be
mutually exclusive and should cover all possible responses.
QUESTIONNAIRE METHOD Cont..
TYPES OF QUESTIONS cont..
4. Ranking questions
Asks the respondent to place things in rank order depending on the
relative importance to the respondent.
5 Rating questions
Often used to collect opinion data. Rating questions most frequently
use the Likert- style rating scale in which the respondent is asked
how strongly she or he agrees or disagrees with a statement or a
series of statements usually on a four, five, six or seven point rating
scale.
6. Quantity Questions
The response to a quantity question is a number, which gives the
amount of characteristic.
7. Grid
A grid matrix enables you to record responses to two or more similar
questions at the same time.
QUESTIONNAIRE METHOD Cont..
INTRODUCTION AND PILOT TESTING
• A self administered questionnaire should be accompanied by a covering
letter, which explains the purpose of the study and assures respondents strict
confidentiality.
• Prior to using your questionnaire to collect data it should be pilot tested.
• The purpose of pilot testing is to refine the questionnaire so that the
respondent will not have problems answering the questions and there will be
no problem recording the data.
• It also helps you assess questions validity and likely reliability of the collected
data.
• When pilot testing you should find out the following from the respondents:
- How long the questionnaire took to complete
- The clarity of instructions
- Which if any, questions are ambiguous
- Which if any questions the respondent felt uneasy about answering
- Whether in their opinion there were any major topic omissions
- Whether the layout was clear and attractive
- Any other comments.
COLLECTING SECONDARY DATA
• Secondary data include both qualitative and quantitative data.
• The data you get may be raw data where there have been little
processing or compiled data that have received some form of
selection or summarizing.
• In business management research secondary data is mainly used
under the case study and survey design.

GROUPS OF SECONDARY DATA


Documentary secondary Data
• Include written materials such as notices, correspondence, minutes
of meetings, reports to shareholders, diaries, transcripts of
speeches and administrative and public records.
• For your research project the documentary sources you have
available will depend on whether you have been granted access to
organisations records.
COLLECTING SECONDARY DATA cont..
GROUPS OF SECONDARY DATA cont..
Survey based secondary data
• Data collected using a survey strategy, usually by questionnaires
that have already been analysed for their original purpose.
Multiple source secondary data
• Can be based entirely on documentary or on survey secondary data
or a mix of the two.
• The key factor is that different data sets have been combined to
form another data set prior to your accessing the data e.g. Financial
statements for listed company.
Note: The reliability and validity you ascribe to secondary data are the
functions of the methods by which the data were collected and the
source credibility.
SAMPLING
• Occasionally it may be possible to collect and analyze data from every
case or group member in what is known as census.
• However, in most cases it will not be possible to conduct a census due
to restrictions of time, money and access.
• In this case a representative sample is drawn from the entire population
from which the elements are generalized to the population.

SAMPLING TECHNIQUES
• Sampling techniques are divided into two types:
• Probability or representative sampling
• Non probability or judgemental sampling
• In probability samples, the chance of each case being selected is
known and is equal in all cases.
• For non probability samples, the chance of each case being selected
from the total population is not known and it is impossible to address
research objectives that requires statistical inferences about
characteristics of the population.
PROBABILITY SAMPLING
• The process of probability sampling can be divided into four stages:
1. Identifying a suitable sampling frame based on your research
questions or objectives.
- The sampling frame for any probability sample is a complete list of
all the cases in the population from which the list is drawn
- Where no suitable lists exist you will have to compile your own
frame from existing lists.
- Completeness and accuracy of the sampling frames is critical for
generalization.
2. Deciding on suitable Sample size
- To improve on accuracy of generalization the larger the sample
size the better.
- Probability sampling is a compromise between the accuracy of the
findings and the amount of time and money you invest collecting,
checking and analysing the data.
Your choice of sample size will be governed by:
PROBABILITY SAMPLING cont..
- The confidence you need to have in your data i.e. the level of certainty that
the characteristics of the data collected will represent the characteristics of
the total population;
- The margin of error that you can tolerate- i.e. the accuracy you require for
any estimates made from your sample;
- The types of analyses you are going to undertake- in particular the number of
categories in which you wish to subdivide your data as many statistical
techniques have a minimum threshold of data cases for each cell.
3. Selecting the most appropriate sampling technique and the sample
- Having chosen a suitable sampling frame and established the actual
sample required, you need to select the most appropriate sampling technique
to obtain a representative sample.
4. Checking the Sample is Representative
- Ensured by comparing data collected for the sample from another source
for the population e.g. you may compare data for demographics for marketing
survey with the characteristics of the population as recorded by census. If
there is no significant statistical difference then the sample is representative.
You may also use Kolmolgorov tests between the proportions of respondents.
SAMPLING TECHNIQUES

