A Guide To Research Writing: David Annan

See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/333395933
A GUIDE TO RESEARCH WRITING
Book · May 2019
CITATIONS READS
2 17,344
1 author:
David Annan
SSBM
6 PUBLICATIONS 3 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
Exploring outlook of South Sudan development after independence View project
Small business/ entrepreneurial Management View project
All content following this page was uploaded by David Annan on 03 August 2019.
The user has requested enhancement of the downloaded file.

Stevejobs.education
Address: 6021NW61 ave Suite 105
Fort Lauderdale Florida 33319 USA
Phone: (954)639-9261/ +7(776) 1673319
email: [email protected]
Printing company «FLASH PRINT»

Address: Saryarka avenue, 8
Astana, Kazakhstan
PREFACE
My students at global perspective and project works, who are starting to prepare for higher
learning at universities across the continent, inspired this book. Very often, little attention
is paid to how students have to prepare and understand the processes of conducting
research. Mostly, young scholars really struggle during the early stages of their university
career regarding what is required of them and how to present their research proposal to
their supervisors.
With this in mind, the purpose of this guidebook is to offer a critical and practical mind map
to research writing to assist first time researchers in creating an appropriate design for their
research studies. The book includes many simple graphs to illustrate and explain what is
expected of researchers at each stage of their research writing and to enable them to deal
with any, a missing link when conducting their research.
The guidebook is mainly intended to serve young students when compiling assignments
on research studies and teachers who teach research writing at their schools, colleges and
universities.
It with joy and appreciation that I thank the Nazarbayev Intellectual School of Physic and
Mathematics in Astana (NIS PhM Astana) and my students and colleagues in the Social
Sciences Department of Global Perspective and Project Works and Economics for
providing the avenue for writing this simple yet comprehensive book.
I am highly indebted to the following editors, Jeanne Elslin and Paul Sweeney for their
great insight, support and criticism that make this guidebook a success.
It is my greatest dream that this book will help others to succeed in good research writing
and develop pioneers in the development fields. I look forward to suggestions from all
readers and students for further improving the content design and making it even simpler.
5
TABLE OF CONTENTS
CHAPTER ONE: INTRODUCTION TO RESEARCH ................................................. 9

INTRODUCTION ................................................................................................ 9
STEPS IN RESEARCH PROCESS .................................................................. 13
STEPS TO DETERMINE THE RESEARCH METHOD ..................................... 15
RESEARCH PARADIGMS................................................................................ 16
METHODOLOGY AND METHODS .................................................................. 17
CHAPTER TWO: LITERATURE REVIEW ............................................................... 20
INTRODUCTION .............................................................................................. 20
THE PURPOSE OF THE LITERATURE REVIEW ............................................ 21
FUNCTIONS OF THE LITERATURE REVIEW ................................................. 22
Provide a context for the study.......................................................................... 22
Create a conceptual frame of reference ............................................................ 22
Report the status of current research ................................................................ 22
Identify appropriate methodology, instrument and data analysis procedures .... 23
Demonstrate theoretical and conceptual gaps in the field ................................. 23
Strategies for literature review .......................................................................... 24
CHAPTER THREE: RESEARCH DESIGN .............................................................. 27
RESEARCH PROCESS ................................................................................... 27
Develop an appropriate research design .......................................................... 29
RESEARCH PHILOSOPHY .............................................................................. 29
Positivist (quantitative research) ....................................................................... 30
Phenomenological (qualitative) research .......................................................... 30
Mixed research approach ................................................................................. 31
Research process within a mixed method framework ....................................... 32
RESEARCH STRATEGIES .............................................................................. 33
6
Positivist research strategies/experimental design............................................ 33
Surveys ............................................................................................................. 34
Phenomenological research strategies ............................................................. 34
Case study ........................................................................................................ 34
Action research ................................................................................................. 35
Grounded theory ............................................................................................... 36
Ethnography ...................................................................................................... 37
Mixed research strategies ................................................................................. 37
RESEARCH PURPOSE .................................................................................... 37
Causal-comparative research ........................................................................... 37
Correlational research ....................................................................................... 37
Explanatory research ........................................................................................ 38
Descriptive research ......................................................................................... 38
Exploratory research ......................................................................................... 38
CHAPTER FOUR: SAMPLING ................................................................................ 39
INTRODUCTION .............................................................................................. 39
THE WHYS OF A SAMPLE POPULATION ....................................................... 40
The sampling cycle ........................................................................................... 41
Representatives ................................................................................................ 41
KINDS OF SAMPLING...................................................................................... 41
CHAPTER FIVE: DATA COLLECTION .................................................................... 49
INTRODUCTION .............................................................................................. 49
IMPLEMENTING THE PLAN ............................................................................ 50
Interaction with participants in the study ........................................................... 50
DATA COLLECTION METHODS....................................................................... 50
Questionnaires .................................................................................................. 51
7
Interviews .......................................................................................................... 55
Observation ...................................................................................................... 59
ETHNOGRAPHIC STUDIES ............................................................................ 63
CASE STUDIES................................................................................................ 64
CHAPTER SIX: DATA ANALYSIS ................................................................................. 77
INTRODUCTION .............................................................................................. 77
THE QUANTITATIVE DATA ANALYSIS ............................................................... 77
Coding of data................................................................................................... 79
Statistical analysis............................................................................................. 80
Guidelines for the successful application of statistics in the analysis of data .... 80
The analysis of univariate data ......................................................................... 81
The analysis of bivariate data ........................................................................... 81
ANALYSIS OF QUALITATIVE DATA .............................................................................82
Strategies for qualitative analysis...................................................................... 82
Categorisation in qualitative research ............................................................... 83
ANALYSING CASE STUDY DATA ................................................................................83
DATA PRESENTATION AND REPORT WRITING FOR CASE STUDIES......... 84
CHAPTER SEVEN: THE RESEARCH REPORT ..................................................... 85
INTRODUCTION .............................................................................................. 85
OBJECTIVES OF RESEARCH REPORT WRITING......................................... 85
Characteristics of the research report ............................................................... 86
Types of reports ................................................................................................ 86
Steps in writing report ....................................................................................... 87
IMPORTANT RESEARCH TERMS ................................................................... 88
BIBLIOGRAPHY AND FURTHER READINGS........................................................ 90
8
CHAPTER ONE: INTRODUCTION TO RESEARCH
Outcomes
By the end of the chapter, the student will be able to:
• Define research
• Distinguish between scientific and non-scientific analyses
• Demonstrate knowledge of research terminology
• Describe the characteristics of scientific research
• Sketch the steps in the research project
• Differentiate between the two major research paradigms.
INTRODUCTION
Research is a systematic way of answering questions about the world. It is intended to
increase knowledge about the process of developing an understanding of the natural laws
governing the universe; innovations or new ideas; commitment and technological
advantages, which will improve the welfare of humanity.
Everybody takes part in some type of research. As individuals communicate with the world,
they characterise explicit issues, gather data (information), examine information and settle
on choices based on the information they obtained. This procedure can happen casually,
now and again, or unconsciously. It is normally not logical and will in general be mistake
inclined, thus, the idea of learning by experimentation. Scientifically, organised research
has clearly defined characteristics that must be deliberately and unbiasedly pursued.
Furthermore, non-scientific examination is inclined to an assortment of distorting factors.
The following two figures illustrate the features of non-scientific analysis and scientific
research.
9
Figure 1.1: Features of non-scientific analysis
Scientifically orientated research is based on rules of logic, established methodological
techniques and statistical theory. Hence, it comprises a process through which new
knowledge is discovered.
Scientific research has several important features as giving in Figure 1.2
Figure 1.2: Features of scientific research
10
Some of the distinguishing characteristics of scientific research are:
• It is often theory-based because some theory is either tested or developed.
• It has minimal ego involvement because the researcher is often humble and willing to
admit when they are wrong.
• The objective is maximised.
• Established rules for data collection are strictly followed.
• Standard rules for data analysis are applied.
• Conclusions are based on data not on preconceptions, beliefs, values or biases.
• It emphasises uncovering regularities and patterns of social and behavioural
phenomena.
• It emphasises the study of aggregates rather than individual cases.
• It welcomes the idea of replication, i.e. for a study to be replicated by other researchers
in order to confirm their findings.
Thus, the general objective of research is to discover new facts and to contribute to the
general body of knowledge in the field under study. Saunders et al. (2003:2-3) noted that
research needs to address issues and to provide a process for solving the problems. It
is important to emphasise that research does not only need to provide findings that
advance knowledge and understanding. It needs to address issues and provide a process
for solving problems.
A distinct focus for research:
• The way in which researchers draw on knowledge developed by other disciplines
• The fact that people are busy. Thus, they are unlikely to permit research access
unless they can see personal or commercial advantages.
• The requirement for research is to have some practical consequence. This means
that it either needs to contain the potential for taking some form of action or needs to
take account of the practical consequences of the findings.
There are two distinct forms of research, namely pure research and applied research. Pure
research is conducted with the sole objective of understanding a phenomenon and to
contribute to the development of research theories. Applied research on the other hand
comprises a process to find solutions to current real-life scientific problems.
Figure 1.3 below illustrates the features of both pure and applied research, and is followed
by Figure 1.4 which lists the purpose and context for both pure and applied research.
Note: pure and basic is used interchangeable in the figures.
11
Figure 1.3: Pure and applied research
Figure 1.4: Purpose and context (Saunders, Lewis, and Thornhill 2003)
12
STEPS IN RESEARCH PROCESS
Mind map 1.1: Research proposal content
13
Mind map 1.2: Development hypothesis of research
Research is a multifaceted process with a particular sequence to be pursued to guarantee
that the project undertaken is effectively completed. Despite this, there is also room for
flexibility and inventiveness of the research procedure.
1. Selection and formulation of the research problem
• Select a topic for research: identification of the problem
• Formulate the research problem
• Acquire knowledge on current theory and research
• Literature review
• Identify and label the variables
• Define concepts and establish reserach definitions
• Formulate the hypothesis
2. Choice of research design
• Research format and research design
• Description of the samples
• Sampling procedures
3. Data collection
• Construction of the research instrument
• Actual data gathering
14
4. Analysis of data
• Data processing
• Statistical analysis
5. Interpretation of results
6. Conclusion and recommendations
7. Writing the research report.
STEPS TO DETERMINE THE RESEARCH METHOD
Mind map 1.3: Steps in research method
Step 1. Identify the research problem