• Probability • Non Probability


- Simple random - Quota
- Stratified random - Purposive
- Cluster - Snowball
- Multi- stage - Self selection
- Convenience
SIMPLE RANDOM SAMPLING
• Involves selecting sample at random from the sampling frame using either
random number tables or a computer. To do this:
1. Number each of the cases in your sampling frame with a unique number. The
first case is numbered 0, the second 1 and so on.
2. Select cases using random numbers until your actual size is reached.
• Simple random sampling is best used when you have an accurate and easily
accessible sampling frame that lists the entire population preferably stored in
a computer. It works best for geographically concentrated populations.
SYSTEMATIC SAMPLING
• Involves selecting the sample at regular intervals from the sampling frame. To
do this:
1. Number each of the cases in your sampling frame with a unique number. The
first case is numbered 0, the second 1 and so on.
2. Select the first case using a random number.
3. Calculate the sampling fraction.
4. Select the subsequent cases systematically using the sampling fraction to
determine the frequency of selection.
SYSTEMATIC SAMPLING cont..
• Sampling fraction = actual sample size/ total population
• Unlike simple random sampling, systematic sampling works equally
well with a small or large number of cases. Where face to face
interviews are required, systematic sampling is not suitable.

STRATIFIED RANDOM SAMPLING


• Is a modification of random sampling in which you divide the
population into two or more relevant and significant strata.
• Your sampling frame is divided into a number of subsets. A random
sample (simple or systematic) is then drawn from each strata.
• To do stratification:
1. Choose the stratification variable or variables.
2. Divide the sampling frame into the discrete data.
3. Number each of the cases within each stratum with a unique
number.
4. Select your sample using either simple random or systematic
sampling.
STRATIFIED SAMPLING cont..
• The stratification variable or variables chosen should represent
the discrete characteristic (s) for which you want to ensure correct
representation within the sample.
• Samples can be stratified using more than one characteristic. You
may wish to stratify a sample of an organization’s by both
department and salary grade. To do this you would:
1. Divide the sampling frame into the discrete departments.
2. Within each department divide the sampling frame into each
discrete salary grades.
3. Number each of the cases within each salary grade within each
department with a unique number.
4. Select your sample using either simple random or systematic
sampling.
CLUSTER SAMPLING
• Similar to stratified sampling as you need to divide population into
different groups.
• The groups are termed as clusters and can be based on any
naturally occurring grouping e.g. geographic area, type of
manufacturing.
• For cluster sampling, your sampling frame is the complete list of
all clusters rather than complete list of individual cases within the
population.
• The technique for cluster sampling has three main stages:
1. Choose the cluster grouping fro your sampling frame.
2. Number each of the clusters with a unique number. The first
cluster is numbered 0, the second 1 and so on.
3. Select your sample using some form of random sampling.
Though cluster sampling, is less accurate than stratified random
sampling, it maximises the number of contacts you can undertake
given the resources available, by restricting the samples to
relatively compact geographical areas.
NON PROBABILITY SAMPLING
• Provides a range of alternative techniques to select samples based on
your subjective judgement.
• It becomes practical when your research objectives dictate an in depth
inquiry of one or a few units or when it is difficult to specify your
sampling frame or resources are limited.
• Non probability sampling include quota, purposive, snowballing, self
selection and convenience sampling.
Quota Sampling
• Non random, usually used for interview surveys.
• To select a quota sample you:
1. Divide the population into specific groups.
2. Calculate a quota for each group based on relevant and available data.
3. Give each interviewer an assignment, which states the number of cases
in each quota from which they must collect data.
4. Combine the data collected by interviewers to provide the full sample.
NON PROBABILITY SAMPLING cont..
Purposive/ Judgemental Sampling
• Enables you to use your judgement to select cases that will best enable
you to answer your research questions and to meet your objectives.
• Used when working with very small samples such as in case study
research and when you particularly want to select cases that are
informative.
Snowball Sampling
• Used when it is difficult to identify members of the desired population.
Procedure
1. Make contact with one or two cases in the population.
2. Ask these cases to identify further cases.
3. Ask these new cases to identify further new cases and so on.
4. Stop when either no new cases are given or the sample is as large as is
manageable.
NON PROBABILITY SAMPLING cont..
Self Selection sampling
• Occurs when you allow each case, usually individuals, to identify their
desire to take part in the research.
1. Publicise your need for cases, either by advertising through
appropriate media or by asking them to take part.
2. Collect data from those who respond.