The first step in the scientific method is usually characterised by realising that some
problem exists. This manifests in the form of a question that troubles the mind.
Step 2. Clarify and contextualise the problem
By participating in discussion and studying or reviewing current literature of what one is
exploring, the issue is illuminated and the nature and specifics of interest of the problem
are identified. As the issue is clarified, the underlying inquiry prompts more inquiries and
the dynamic illumination of variables that may influence the examination of the underlying
problem begins to improve our understanding and to show increasing complexity.
15
Step 3. Develop a research design
This entails all activities the researcher engages in when planning an arrangement for the
exploration. A set of research questions or a theory should be detailed as an informed
speculation about the conceivable responses to the issue. Now in the examination structure,
the researcher has two differentiating approaches that offer them alternative courses in the
advancement of the plan. The researcher may select the interpretive-inductive methodology
where they start to observe before arriving at conceivable clarifications or they may select
the hypothetical deductive methodology where the starting point is a hypothesis or a theory.
Table 1.1 Concepts of induction and deduction
Induction Deduction
Start with data and look for patterns in the Forms hypotheses and tests in data
data e.g. people who are at risk averse in collected subsequently e.g. brand loyalty
personal lives are more likely to be loyal increases with age
Step 4. Examine the data collected for the underlying patterns

When the research design is finished and information gathered, the researcher needs to
inspect the information for fundamental patterns that recommend answers to the research
exploration questions or test the adequacy of the hypothesis using proper statistical
devices. Simultaneously, the researcher needs to perceive how the discoveries of the
examination hypothesis and the mind in the field affect the theory or hypothesis.
Step 5. Interpret the findings
The progression includes the understanding of the discoveries and generalisation of the
conclusion to the bigger collection of knowledge about the phenomenon. One of the
objectives in this phase of the examination is to contribute change or expound on existing
exploration and hypotheses in the field. This procedure may recommend strategies to
discover the context of the problem.
RESEARCH PARADIGMS
The word paradigm is generally used in the academic world to convey three distinct sets
of ideas:
• The researcher’s basic beliefs about the world and the nature of reality
• The broad conceptual framework the researcher uses to carry out the scientific inquiry
• The specific methods and techniques which should be adopted when conducting
research.
16
Mostly, there are two widely recognised research paradigms, namely the positivist and
phenomenological. The positivist paradigm is sometimes referred to as the quantitative
model and the phenomenological as qualitative or interpretivist model. These two paradigms
are actually two ends of a spectrum with a combination of the two models occurring in
varying degrees of emphasis along the field.
Figure 1.5: Research paradigms
METHODOLOGY AND METHODS

Research methodology is the process used to collect information and data for the purpose
of making informed decisions. Methods, in contrast, refer to the specific means by which
data are collected and analysed.
Therefore, the paradigm a researcher adopts has a direct relationship with the research
methodology available to them.
17
Table 1.2. Features of the two main paradigms
Positivist Phenomenological
Tends to produce qualitative data Tends to produce qualitative data
Uses large samples Uses small samples
Concerned with hypothesis testing Concerned with generating theories
Data is highly specific and precise Data is rich and subjective
The location is artificial The location is natural
Reliability is high Reliability is low
Validity is low Validity is high
Generalises from sample to population Generalises from one setting to another
Source: Hussey and Hussey (1997)
Mind map 1.4: Research paradigm differences in research methodology

VARIABLES
Any phenomenon, persons, places or things that the researcher is trying to measure in
some way is referred to as a variable. The effective way to understand variables is to look
at dependent and independent variable and the importance each of them imply in research
writing.
Dependent variable always look at the impact of a test. It is the variable that the researcher
is measuring or testing in an experiment. For instance, teachers can look at the impact of
junk food on student’s health. The dependent variable would be on student’s health.
Independent variables are factors that can be controlled or manipulated by the researcher
and can produce more than one results.
Mind map 1.5 below gives some basic difference between dependent and independent
variables.
18
Mind map 1.5: Differences between independent and dependent variables
(Cooper and Shindler 2003)
19
CHAPTER TWO: LITERATURE REVIEW
Outcomes
By the end of this chapter, the learner will be able to:
• Clarify the purpose of a literature review
• Develop familiarity with the steps for a literature review
• Categorise and locate sources of information.
INTRODUCTION
According to Bloomsburg University guide on literature (2018), a literature material is the
general account or summary of a previous research topic. The types of scholarly fields
may be empirical, theoretical, critical/analytical or methodological in nature. A literature
review seeks to describe, summarise, evaluate, clarify or integrate the content of primary
reports.
A literature should give a theoretical base for the research and assist the author to determine
the nature or the components of the research. The researcher’s work contributes in some
small but significant way to pushing the boundaries of knowledge in the field. The literature
review should acknowledge the work of previous authors and in doing so, assures the
reader that the research work has been well conceived. In addition, a literature review can
purge the researcher of potential theories that have already been disproved.
Each researcher therefore has to be thoroughly familiar both with the major theoretical
constructs in the field and all research literature that is available. A logical, systematic and
critical review of the body of knowledge provides the backdrop for the research being
undertaken. To demonstrate this through familiarity with earlier work in the field, all
researchers are required to include a literature review in their study.
In the context of the study, a thorough literature review can be described in terms of process
and product.
• The process of the literature review requires the researcher explore the literature to
establish the status quo, formulate a problem or research enquiry, defend the value
of pursuing the line of enquiry, and compare the findings and ideas with their own.
• The product involves the synthesis of the work of others in a form to demonstrate the
accomplishments of the exploratory process.
The literature review is basically a short survey of relevant work done by other theorists,
researchers, academics, etc. in the same field.
The literature review process is an integral part of research planning. It provides a foundation
for the researcher /student’s research and triggers creative thinking. It also assists in
20
identifying appropriate research methods and techniques, and helps in formulating a
discussion about the implications of the research.
THE PURPOSE OF THE LITERATURE REVIEW
Mind map 2.1: The purpose of the literature review
21
FUNCTIONS OF THE LITERATURE REVIEW
Mind map 2.2: Functions of the literature review
Provide a context for the study

The literature review provides a concise synthesis of existing research on the current
research topic. This creates the context from the past for the new study to be conducted
with the new subject and newly obtained data.
Create a conceptual frame of reference

The researcher must carefully assess the key components in this body of literature and
identify areas that are still conceptually and methodologically under-developed and point
out ‘gaps’ in the field. Using the basic writings and theoretical constructs of the problem,
the researcher must fully familiarise themselves with all the ramifications of all points of
view in the current literature.
Report the status of current research

The point here is to provide a brief overview of past research, distinguish areas of
consensus among researchers in the field of hypothetical and theoretical issues, taking
note of the territories of significant discussion and debate. It is necessary to distinguish the
main analysts and scholars in the field and details of the schools of thought arising from
their work, which refer to real ways to deal with research in the field. The literature review
will pinpoint what has been done and how the current research could address explicit
issues or gaps the field.
22
Identify appropriate methodology, instrument and data analysis procedures
A review of the literature helps the researcher to identify what research approaches and
methods have or have not been tried and to determine what data gathering instruments
already exist. Review of earlier research provides insight into a variety of research methods
used and enables the researcher to select a method, design an appropriate research
instrument and develop a data analysis strategy.
Moreover, reviewing the literature provides clues to factors that influenced the method and
instrumentation of earlier research and explains how the research was carried out. Lastly, a
review of the literature assists the researcher with the conceptual and operational definition
of the key terms, assumptions, limitations and the articulation of research questions and
hypotheses of the new research project.
Demonstrate theoretical and conceptual gaps in the field

It is critical for the researcher to understand how earlier research helps to guide and inform
their own study. Therefore, the literature review must not only improve the researcher’s
knowledge of the chosen field but also demonstrate the depth of understanding of the field.
Table 2.1 below provides lists of the different types of literature sources available when
conducting research.
Figure 2.1: Types of literature sources
23
Strategies for literature review
• Structure the literature review as early as possible in terms of headings and sub-
headings; these can always be revised and amended as time goes on.
• Draw concept maps.
• Write as much as possible about aspects of the research area; writing can always be
restricted later.
• Formulate questions that the literature review addresses.
• Read through the theses or assignments written by previous researchers and examine
their literature review chapter.
• Search indexing and abstract databases.
The scope of the literature review is illustrated in Mind map 3.2 below.
Mind map 2.3: Identifying the scope of the literature review

The main problem of writing the literature review is what to include or not. This is a common
concern for many researchers. The following range of factors is critical to identify the scope
of coverage of the literature review.
• Comprehensiveness – the review should cover all existing and past knowledge on
the area under study
• Specificity – confine your writing to your particular topic
• Authority – ensure that the authoritative authors have been identified
• Currency – include current thinking and writing in the field
• Availability – be interested in material which is readily available
• Relevance – include only relevant material.
24
Criteria for evaluating a literature review are listed in Mind map 2.4 below, followed by the
steps required for writing the literature review in Mind map 2.5.
Mind map 2.4: Criteria for evaluating a literature review

(Saunders, Lewis, and Thornhill 2003)
Mind map 2.5: Steps in writing literature review