Convenience/ haphazard Sampling


• Involves selecting haphazardly those case that are easiest to obtain
for your sample.
• The sample selection process is continued until your required sample
size has been reached.
• It is prone to bias and influences beyond the researcher’s control thus
making generalizations flawed.
SAMPLE SIZE
• The size of the sample is a function of the variation in the
population parameters understudy and the estimating precision
needed by the researcher.
• Principles that influence sample size include:
1. Dispersion or variance- The greater the dispersion the larger the
sample must be to provide estimation precision.
2. Precision- The greater the desired precision of the estimate, the
larger the sample must be.
3. Interval range- The narrower the interval range, the larger the
sample must be.
4. Confidence level- The greater the confidence level in the estimate
the larger the sample must be.
5. Number of subgroups- The greater the number of subgroups of
interest within a sample, the greater the sample size must be as
each subgroup must meet minimum sample size requirements.
Note: If the calculated sample size exceeds 5% of the population,
sample size may be reduced without sacrificing precision.
SAMPLE SIZE cont..
• Precision is measured by (1) the interval range in which the
parameter is to be found and (2) the degree of confidence desired
in the estimate.
• The size of the probability sample needed can be affected by the
population, but only when the sample size is large compared to
the population. When the sample size is equal or greater than 5%
finite adjustment factor is used to reduce the size of the sample
needed to achieve a given level of precision.
DATA ANALYSIS AND PRESENTATION
TYPES OF QUANTITATIVE DATA
• Quantitative data can be divided into two distinct groups: categorical
and quantifiable.
• Categorical data refers to data whose values cannot be measured
numerically but can be either be classified into sets (categories)
according to characteristics that identify or describe the variable or
place in rank order. They can further be divided into descriptive and
ranked. E.g. a car manufacturer may categorise its cars as saloon and
estate since it is not possible to define them numerically or even rank
them. This is known as descriptive or nominal data.
• Some statisticians separate descriptive data into two categories;
dichotomous data, two categories e.g. yes or no; male or female AND
ranked or ordinal data being more precise form of categorical data.
• Quantifiable data are those data whose values are measured
numerically as quantities.
• Quantifiable data is more precise than categorical data as you can
assign each data value a position on a numerical scale and it can be
analyzed using a wider range of statistics.
DATA ANALYSIS AND PRESENTATION cont..
TYPES OF QUANTITATIVE DATA cont..
Quantifiable data cont..
• There are two ways of subdividing quantifiable data; interval or ratio data
AND alternatively into discrete and continuous data.
• Continuous data are those whose values can theoretically take any
value (sometimes within a restricted range) provided you can measure
them accurately e.g. distance, height, length of service etc.
• Discrete data takes one of finite number of values from a scale that
measures changes in discrete units e.g. number of customers served.
• It is important to understand the differences between types of data when
analysing quantitative data:
1. To avoid generating inappropriate statistics that is of little value.
2. The more precise the level of measurement, the greater the range of
analytical techniques available to you.
Note: Data that have been collected and coded using precise numerical
measurements can also be regrouped to less precise level where they
can also be analysed. Less precise data cannot be made more precise.
ANALYSIS OF QUANTITATIVE DATA