Step 1: Decide on the format
Generally, the literature review forms a chapter of the research report. Whatever the format,
the relevant literature must not be presented as summaries of books and articles but as a
blended and concise evaluation of current information on the subject.
25
Step 2: Develop a unified theme
The literature review should provide a concise and coherent account of the existing
literature on the research topic. Hence, there has to be unity of the theme and a logical
cohesion of ideas throughout the review. Important lines of thought must emerge from the
introduction that presents a broad entry to the field to a narrow focus which includes the
pivotal issues in the current research. The objective is to elicit the reader’s interest and
involvement in the current research by providing a critical overview of previous work in the
field and to contextualise the present study.
Step 3: Organise the collated material
The presentation of the material must reveal a clear underlying design. As noted above,
the literature review must not read as various summaries of journal articles and books. A
common strategy used by any researcher is to organise their material chronologically
under carefully arranged subsections of the topic. Moreover, within the design, a good
researcher will:
• start at a level that is more general before narrowing down to the focus of the study.
• review some of the key concepts and areas of research.
• provide a flow of information that synthesises, compares and contrasts the work of
key writers in the field.
• highlight most the relevant studies in relation to the topic.
Step 4: Ensure a smooth flow
The flow of research writing is very important. Therefore, the researcher must ensure that
there is a smooth flow from section to section by highlighting the logical connection
between different components of the review. The biggest challenge in research writing is
to uncover the possible intersections among seemingly unconnected fields of information.
Step 5: Develop and work from an outline
An important final step before the actual writing process is to develop a detailed plan and to
organise the material in terms of the researcher’s design. This will enable the development
of a schematic plan that allows flow of the main lines of thought in the research topic, leads
the reader to the specific, and arouses interest in the researcher’s own effort to advance
knowledge in the field.
26
CHAPTER THREE: RESEARCH DESIGN
Outcomes
• Outline the features of research paradigms
• Label and explain the features of various research strategies.
The research process is a systematic process that involves an objective gathering of
information for analysis to assist the researcher to come a credible conclusion.
RESEARCH PROCESS
Mind map 3.1: Research process

The research process has clearly defined elements that reflect an application of the
research methodology. These elements in the mind map are elaborated on below for clear
understanding:
1. Commence with the research problem
The researcher begins the study by focusing on a problem or an idea that they believe
needs to be explored.
27
2. Reflect on the problem
The researcher has to reflect on the significance of the problem and its relevance to the
study.
3. Define the problem as a specific research problem
An initial review of the literature should enable the researcher to begin developing a frame
of reference for the research, formulating conceptual and operational definitions of key
concepts, identifying the significance of the research problem and crystallising in specific
terms the research topic for the research problem.
4. Undertake an intensive literature review
The purpose is to attain a deep understanding of the problem at hand and its context.
Further, it is necessary to create a concise, critical and evaluative summary of previous
research literature on the research topic. The researcher must now to undertake an
intensive literature review. This will help to gather ideas for the literature design, data
collection, data analysis instruments and techniques.
5. Select the research methodology
The researcher has to begin to formulate one or more hypotheses, research questions and
research objectives, decide on the type of data needed, and select the data collection and
data analysis strategies. It is therefore necessary to select the research methodology to
gather decisions about the research paradigm, research approach and research method.
6. Prepare the research proposal
The researcher has to prepare a sound research proposal that contains structured details
of the research topic.
7. Identify the population and the sample
The researcher has to define the target population, identify the sample selection method,
decide on the sample size and identify those who will participate in the study.
8. Develop a data collection design
The researcher has to develop the research instruments that will fully address the needs
of the topic. To achieve a balance between the adequacy of the data collection design and
the availability of material and human resources, the researcher must take note of cost in
terms of time and money before the start of the research and data collection process.
9. Select an appropriate data analysis strategy
The researcher must be aware of the statistical tools needed to analyse the data and
decide on the tables and diagrams that may be appropriate for examining the patterns and
regularities in the data.
28
10. Conduct a pilot study
It is important to conduct a pilot study to identify areas that may require revision and
correction in order to refine both the instrument and data analysis procedures to achieve
the research objectives and to review the choice of statistical tools.
11. Revise and fine-tune the research techniques
The findings of the pilot study could be valuable to make the necessary changes to the
research instruments and the data collection and data analysis strategies.
12. Implement the final data collection design
The researcher should implement the data collection design and at the same time should
not lose sight of the ethical issues of participants in the study. The researcher must ensure
that the study conforms to broad ethical guidelines.
13. Analyse the data
During data analysis, the researcher should be guided by the research objectives. It is
necessary for the researcher to ensure that their own preferences and preconceptions are
not imposed on the data.
14. Write the theses/dissertation
Before writing the dissertation, the points about the procedure to be adopt in writing the
literature review should be taken into consideration.
Develop an appropriate research design

The research process outlined above spells out the actual process. A concurrent process,
however, which is the development of a research design appropriate for the needs of the
research topic, requires the researcher to engage in a series of choices and decisions.
RESEARCH PHILOSOPHY
The research philosophy comprises the perceptions of the way data about a phenomenon
should be assembled, analysed and used. Research paradigms incorporate the fundamental
philosophical concepts and values about the nature of reality and the scientific pursuit of
knowledge. Importantly, there are two schools of thought about science and knowledge –
positivism and phenomenology. They hold diametrically different views about the research
process and research design.
29
Positivist (quantitative research)
Positivism evolves around the use of numerical measurements and statistical analyses of
measurements to examine social phenomena. Positivist research is generally quantitative
in nature.
• It views reality as a consisting phenomenon that can be observed and measured.
• It places great premium on objectivity and reliability of findings and encourages
replication.
When it is applied to social sciences and business research, positivism may not always be
appropriate, as all social phenomena cannot be accurately and reliably measured, thus
reducing the validity of the findings.
Phenomenological (qualitative) research

Subjective researchers argue that the world is a social construct and that science is driven
by human interests and that the researcher, as a subjective entity, is part of the world they
are observing.
• Objectivity is an impossible aim.
• The findings often have greater validity and less artificiality as the process of observing
phenomena in a natural, real-life setting.
• It often allows researchers to develop a more accurate understanding of those
phenomena.
• It often reveals depth of understanding and richness of details.
However, research driven by phenomenological philosophy is sometimes undermined by
the subjectivity of the researcher and the poor reliability of the findings in that two
researchers may arrive at different conclusions based on their observations of the same
phenomena at the same time.
Figure 3.1 below is a layout structure of qualitative research and the choice a researcher
may undertake.
30
Figure 3.1: Structure of qualitative research
Mixed research approach

Noticing the strengths and weaknesses that flow from both positivistic and phenomenological
biases in research, researchers sometimes adopt a mixed approach that draws on both
positivism and phenomenology.
The use of multiple research methods enables the researcher to increase the reliability
and validity of the findings.
The weakness of one method can be reduced by the strengths of other methods incorporated
in the same study.
Figure 3.1 below provides aspects relevant in the research philosophy.
31
Figure 3.2: Research philosophy
RESEARCH PROCESS WITHIN A MIXED METHOD FRAMEWORK

The two main paradigms represent two extremes of a continuum; therefore, it is possible for
the researcher to use a blend of philosophical assumptions and methodologies. Creswell
(2014) noted following about the mixed method framework:
• It is a – two-phase design in which the researcher conducts entirely separate positivist
and phenomenological examinations of the problem.
• The dominant/less dominant is where one paradigm dominates while the other is
used for a small component of the study (e.g. the researcher may use observation
and in-depth study to generate themes and variables and then use a quantitative,
hypothesis-testing design for the study as a whole).
The use of a mixed-methodology design allows the researcher to combine aspects of both
paradigms using the advantages of both when appropriate.
32
RESEARCH STRATEGIES
A brief description of some of the important research strategies available to students/
researchers is provided next. Each strategy differs from others in two distinct areas: the
nature of the question asked and the method used to answer it.
Positivist research strategies/experimental design

The basic experimental designs used in research have been adapted from the physical
and biological sciences. Experimental studies seek to identify causal relationships.
• The aim is to manipulate the independent variable in order to observe the effect on
the dependent variable.
Because of the greater difficulty to control experimental conditions in the human sciences,
experimental methods can only be used under very clearly defined conditions. The typical
experimental design in for instance in business research involves:
• the selection of a sample of subjects; random assignment of these subjects to
experimental and control groups;
• the exposure of the experimental group to the independent variable which is withheld
from the control group;
• finally, the evaluation of the two groups on the dependent variable. There are other
variations in experimental design – repeated measures design, matched-pairs design
and single-subject design.
In a quasi-experimental design, the researcher does not have as high a degree of control
over the independent variable. People, for example, are already assigned to groups such as
social class, type of injury, type of occupation and income group, for which the researcher
is testing the effects. The experimental designs isolate and control all the factors that could
be responsible for any effects except the one under examination. The most important use
of quasi-experimental research designs is where researchers cannot, in good conscience,
assign people to groups and test the effect of the group’s membership on some other
outcome. For instance, researchers interested in the effect of retrenchment on staff morale
could not encourage the process or actively identify those to retrench in any organisation.
Rather they would seek out companies where retrenchments are occurring and then
conduct the research.
Quasi-experimental research is also called post-hoc research or after-the-fact research
means that the actual research takes place after the assignment of groups such as
employed versus unemployed, male versus female, etc.
33
Surveys
The survey is a research design in which a sample is selected from a population and
studied to make inferences about the population. Surveys typically use questionnaires and
interviews in order to determine the options, attitudes, preferences and perceptions of
persons of interest to the researcher.
In well-designed surveys, the sample can be carefully selected to ensure that it is a
representative of a larger population; it is possible to use statistical techniques to assess
the applicability and generalisability of the findings to the large population. To ensure
greater reliability and validity, the researcher must also ensure that the questionnaire and
interview do not reveal bias in the way the items and questions are presented. The way
questions are asked, for example, can influence the responses.
Phenomenological research strategies

Case study
A case study is a research strategy and an empirical inquiry that tries to investigate a study
phenomenon within a real life context. They are normally based on the following:
• In-depth investigation of a single group or events to explore and understand the
underlying causation principles.
• Involves looking at groups, a project, institution or company.
• Requires intensive investigation of the factors that contributed to the characteristics
of the case under investigation.
• Draws on multiple sources of information and tells a story, usually in chronological
order.
The aim is to create a rich, textured description of a social process. This can set the stage
for more questions that can be asked later, using more tightly structured methods. Case
studies are usually helpful when the researcher is dealing with the following questions:
• How or why questions
• Phenomena over which the researcher has little control
• Phenomena embedded in a real life context.
34
Data collection methods in the case study
Figure 3.3: Case study data collection methods

The case study design differs vastly from other research methodologies in that researcher
tries to examine a huge number of elements by constraining the number of cases that
should be observed. Another distinctive element is that the case study researcher in
general tends to be an in-depth investigator of phenomena, as they exist in the character
setting (Yin 2009).
Two techniques that are often used to analyse case study data are pattern matching and
time-series analysis. Pattern matching is the process of taking several pieces of information
that seem logically related and connecting them to some idea or theoretical proposition.
The patterns should be compared to rival theories, looking for the best ‘fit’ of observed data
to theory. Time-series analysis involves comparing a trend of data points to some
theoretically significant trend, or to some other alternative explanation.
Action research
Action research can be defined as a reflective process of progressive problem solving
facilitated by individuals, or groups working with other teams trying to improve and address
an issue in a community. Action research is a strategy that has the dual aims of action and
research:
35
• The action is to bring about change in for instance a community or department
• The research seeks to increase the researcher’s understanding and/or that of the
target group/community.
Action research is a cyclical process that consists of:
• planning
• action
• review of the outcomes of action
• reflection because of outcomes.
At each point in this cycle, the data available is used to determine the next stage. The
whole purpose of the research is to determine simultaneously an understanding of the
social system and the best change opportunity available.
Researchers generally adopt an action research design to increase the reliability of their
findings by working with various data sources, ideally autonomous or partly independent
samples of witness/informants, diverse research settings, the same informant responding
to different questions which address the same topic from some different directions, data
gathered at various occasions by different researchers or diverse techniques.
Grounded theory
Grounded theory can be defined as a step-by-step methodology in the social sciences that
involves the construction of differentiated theories through gathering methods and analysis
of the data. The use of grounded theory methodology as a research strategy remains
minimal partly because of the bias of favouring deductive and quantitative approaches and
partly because of a critical view that some researchers have of the grounded theory
methodology.
Grounded theory has as its basic tenet view that theory must be inductively derived from
the data. The theory, in short, must emerge from and be grounded in data.
• Data collection, analysis and theory formulating are regarded as reciprocally related.
• The emergent theory should account for the phenomenon that is relevant and
problematic for those involved.
• Data collection and analysis are fused deliberately, and the initial data analysis can
be used to shape continuous data collection.
• Interweaving data collection and analysis increases insights and clarifies the
parameters of the emerging theory.
The approach also argues for initial data collection and preliminary analyses to take place
in advance of consulting and incorporating prior research literature. This is to ensure that
pre-existing constructs do not shape the current analysis and theory formation.
36
Hence, the literature review is purely needed to be underscored but is delayed, not omitted,
and is regarded as an important part of theory building.
Ethnography
Ethnography normally involves the scientific description of people, customs and their culture
as well as the mutual differences between human beings. Ethnography is not a widely
used research strategy as it is time consuming and generally requires the researcher to
immerse himself in the real-life context of interest as a participant observer. Over a period,
the researcher gathers data and applies an inductive methodology to uncover patterns of
meaning.
Mixed research strategies

Positivism and phenomenology are like two ends of a continuum. Researcher may regularly
create a research structure that joins research strategies from those two paradigms in a
solitary research plan. For instance, a researcher may utilise a subjective methodology in
conducting in-depth interviews with people from the objective populace and after that
continue to test these provisional ends in the bigger populace through a survey research
technique and quantitative, statistical analysis tools.
RESEARCH PURPOSE
Research design may also be classified in terms of its purpose. Below are some of the
common forms of research design based on their general purpose.
Causal-comparative research
The fundamental target of causal-relative examinations is to use an exploratory or quasi-
experimental design to contemplate firmly equivalent groups (except on the variable being
studied) to establish contrasts, explanations behind these distinctions and to reveal causal
connections among factors. The causal-comparative approach in research is profitable in
distinguishing conceivable foundations for human conduct in the business and the board
setting.
Correlational research
Correlation research refers to studies in which the purpose is to discover a relationship
between variables with correlational statistics such as the correlational coefficient® which
measures the strength of this relationship. A correlational connection between two factors
is every so often the after effect of an outside source; the researcher should be cautious
in not contending for a circumstances and logical results connection between the factors
37
only in view of the relationship between them. In the event that a solid connection is found
between the two factors, causality can be tested by utilising an experimental research
design. It is important to note that, logically speaking, correlation is necessary for causation
but not sufficient for it.
Correlation studies can sometimes be prediction studies or ‘relationship studies’. A
noteworthy preferred standpoint of correlational research is that the examiner can
investigate a wide range of connections in a similar report. One of the most important points
about correlation research is that it examines relationships between variables but in no way
implies that one causes the other.
Explanatory research
Explanatory studies seek to explain the relationship among variables and to identify the
connectedness among the components of a phenomenon. The essential point in these
examinations is to intently study a problem, gather information on the subject, and through
an explanatory and deductive procedure, frequently involving measurable investigations,
to clarify the relationship among factors.
Descriptive research
Descriptive research describes the characteristics of an existing phenomenon.
• Descriptive studies seek to discover answers to questions relating to the fundamental
characteristics that define the research subject.
• Often descriptive studies are conducted to advance the broad aims of science.
• Descriptive research is done to develop knowledge on which the problems and
explanations of subsequent research are based.
Descriptive research, however, often goes beyond a mere description of the phenomena.
For instance, if interested in the occurrence of conflicts and development and their impact
on the people, the researcher may survey a sample of the relevant community and present
a descriptive account of the phenomenon. However, the researcher may also examine the
responses of the people in the affected community and through analysis of the data will
identify a pattern of behaviour at various levels of the community.
Exploratory research
Exploratory studies are primarily concerned with finding out what exists and gaining new
insight into a phenomenon. The researcher undertakes an in-depth search of the literature,
interviews specialists in the field, and conducts focus group dialogues. From these different
sources of data, the researcher starts to form an idea of the actual field of intrigue.
38
CHAPTER FOUR: SAMPLING
Outcomes
• Explain why sampling is fundamental to research
• Define the terms generalisation and representativeness
• Explain the difference between a sample and a population
• Discuss the appropriate usage of the various types of probability and non-probability
sampling techniques
• Be familiar with a range of sampling techniques
• Identify the different types of sampling.
INTRODUCTION
Sampling is a procedure of methodically choosing targets for consideration in a research
project. The assets of the sample or the group or subgroups of the population are then
generalised to the population. This process of sampling helps to solve the research problem.
• This process of selecting a small part from the relevant group of the population is
called sampling.
• The essential point is that by choosing a portion of the components in a populace and
concentrating research consideration on this limited group, the specialist may apply
the discoveries of the investigation to the entire populace of interest.
A population is the full arrangement of components from which an example is drawn. A
populace component is the single unit of the example from which estimations and
perceptions are drawn.
Note:
• In sampling, the term population is not used in the normal sense, as a full set of
elements may not necessarily be people. For instance, the researcher may wish to
examine the administrative effectiveness of local schools in Astana – then the
population from which they would draw the sample would be local schools and each
local school would be an element in the population of local schools of Astana.
There are two types of sampling – probability and non-probability.
In probability sampling, the likelihood of any one member (or element) of the population
being selected, is likely known. For example, if there are a thousand local schools and two
hundred local high schools in Astana, the odds of selecting one high school as part of the
sample is 400:1000 or 0.40.
39
However, in non-probability sampling, the exact number of elements in the population is
unknown with the result that the likelihood of selecting any one member in the survey and
cannot be computed.
THE WHYS OF A SAMPLE POPULATION
Mind map 4.1: Reasons for sampling

As noted above, it is often not feasible to study the entire population. The major reasons
why sampling is necessary, as listed in Mind map 4.1 are discussed next:
1. Cost-effective procedure for quality control
To guarantee that its items satisfy the guideline tests. Every item in the sample should go
through a thorough test and its capability recorded. Clearly, if all things are exposed to
limited tests, none would be accessible or available to be used.
2.The physically impossibility of checking all items in the population
In cases in research where the population is enormous and developing, it is hard to portray
in fixed terms the range of the population.
3.The cost of studying all items in a population is often prohibitive
The cost of including all the members or items of population is often prohibitive. Unfortunately,
selecting a smaller population can result in an invalid sample.
4.The appropriateness of sample results
Good sampling techniques should maximise the degree to which the samples represent
the population. The results are therefore generalised to the whole population.
40
5.Time-consuming to contact the whole population
In instances where population has more than 1000 objects, to interview every member
would take a considerable amount of time if the researcher were undertaking the task
alone.
The sampling cycle

Three specific sub-components are relevant:
• The invited sample
• The accepting sample
• The data-producing sample.
The invited sample is all components of the populace chosen to form the sample and invited
to participate in the study. The section of the sample that acknowledges the invitation to
participate in the study is called the accepting sample. The data-producing sample is the
actual portion of the sample that provides information for the study.
Representatives
Applying the findings and generalisation of a study to the population and the universe is
only permissible when the sample can be considered a representative of the population.
Hence, in the sampling process, the researcher must be:
• Guided by the recurring requirement to ensure representation.
• It is important for the researcher to face the critical issue of determining whether the
actual number of respondents constitute an adequate percentage of the sample for
the findings to be representative of the study population.
KINDS OF SAMPLING
The two extensive categories of sampling designs are probability sampling and non-
probability sampling.
Probability sampling is based on the concept of random selection – a selection procedure
that ensures that each element of the population is given a known chance of selection.
Non-probability sampling is non-random, purposive and subjective because the
researcher may select the sample using criteria other than those associated with
randomness of selection.
Mind map 4.2 below lists all the features of probability and non-probability sampling.
41
Mind map 4.2: Kinds of sampling
Mind map 4.3 below illustrates the different types of sampling design, followed by Mind
map 4.4 illustrating.
Mind map 4.3: Types of sampling design
42
Probability sampling
Simple random sampling
• Each element in the population has an equal and independent chance of selection
as part of the sample.
• There is no bias or predetermination in the selection process.
For instance, in simple random sampling, if the researcher decides to choose every fifth
element in the sampling frame, that is, the actual list of the elements from which the sample
is actually drawn, ideally the complete and correct list of population members only, then
there is no independent randomness in the selection process.
The process of random sampling consists of four basic steps:
• Define of the population clearly
• List all members/elements of the population
• Number the elements of the population
• Select the sample, use an approach that guarantees randomness.
For the actual sample selection, use a table of random numbers or a computer program to
generate samples. Often, simple random sampling is not practical as it requires a complete
list of a population which is not always possible.
Systematic sampling
Systematic sampling is a method of probability sampling where the target from the larger
population is chosen according to a random starting point but with fixed periodic interval.
• The interval is calculated=
Systematic sampling is one statistically valid alternative. In this approach element in the
population is sampled, beginning with a random start of an element in the range of one.
Systematic sampling is simpler than simple random sample; however, it may not be as
exact as simple random sampling in the randomness and independence of the selection
procedure.
Stratified sampling
It is desirable to select a sample to assure that all sub-groups represented in the population
are in proportion to the sample, and match the profile of the population.
Essentially: the steps in stratified sampling would be as follows:
• Identify the various strata in terms of the variables of interests, for example, in the case
of a school, it would be the principal, deputy principals, teaching staff and students.
43
• Separate the sample frameworks and establish each stratum with a list of all the
elements/members who fall into a stratum.
• Each member in each group receives a number.
• The proportion of each group in relation to the total population is established and the
number that will be selected from each stratum is calculated accordingly.
• Use a table of random numbers, the individual members are selected from each
stratum in terms of the required numbers.
Calculation of strata samples:
• How large the total should be, and
• The ratio by which the total sample should be allocated among the strata with both
proportionate and disproportionate options available to the researcher.
Cluster sampling
In cluster sampling, the sampling unit is not the individual component or member but rather
a naturally occurring group of individual members. For instance, the researcher might
examine teachers’ responses to the executives amid the underlying phases of filling senior
positions in school in Astana. It is not plausible to study or convenient to choose people
from a wide scope of teachers’ settings. It would, for instance, be either unrealistic or
difficult to get a list of the theoretical population. In this situation, cluster sampling would
be most practical and convenient:
• Division of population into groups of elements either geographically or by some other
uniform criterion
• Random selection of groups.
In any case, it is most essential to stress that researcher should pick a cluster only when it
is the most conservative and proficient regarding time and money and when it is essentially
difficult to set up a solid examining frame of individual components.
The researcher must guarantee that the cluster has been productively characterised, then
haphazardly select the required number of groups and afterwards continue with the
suitable probability sample system. It is critical to stratify the sampling regularly in order to
guarantee full inclusion of the number of strata in the number of population in each cluster.
44
A comparative summary of various types of sampling
Mind map 4.4: Various types of sampling
Figure 4.1: Merits and demerits of sampling