• The simplest way of summarizing data for individual variables so that


specific values can be read is to use a table (frequency distribution).
• For descriptive, the table summarises the number of cases (frequency)
in each category.
• For values where there are likely to be large number of categories
(values for quantifiable data) group the data into categories that reflect
your research questions and objectives.
• Where visual representation is required use bar charts, histograms and
pictogram.
• To show trends line graph is the most suitable diagram.
• Pie charts are best suited to show proportions.
MEASURES OF CENTRAL TENDENCY
• A measure of central tendency is a single numerical value that is used
to describe average of an entire set of scores.
• The mean, median and mode are three different measures of central
tendency.
• The mean is calculated by dividing the sum of all scores by the number
of scores. The median is the middle point in a distribution of scores. The
mode is the most frequently occurring score.
• The mean is considered the best measure of central tendency because
it is more stable than the median and the mode. Thus, if we study
several samples from the same population the means are likely to be in
closer agreement than the medians and modes.

SKEWNESS
• When a distribution of scores is symmetrical, the mean and the median
are located at the same point in the distribution.
• When the distribution has more extreme scores at one end than the
other, that is when it is skewed, because the mean will always be in the
direction of the extreme scores. In this case a median will reflect more
accurately the average of the sample.
SKEWNESS cont..
• When a distribution is highly skewed, both the mean and the median
should be reported. Special statistics may be used to describe the
amount of skewness and the shape of score distribution.

KURTOSIS
• Kurtosis is a measure of shape that describes departures from the
symmetry of a distribution and its relative flatness or peakedness,
respectively.
• Skewness and kurtosis are related to statistics known as moments,
which use deviation scores. E.g. the variance is a second power
moment. The measures of shape use third and fourth power deviations
for their computations and are often difficult to interpret when extreme
scores are in the distribution.
• Measures of shape are best communicated through visual displays.
MEASURES OF DISPERSION
• Dispersion is the amount of variability of scores about the mean score or other
measure of central tendency.
• The common measures of variability include variance, standard deviation,
range, interquartile range and quartile deviation.
THE STANDARD DEVIATION
• SD is the measure of variability mostly reported in research studies.
• It is a measure of the extent to which scores in a distribution deviate from the
mean.
• The standard deviation is the most stable measure of variability. This implies
that, repeated samples drawn from the same population are likely to have
similar standard deviations. SD is also used as a basis for computing other
statistics. These reasons make it the most commonly used measure of
variability.
• The mean and standard deviation taken together usually provide a good
description of how members of a sample scored on a particular measure.
• E.g. If a group of individuals has a mean score of 10 and SD of 2 on a test, and
that the scores are distributed in the form of a normal curve, we can infer that
approximately 68% of them earned scores between 8 & 12 and approximately
95% earned scores between 6 and 14.
CORRELATIONAL STATISTICS
• They describe the relationship between two or more variables.
• Bivariate correlation coefficient describes in mathematical terms the
strength of relationship between two variables.
• There are many types of correlation coefficients and selection of an
appropriate coefficient depends upon the form of scores that are to be
related e.g. continuous, ranked, dichotomous or categorical.
• Multivariate correlational methods enable researchers to study how
factors singly and in combination affect outcome variables.

INFERENTIAL STATISTICS
• Statistical inference is a set of mathematical procedures for using
probabilities and information about a sample and to draw conclusions
about the population from which the sample was drawn.

You might also like