45
Non-probability sampling
Non-probability sampling is often the chosen route when the researcher, for instance, is
undertaking an exploratory, qualitative study and does not have the objective of generalising
the findings to the population from which the sample is drawn.
• With probability sampling, bias and subjectivity are reduced or eliminated through the
random selection of elements.
• There is relatively high level of confidence that the sample is representative of the
population from which it is drawn.
• The greater scope allows the researcher subjectivity in the constitution of the sample.
However, there is more a noteworthy ‘open door’ for the researcher who wants to influence
the sampling system and that is to contort the discoveries of the examination. Cost and
time factors may likewise affect the decision of non-probability sampling as it requires
cautious planning and a far-reaching definition in characterising the population and setting
up the sampling outline
Convenience sampling
The researcher has the opportunity to pick whoever is accessible for consideration in the
sample. Despite the fact that it is not a dependable research structure, convenience
sampling is frequently the most effortless to establish and impact. Models incorporate the
choice of companions and neighbours who are anything but difficult to find and helpful to
survey. While the discoveries made from convenience sampling may not be exact and
need unwavering quality, they might be helpful, for instance, in the exploratory systems.
For the most part, this technique does not require much to recognise or legitimise it as a
sampling strategy as it does not have a sound research ethic and legitimacy.
Judgmental sampling
Judgmental sampling is a type of a purposive sampling. Purposive sampling, thus, is a
conventional term used to depict any sample intentionally picked by the specialist in
accordance with predetermined non-probability criteria.
For instance, in an investigation of artificial intelligence trends, the specialist might need to
meet just those with a genuinely wide involvement in the field. When it is used in the
beginning of an exploratory or descriptive examination, it serves as a powerful time-
proficient strategy.
Quota sampling
Quota sampling is another purposive approach available to the researcher. The study may
require a sample of certain variables but for some valid reason proportional sampling is
not possible. In this situation, quota sampling may be an appropriate choice to improve the
representativeness of the study.
46
• The population is divided proportionately into predetermined categories.
• The subject category is deliberately selected from the population until a particular
quota is met for each category.
Two basic conditions:
• Firstly, the categories should have a distribution in the population that can be
estimated, and
• Secondly, the variable used in forming each category must be relevant to the topic
of the study.
For example, in a study of the buying patterns of young executives working in the government
institutions in Astana, the following categories can be identified for quota sampling:
• Gender: 2 categories – male, female
• Marital status: 3 categories – married, single, divorced
• Family social economic class: 3 categories – upper, middle, lower
• Educational qualification: 4 categories – postgraduates, undergraduates with
diplomas, high school diploma, non-high school diploma.
From the combination above, the researcher will proceed to locate subjects who fall into
each category in terms of an estimate of their occurrence in the population.
Maximum variation sampling
In this form of purposive sampling, the researcher identifies the categories of interest in
relation to the research topic and then intentionally seeks out subjects or settings which
will represent the greatest possible range of differences in the phenomena being studied.
Snowball sampling
In the initial stages of snowball sampling, individuals are identified using probability or non
-probability methods. The group is then used to locate other subjects who possess similar
characteristics who, in turn, direct researchers to yet other possible participant for the
study.
Sampling error
Sampling error is the difference between the statistical characteristics of the sample and
those of the population from which the sample was selected. The results are not likely to
be identical to the population statistic. The larger the diversity of sample values, the larger
the error and the less precise and representative the sample will be in relation to the
population from which the sample was selected.
• The objective of good sampling is to ensure that the sampling error value is as low
as possible.
47
Sample size
Sample size can be statistically calculated. However, the researcher can proceed without
calculating a scientifically precise sample size. The researcher needs to be guided by the
fact that a sample that is too small is not likely to be representative while one that is too
large is likely to increase costs and time demands without producing significant benefits.
• Generally, a larger sample is advisable to ensure good respresentation.
• Sub group the sample into smaller units for analysis
As variability increases, it means that people/aspects in the sample are more diverse. This
implies that more information is required to be representative of the sample.
It is very important that researchers should keep the following in mind when determining
the size of their samples:
• In general, the larger the sample (within reason), the smaller the sampling error and
the higher the representativeness of the sample.
• If the researcher wishes to discuss the influence of variables such as gender, age,
and profession in the findings, then the initial selection of the sample must be large
enough to enable the eventual creation of statistically sufficient numbers in each
category or sub-sample .
• While a big sample is good, an appropriate-sized is better as it is more cost-effective
in terms of time and money.
The following image is a convenient summary of the various sampling methods.
48
CHAPTER FIVE: DATA COLLECTION
Outcomes
By the end of the chapter, the learner will be able to:
• Identify the different primary and secondary data collection strategies
• Explain the appropriate use of questionnaires as data collection instruments
• Define the terms validity and reliability
• Classify and explain the purpose and types of research interview
• Describe the types of observations and their use in research
• Explain data collection procedure in ethnographic studies and case studies
• Discuss the concept of triangulation and its relevance to good research design.
INTRODUCTION
The entire research planning, design and literature review processes converge at the data
collection stage. All the critical thinking is a preparation for the actual process of collecting
primary data on the topic of the research. Additionally, the researcher must also have the
data analysis plan established before planning data collection and data analysis requires
clarity about:
• The format of the research instruments
The analyst must guarantee that all classifications of information necessary to examine
the objectives are incorporated. In addition, there must be clarity about all aspects that the
research instrument(s) need to analyse, how qualitative and quantitative items will be
handled and analysed during the data analysis stage.
• Identify appropriate statistical technique
The researcher must have a full grasp of the particular statistical strategies that will be
used to examine each segment of the exploration instruments. Should inferential statistics
be required, the researcher must make sure they understand the procedures and the
translation of the significant measurements.
• Data layout and presentation
The researcher must select the type of tables and graphics that will be used in presenting
the data.
49
• Pilot study
The researcher must test the instruments with a small pilot group, inspecting the ease of
use, accuracy and sufficiency of the information to be used in the actual research study.
Anything that needs improvement can then be dealt with prior to commencing the study.
IMPLEMENTING THE PLAN

The data collection plan may not be implementable as a unique or perfect structure and
therefore the researcher must be able to address unexpected possibilities. For example, if
access to one of the groups is denied for some unexpected reason. It is thus necessary to
have alternate courses of action for every conceivable challenge.
Interaction with participants in the study

The information-gathering plan must aim to encourage positive, informed interaction with
the research participants. Prior to the data collection, all respondents are entitled to have
all information about the investigation explained to them, including what is expected of
them. The researcher must explain what the outcome of the results is for, so that the
participant can decides if they want to participate in the research. Further, the researcher
must guarantee tension free participation for the participants and that confidentiality will be
maintained.
DATA COLLECTION METHODS

The specific research instrument that is most suitable for the topic should be stated during
the research design stage.
The two most commonly used primary data collection methods are the questionnaire and
the interview. All research is generally concerned with obtaining answers to questions.
Data collection instruments:
• Interview
• Questionnaire
The questionnaire and interview are data collection instruments that enable the researcher
to pose questions to participants in search of information on the research topic. Each of
these instruments has distinct features that enable the researcher to decide which is the
correct and appropriate one for the specific data collection purpose.
50
Appropriate research context
Questionnaires are most widely used in surveys with a descriptive or exploratory purpose.
They can, however, also be effectively used in studies with experiment and case study
research strategies. The appropriateness of questionnaires as research tools must however
be carefully examined in the context of each study. Students sometimes fail to grasp that
observation, semi-structured interviews and other data collection procedures may be more
appropriate for their research objectives than questionnaires. Saunders et al. (2003:280)
maintained that it is generally good practice not to rely solely on questionnaire data but to
use the questionnaire in conjunction with at least one other data collection instrument. For
example, a questionnaire designed to establish customers’ attitudes can be complemented
by in-depth interviews to explore and understand the basis of these attitudes.
Questionnaires
The questionnaire comprises various standardised questions designed to gather the data
required. The questions serve to gather the data expected to test your theory. You need to
give attention to the reliability of responses and the legitimacy of the discoveries/findings
from the research instrument.
Questionnaire design
In designing questionnaires, there are five main issues that need attention, as discussed
in the sections following Mind map 5.1 below:
Mind map 5.1: Designing questionnaires
51
1. Categories of questions
The questions included on the questionnaire should individually and collectively provide
the data required for successful achievement of the research objectives. A well-constructed
questionnaire also has a range of question categories, each consisting of small number of
related questions, intended to elicit information of a particular type relating to the research
topic.
• Socio-demographic items : to develop a “summary” of the respondent by asking
questions about their gender, marital status, age group, occupation and related non-
sensitive personal information.
• Orientation items: to familiarise the respondent with the core issues relating to the
research and sometimes to test their level of knowledge of the topic.
• Behavioural questions: to measure attitudes, beliefs, opinions, motives and
behaviours. Attitude questions record how respondents feel about something (their
belief in something) and opinion questions record what respondents believe is true
or false.
• Content-related questions: to elicit data on the major purpose and content of the
research topic.
2. Number and content of questions
Most researchers tend to include too many questions in their questionnaires. This often
arises from an incomplete analysis of the research objectives. Researchers should
therefore have absolute clarity about their research objectives, and keep these in mind
during the planning and design stage so that all the items on the questionnaire are relevant
and have a clear purpose. Clear, concise and well-constructed questionnaires generally
result in a better participant response rate.
3. Structure and layout of the questionnaire
This includes the researcher determining the numbers, question classifications and the
kinds of inquiries. It is necessary to consider the genuine structure and format of the
questionnaire and the succession of the questions. A few recommendations here are that
the researcher should begin with comparable and recognisable ‘introduction’ questions,
continue to ‘content’ and conduct questions and keep the individual, socio-demographic
items for last and to word these cautiously to abstain from giving offense.
4. Type of questions
The following broad points are noteworthy:
• Closed questions that define the participant’s range of responses to questions are
better suited to questionnaires as they readily lend themselves to coding and to
analysis.
52
• Questions should be designed to facilitate computer analysis as this allows for rapid
computation, statistical analysis and graphical presentation of data.
Depending on the needs of the research topic and the range of data required for
comprehensive coverage of the research objectives, the typical question formats include
the following:
• Single-option responses (‘yes’, ‘no’ or short answers)
• Multiple choice responses (sets of options)
• Rating questions (using Likert scales, for example)
• Ranking questions (ranking set of options).
5. The wording questions
Clear correspondence should be an essential objective of all questionnaires. The researcher
should avoid wording that gives rise to misconception, proposes analyst predisposition, or
is offensive. The following are a few suggestions for the wording of questions.
Suggestions
1. Avoid open-ended questions:
If necessary, categorise the questions into discrete groups. For example, the question:
• What do you think are the reasons for racism in football?
These sorts of questions may create an entire scope of answers of varying length and
articulation. If the researcher is keen on making extremely exact decisions about every
individual respondent, this likely could be valuable.
2. Plan to computerise analysis
It is effective to compute all the results as soon as possible because the responses from
the participants will still be fresh in your mind as a researcher.
3. Keep answers mutually exclusive
When designing questions for a single answer, make sure you have just one answer. For
example, if the following question is asked?
How do you travel to work?
A different number of replies from each respondent may be expected.
Phrasing the question as “What is your most usual means of traveling to work?” will certainly
help but may not include all the information needed. The respondent should be allowed to
select a combination of answers to what is in fact a series of independent dichotomous
yes/no questions
53
4. Ranked replies
A useful way to ask an ordering set of options may be to demand a numerical ordering from
1 to the maximum number you are interested in.
For example, to a question like:
Place in order of importance the following features of a camping holiday (indicate by
numbering from 1-5 in order of importance)
Open air
Mobility
Cost
People
Atmosphere
5. Avoid dual questions
Do you think the Kazakhs should eat less and exercise more?
Instead, ask:
Yes No
Do you think Kazakh’s should eat less? 1 2
Do you think Kazakh’s should exercise more? 1 2
6. Avoid asking questions involving negatives
Do not confuse the respondent by language such as this:
Yes No
Are you against a ban on smoking? 1 2
Confusion leads to errors!
Instead a better wording would, do you support a ban on smoking?
7. Getting the maximum response
The researcher cannot always expect the respondent to have the same concern for the
greater good. The following two main considerations must be made when asking a person
to give up some time to help the research:
• Firstly the researcher must allow for privacy and not ask questions which may offend.
• Secondly, especially if there is a need to ask some personally searching questions, it
helps to explain the reason for the research to the respondent, both at the beginning
and during completion of the questionnaire.
54
8. Explain the purpose of the questionnaire
The researcher must clarify the reason for the survey to the participants before they answer
the questionnaire and should include a covering letter with the questionnaire which also
explains the reasons for the study. In addition, the survey itself should have an opening
segment that clarifies the essential point of the examination and the significance of the
participants’ involvement in the study.
Pilot testing
Before administering the questionnaire to members in the examination, the analyst must
test it on a small sample. The analysis of the pilot survey will reveal flaws in certain
questions.. Moreover, the pilot study empowers the researcher to do the following:
• Make amendments necessary to maximize returns and minimize the error rate of
answers
• Categorise the open-ended questions effectively
• Perform the analysis on the pilot sample, test all the computational procedures and
produce some initial hypothesis
• Evaluate the adequacy of the data for the research questions.
Validity and reliability
Validity addresses the issue of whether the researcher is actually measuring what they set
out to do. There are four types of validity – each of which the researcher would ideally want
to establish for the research instrument prior to administering it for the actual study. These
four types are listed in Figure 5.1 below.
Reliability of a research instrument refers to the consistency or repeatability of the

components of reliability. There are three types of reliability, as listed in Figure 5.2.
Interviews
Interviews and questionnaires are two of the most widely used primary data collection
methods. Questionnaires have been dealt with in detail in the previous sections. The
interview is a form of data collection that is very common in descriptive research such as
surveys, and can be use to collect valid and reliable data in other types of research. In
contrast to questionnaires, interviews generally tend to:
• Make greater use of open-ended questions
• Are associated more with qualitative, phenomenological-oriented research
• Make use of small, deliberately selected purposive samples.
55
Figure 5.1: Types of validity
Figure 5.2: Types of reliability

56
Direct, verbal interaction
The interview is unique because it involves the collection of data through direct verbal
interaction (often face-to-face).
• The interview enables the researcher to follow up verbal leads and thus obtain more
data and greater clarity.
• The interview situation also permits much greater depth than other methods of
collecting data.
There are various types of interviews with the highly structured, interviewer-administered
questionnaire and the structured open-ended, in-depth interview as opposite ends of a
continuum.
Types of interviews
The various types of interviews and their characteristics are listed in Figure 5.3 below.
Figure 5.3: Types of interview
57
Each type of interview has a different purpose:
• Highly structured and structured interviews may be used in surveys and be processed
quantitavely.
• In contrast, semi-structured and unstructured interviews are essentially qualitative,
phenomenological-oriented data collection methods. They enable exploratory
discussion that help the researcher to understand the what and the how but also to
grasp and explore the internal dynamics of the research topic.
The different kinds of interviews can be used in a solitary study to expand the reliability of
the findings. For example, in-depth, instructed interviews might be used in the underlying
phases of the examination to distinguish subjects and factors. This information could then
be used to plan a questionnaire or a structured interview to look at explicit subjects and the
cooperation of explicit factors.
In addition, in the second phase of a quantitative questionnaire, semi-organised or
unstructured interviews might be used to investigate and to approve the discoveries from
the questionnaire.
Design of interview
Most interviews include composed content or some likeness thereof with differing
dimensions of adaptability structured into the interview plan (the organisation, composed
posting of the inquiries or subjects). In an exceptionally organised interview, the plan of the
meeting would be fundamentally the same as that of questions. The unstructured open-
ended interview, on the other hand, would have no schedule of questions at all.
Furthermore, semi-structured interview schedules would consist of some closed questions
with the interviewer having the freedom to ask the participant to provide more details, as
well as a test of open-ended questions and themes for discourse.
Conducting the interview
The subjects or participants are chosen for their experience and specialist background to
establish a purposive sample. Interviews do not require large samples. In the interaction
with the subjects in the sample, the interviewer should avoid the common pitfalls in the
interview that might affect the reliability and validity of the findings.
The following should be avoided during the interview:
• Agreeing or disagreeing with the subject
• Suggesting answers
• Displaying bias or prejudice
• ‘Leading’ the subject
• Being in any way judgmental
58
• Lapsing into general conversation.
In addition, interviewers should use an appropriate dress code and create a conducive
climate before commencing with the interview.
Recording the interview data
Generally, it is not appropriate to make notes as the interview is in a process as this is not
only distracting to the participants, but disrupts the flow of the interview. The researcher
may also give the subject clues about points of importance and so influence the subject’s
later responses.
• More appropriately, the interviewer should use a tape recorder, phone recorder (with
the subject’s content)
• Use an accompanying note-taker
• Make the relevant notes as soon as possible after the interview.
In summary, the interview is an excellent technique for gathering certain kinds of research
information. However, because of its subjectivity, there are as noted before, many potential
sources of bias.
Observation
General characteristics
An observation involves systematic observing, recording, description, analysis and
interpretation of people’s behaviour. There are numerous positive viewpoints to observational
research. Perceptions are normally adaptable, empowering the researcher to assemble a
wide scope of information for an assortment of research destinations. For instance, before
attempting more structured research, a researcher may lead observations to frame an
exploration question. Regarding validity, observational research discoveries are seen as
effective because the researcher can gather in-depth data about a specific phenomenon.
Reliability and generalisability of discoveries, notwithstanding, are not similarly high. In
observational research, the discoveries are often identified with a unique population and
in this way not fully appropriate to the bigger population. Nonetheless, observations are a
profitable instrument for research.
Appropriate use of observation
As indicated above, observation can in conjunction with other data collection methods
increase the reliability of the study.
Some points to note when deciding on the use of observation as a research tool:
• Sensitivity of the topic
59
Now and then members are hesitant to respond to inquiries concerning sensitive issues.
For instance, if the researcher aims to investigate gender prejudice among staff, numerous
individuals would be hesitant to uncover the reality about their perspectives and attitudes.
Rather, the researcher should observe staff communication in a big organisation. In this
case, observations are probably going to help with grouping precise information. Hence,
delicate social issues are better drawn with observational research.
• Observation of the phenomena
The researcher must determine what is applicable to the study. For instance, you cannot
see attitudes but you can observe behaviours and make inferences about attitudes. It is
important to bear in mind that questions regarding sexual conduct can be better
accommodated with the guide of a survey questionnaire that gives members anonymity.
• Available time resources
Observational research is tedious. In order to obtain total reliability, behaviours must be
watched a few times over an undefined period of time. Further, the participants may over
time get used to the observer’s/researcher’s presence and act more normally.
Research clarity and gaining insight through observation
Frequently, the analyst may start with the area of intrigue yet not have full clarity on the
theme and the exploration questions. Observation for an undefined period may recommend
a hypothesis and a theory testing technique. These perceptions become hypotheses once
they are repeated.
Types of observations
Participant observation
As with interviews, there are two broad categories of observation – participant observation
and structured observation. Saunders et al. (2003:224) classified the researcher roles in
participant observation in terms of the researcher’s involvement in the activity being
investigated and the subjects’ awareness of the researcher’s/observer’s presence.
The roles of participant and researcher/observer require the researcher to conceal their
identity and research preoccupation.
• The advantage is that the research participant does not modify their behavior as a
reactive response to an external agent.
• They act naturally and spontaneously because they do not know that they are being
observed. There are ethical issues in this form of data gathering because there is
deception of the subjects.
In contrast, the researcher/observer as member jobs involves the analyst uncovering the
exploration destinations to participants. While there is the threat that they may respond to
the researcher’s presence by not being honest, they may well share their sentiments.
60
Structured observation
Like structured interviews, structured observation is efficient with a predetermined
convention for perception and obviously characterised criteria for categories and
structures. The goal is to measure the observed behaviour. The procedure fundamentally
includes building up the clear, noticeable certainties and grouping information to meet the
examination objectives.
Observational variables
In both participant and structured observation, the researcher has to know what they are
observing and how to interpret the observations.
Three categories of data of participant observation.
• Primary observations: relate to observations of what is said and done. The
researcher may use diaries to record this data.
• Secondary observations: relate to statements by observers of what is said or done.
• Experiential data: records the perception and feeling in the course of observing
phenomena. Diaries are used to record this data.
The critical issue in the choice of any data gathering technique is that it must effectively meet
the demands of the research objectives. This is also true of observational data collection
techniques. It is also important, as with other data collection strategies, that the researcher
should start with understanding how they are going to interpret the observations.
The data may be categorised into three-analysis perspectives:
• Descriptive observational data which requires no inference making on the part of the
researcher: the see something and write it down.
• Inferential data requires the researcher to make inferences about the underlying
emotion of what is observed. For instance, if the researcher observes a manager
consistently visiting the staff offices, five minutes before closing time for a day, the
researcher may conclude an instructive fault-finding style of management.
• Evaluate observational data requires the researcher to make an inference and a
judgment from the observed behavior.
The observation collection methods are illustrated in Mind map 5.2.
61
Mind map 5.2: Observation collection methods
• Continuous monitoring involves observing a subject and recording (either manually,
electronically, or both) as much of their behavior as possible. It is relatively easy but
a time consuming endeavour.
• Time allocation involves the researcher randomly selecting a place and time and
then recording what people are doing when they are first seen and before they see
the researcher. There are several sampling problems with this approach. Firstly, the
researcher needs a large representative sample for generalisation. Secondly, for
questions such as when, how often, and where the researcher needs to observe the
subject(s) which is often a concern.
• Narrative logbooks involves the researcher maintaining a descriptive and/or
narrative account of their observations. The diaries, however, must not only record
description and narrative accounts but interpretations and evaluations and develop a
framework of theory that will help in understanding the underlying dynamics of the
business phenomena.
• Coding schedules are used in structured observation to record the nature and
frequency of defined categories of behavior in the research context. The coding
scheduled is often for recording inter-personal interactions in social situations such
as meetings or negotiations.
Appropriate use of observational procedure
In evaluating the appropriate use of observational procedures in any study, the researcher
should examine the research in terms of the following criteria:
• Was a full range of behavioral variables identified to permit description?
• What were the inferences and evaluations of behaviors and inter-related patterns of
actions?
• Was the observer trained to identify the variables being observed?
62
• Was the observer trained in the maintenance of diaries, records, and coding
schedules?
• If there were more than one observer, what was the inter-observer reliability of the data,
that is, what was the level of agreement between the observations of independent
observers?
• What was the duration of observation as observations must aim at a representative
sample of the behavior of individuals being observed?
• Was the period too short to permit sufficient observation of the entire research
situation?
• How time consuming, obtrusive and directive were the role of the observer?
• Did the researcher describe the observational situation and present an estimate of
the possible effects of their presence as a participant-observer?
ETHNOGRAPHIC STUDIES
Ethnography involves a systematic, extended observation of social groups to gain inside
information of the phenomenon. Ethnographic studies are characterised by all or many of
the following features:
• They are broadly qualitative, phenomenologically orientated
• Participant-observation is often of a concealed, convert, unobtrusive variety
• The researcher’s adoption of the participants’ worldview and frame of reference
• Use by the researcher of the participants’ communication and the special meaning
and significance they attach to ordinary words and phrases
• The researcher’s effort to define and dramatise the group’s sense of its own identity
and uniqueness as a group
• Presentation of detailed accounts for specific situations from a narrative, descriptive
and inferential perspective
• A complex interweaving of the events and the wider social context within which they
are located.
Ethnographic investigations do not start with a well organised research plan. The researcher
is commonly open to observing, assessing and interpreting the much unforeseen conduct
and events. The board focal point of research interest that advances as the member -
perception process unfolds.
63
CASE STUDIES
The case study generally involves an in-depth study of a phenomenon with reference to a
particular “case” or “cases”. It is usually an exploration of a phenomenon or question of
interest where there is little knowledge in advance and where the situation may be complex
and has to draw on multiple sources of information, and tell a story, usually in a
chronological order (Yin 2009).
In case studies:
• The researcher can create a rich description of a social process
• The operation of an organisation.
This sets the stage for more specific questions that might be probed later using more
tightly structured methods.
Mind map 5.3 below illustrates the many aspects of the case study.
Use of case study methodology

Five distinct types of case studies:
i) Exploratory case studies are undertaken in few research studies or in new areas
with only a few existing theories or a deficient body of knowledge.
ii) Descriptive case studies limit themselves to a description of current operations in
an organisation or the research situation.
iii) Illustrative case studies attempt to illustrate new and possibly innovative practices
adopted by practical companies.
iv) Experimental case studies examine the processes and problems in implementing
new procedures and techniques in an organisation and evaluating the outcomes.
v) Explanatory case studies use existing theory to understand and explain events
and practices within the observational context.
Within this typology of case studies, there are two broad categories –
• The single case study design
• The multiple case study design.
The former is frequently used in quantitative studies. Multiple case study designs are
widely used in both qualitative and quantitative research and have the advantage that they
allow the researcher to compare and contrast aspects of the phenomenon of the research
interest in different contexts.
64
Mind map 5.3: Case study
65
Problems with case study methods
The case study, like all social research, should be clearly designed to facilitate the data
collection stage. From the start, the researcher should pay attention to the following:
• Evaluation questions
The researcher should have a clear sense of what to examine in the research process,
with the variables of interest clearly defined.
• Propositions
The researcher must have clear guide of the considerable number of things that should be
looked at within the scope of the examination. Expectations should address aspects of the
examination that are applicable to the current inquiry. Propositions should guide the
researcher on what to search for that is critical, and where that data can be found.
• Unit of analysis
This alludes to the dimension at which the contextual analysis is focused. The unit of
examination has to be controlled by the exploration question and accessibility of time and
different assets. The researcher may go past the unit of analysis to build up a progressively
detailed presentation of the case study.
Advantages of the case study design
In general, a number of benefits accrue from the use of case study design. Perhaps the
most compelling are the following:
• It can incorporate multiple methodological approaches in a single research.
• There can be triangulation of methodologies: different investigative methods can be
combined in the context of a clear research framework.
• Similarly, quantitative and qualitative approaches can be used either separately, or
in combination. The case study is a way of presenting data more than it is a data
gathering technique.
• Data gathering can take place in different ways in a unified case study format.
Gathering data for the case study

To increase the reliability and validity of the study, it is generally imperative to use multiple
sources of data.
66
Possible data gathering techniques are:
• Narrative/ log/ diary/ journal
• Documentary records
• Focus group meetings
• In-depth interviews
• Direct observation
• Participant observation.
Information should be stored in such manner that the raw information, field notes about
information and different reports of the researcher are stored and maintained in legitimate
databases. A chain of proof should be kept in which the researcher’s rationale and report
can inform the reader of steps taken from introductory suggestions to definite revealing of
information. Very important about data accumulation are the original study questions and
intentions.
Developing a case study protocol
In the design stage, the researcher should build up a far-reaching contextual analysis
convention. The protocol acts as a manual from the underlying phases of the examination
to its completion. The protocol as a rule incorporates the accompanying:
• Overview: Includes project objectives, case study issues, propositions and relevant
readings.
• Sources of information: Include locations for information and general procedures.
• Case study questions : The question for the case study
• Guide for the case report: Include an outline, narrative format and any bibliographic
or background literature.
The inquiries concerning which sort of information gathering technique is the best are
actually misleading. The main issue is to decide on the suitable data collection method/
strategy which should be based on the research goals. In addition, it is recommended that
researchers make use of different strategies to expand the reliability and legitimacy of their
discoveries through a methodology normally referred to as triangulation.
The essence of triangulation is that different strategies are utilised in a parallel sense, so
that they provide overlapping information, making it conceivable to check results from more
than one perspective.
Figure 5.4 below lists the aspect of the four types of triangulation.
67
Figure 5.4: Types of triangulation
The structured interview

• Interviewer asks questions and respondent answers most of the time.
• Only the participants reveal feelings and opinions.
• Interviewer is non-judgmental and does not try to change respondent’s opinions or
beliefs.
• Interviewer tries to obtain direct answers to specific questions.
• Interviewer seeks genuine answers, not ritual responses.
• Participants provide almost all the information. Interviewer does not correct a
respondent’s factual errors.
• Interviewer should control the topic, direction and pace. Interviewer must keep the
respondent’s attention on the task and ensure that irrelevant diversions are contained.
• Interviewer should attempt to maintain a consistently warm but serious and objective
tone throughout.
68
• Respondent should not shirk questions and should give truthful and considerate
answers.
Unstructured interviews
In unstructured interviews, the interviewer should keep to the previously formulated
questions contained in the interview schedule to prevent different interviewers from
collecting information that is not comparable.
• Unstructured interviews allow room for revealing feelings and beliefs of individuals
that a structured interview does not allow.
• The interviewer in unstructured meetings just proposes the general topic of discourse.
• Interviewer offers conversation starters to ensure a comfortable atmosphere for the
interview.
Face-to-face interviews
The face-to-face interview is a data collection method where the researcher communicates
directly with the participants in accordance with the research questionnaires. Face-to-face
interviews have the highest response rates and permit the longest questionnaires.
• The researcher/interviewer can make notes on the context (surroundings) of the
interview
• Use gestures
• Use other nonverbal communication methods and visual aids like pictures
• The researcher can ask complex questions and can make use of probing questions
if the initial question does not yield an answer.
However, the disadvantages of this type of interview are:
• The costs can be high.
• Interviewer bias often exists in face-to-face interviews.
• Researcher may influence the interviewee by means of appearance, tone of voice,
and wording of the questions.
Telephone interviews
The researcher/interviewer calls a subject telephonically, asks questions and records the
answers.
• The researcher can quickly reach many respondents, even those across long
distances.
• The response rates can also be high and you can use many interviewers.
69
• The researcher can control the sequence of questions and can also ask probing
questions.
The disadvantages are:
• They are very costly.
• Length of the interview is limited.
• Participants without telephones are excluded.
• The time of the call may be inconvenient for the interviewee.
• Open-ended questions are difficult to use.
• The researcher cannot assess the surroundings of the interviewee.
The role of the interviewer

• The interviewer’s role is difficult. As a specialist of the study, you need to get answers
to your questions and build rapport with the respondent, yet remaining neutral and
objective.
• You encroach on the respondent’s time and privacy and your research may not benefit
the respondent – so you need to be considerate and polite all the time.
• The respondent may be uncomfortable, afraid, embarrassed and suspicious of you
and the questions – again, you need to be considerate and polite all the time.
• You need to help the participant feel that they can give any truthful answer.
• You may not reveal your opinion, verbally or nonverbally.
• Treat the participant’s answers in a matter-of-fact manner and retain ethical standards.
• The respondent may deviate from the question and you need to re-direct the response
to the question.
• You need to define the situation, ensure that respondents have the information, and
understand it.
• Ensure motivation and cooperation so that the respondent seriously considers your
questions.
Mind map 5.4 below shows all the stages of an interview. This is followed by Mind map 5.5
showing the possibilities of interviewer bias.
70
Mind map 5.4: Stages of an interview
Mind map 5.5: Interviewer bias
71
Questionnaires
• Ensure the following:
• The questions are relevant to the study.
• The questions are carefully worded.
• The respondents understand the questions.
• The respondents are not influenced by the wording.
Mind map 5.6 below shows the various principles of good question writing, followed by a
short discussion of each principle.
Mind map 5.6: Principles of good question writing
• Avoid jargon, slang and abbreviations

The questions must be clear, relevant and significant to all respondents. Language and
specialised terms may bode well to specific subcultures only. For example, educationalists
use the terms didactics and pedagogics while legal advisors use phrasing like in camera
and subpoena. Shortened forms like USA and GPPW may mean nothing to many
respondents. The vocabulary and sentence structure for the overall population should be
easy to understand.
• Avoid ambiguity, confusion and vagueness
Ambiguity is one of the common problems in questionnaires. For example, an answer to the
question. Do you do your homework regularly? This question hinges on the understanding
of the word regularity. Respondents may respond differently to the question. To reduce
confusion and get information for the study, such types of questions should be closed
(provide options) with a question like how many hours per day do you spend on your
homework?
72
Do not make assumptions that your respondent will understand your question. For example,
the question, “What is your income?”, can have a variety of understandings – it could mean
gross or net, annual or monthly, only from salary or all sources of income, etc. The answers
would be inconsistent and the validity of the findings can be questioned. Make sure to
specify exactly what answer you expect, e.g. in the case of income you may want monthly
gross family income.
• Avoid prestige bias and emotional language
Prestige bias is an associated statement with a prestigious person or group and the
researcher must avoid it. Respondents may be influenced by their feelings towards the
person or group rather than the issue. For example, President Trump has branded media
news as fake news. Do you agree? The respondent may be influenced by people’s support
for President Trump. Respondents who do not understand the issue may answer or be
biased in their view of the President.
Use neutral language instead of emotionally burdened words because respondents may
respond to the emotional words instead of the issue.
• Avoid double-barrelled questions
Each question must address only one concept, meaning or issue. When two or more
question are joined together, the question becomes double-barrelled. Such questions are
ambiguous and confuse the respondents. The researcher will also struggle to be certain
of the respondent’s intention. An example of a double-barrelled question is does your
organisation address the problems associated with gender and equality in your
workstation? The participant may have different answers to the issues equality and gender
at their organisation.
• Avoid leading questions
A leading or loaded question leads the respondent to choose a particular response by its
wording, e.g. you do not agree with racism in the media, do you? Respondents are led to
state that they do not agree with racism in the media.
• Avoid asking questions that are beyond the respondent’s capabilities
A few difficult responses would include remembering past details, specific factual knowledge
and answers that expect mathematical skills. The researcher will get poor quality responses
if many of the respondents are unable to answer the question.
For instance, asking an adult: “How did you feel towards your grade 11teacher in high
school?” Questions like this may lead to a guess which is not reliable.
• Avoid false premises
The winter days is very long. Do you think schools should open around 9am in the morning,
or should the school close an hour earlier? The respondent may either accept or reject the
premise or not agree with either of the choices. Respondents who do not agree with the
73
premise may get frustrated and they will not know how to answer. The question should
rather assume a premise is true.
• Avoid asking about future intentions
Asking questions about what people may do when placed in hypothetical situations is not
reliable because it is not easy to predict behaviour. Questions on current issues,
experiences and recent behaviour are answered more reliably than questions about future
behaviour and abstractions.
• Avoid double negatives
Double negatives are grammatically incorrect and confusing. The double negative
generally arises when respondents are asked to agree or disagree with statements. For
example, when respondents disagree with the statement, “Students are not required to
attend conferences during working hours”, they can disagree with not doing something.
• Avoid overlapping
Often in numerical ranges one finds overlapping. A question on age with the numerical
ranges (20-30, 30-40, 40-50, 50+) is confusing and should be corrected to (20-29, 30-39,
40-49, 50+). Overlapping can also arise in verbal choices, for instance, “Are you satisfied
with the requirement for admission into the university or are there things that you feel
should be changed?”
Open and closed questions
Open questions:
Participants answer in their own words, no alternatives are given, thoughts and feelings
are revealed and the participants give reasons for their answers.
For instance, “Did exposure influence your stay in Astana? If yes, how?”.
One of the disadvantages of open questions is that they are difficult to interpret, tabulate
and summarise in research findings.
Closed questions
The most common closed question is the Yes/No option as it is easy to fill answer.
If alternatives are given, it confuses the participants.
74
Question format examples
Example of horizontal vertical response choices:
Do you think that there is evidence of female racism in sports?
The table below is an example of a matrix question format:
The doctors
Strongly Strongly
gave Agree Disagree Don’t know
agree disagree
prescriptions
Some examples of response choices:
• Excellent, good, fair, poor
• Strongly approve, approve, strongly disapprove, and disapprove
• Very interested, interested, not interested.
Scaled items or Likert scales:
The closed question describes various degrees of something. It enables people to get
accurate assessment of beliefs or opinions with Likert type questions.
Examples:
Female education is important
Strongly
Critical Very important Undecided Disagree
disagree
Guidelines for an effective questionnaire

• Participants should not be asked to identify themselves in questionnaires (they should
remain anonymous).
• Responses from participants should remain confidential in order to encourage frank
answers to sensitive questions in the study.
• Target only those respondents to whom your study is applicable.
• Neatness and conciseness are important in questionnaires to avoid confusion.
• The questionnaire must be attractive and easy for respondents to deal with.
• Time and simplicity are key issues.
• Plan carefully and only relevant questions must be included. Present an attractive
questionnaire to ensure that respondents accept it and that they will answer the
questions.
75
• The questionnaire should be comprehensive. It must gather as much information as
possible.
• Clear instructions. For instance, how the respondents should answer the questions
(ring, cross or tick the choice). The respondent should know that is expected of him/
her.
• Questions should move from the general to the specific. The first few questions can
win or lose their favour. Keep the delicate or sensitive questions for the end. The
questionnaire should be presented in a respondent-friendly way.
• Questions should be categorised if you have different variables (e.g. questions on
dress, identity, culture, language etc.). This will help to guide the respondent’s
thinking.
• Questions should also be sequenced logically.
• Responses should be easy to tabulate, summarise and interpret.
• Make provision for adequate code numbers if you intend using a computer program
to process your data.
• Enclose a post-paid envelope outlining the objectives of the study as well as a few
courteous words to encourage respondents.
• Give attention to the response rate. The response rate ultimately affects the
completeness of the sample. Each respondent who refuses to participate has an
impact on the representativeness of the eventual sample.
Factors affecting the validity of a questionnaire

The researchers needs to ask themselves the following:
• To what extent do the questions influence respondents to portray themselves in a
good light?
• To what extent does a question influence respondents to react in a way that they think
the researcher wants them to?
• To what extent does a question ask for information that could elicit resistance from
the person?
It is important for the researcher to avoid any of the above happening as this will have a
negative effect on the validity of the questionnaire.
76
CHAPTER SIX: DATA ANALYSIS
Outcomes
• Identify appropriate methods in planning the data analysis research
• Define the different types of data
• Identify the data analysis implications of each form of data
• Justify appropriate approaches in the analysis of quantitate and qualitative data
• Be aware of computer-assisted methods of data analysis.
INTRODUCTION
Research incorporates the formal and casual procedure of picking up, using and efficiently
applying information to the area of interest. The objective is to establish a connection
between what one knows and what one finds out about a research problem through an
audit of relevant literature and assembling essential information from people and the
different components of both quantitative and qualitative research strategies.
The process of information gathering and data analysis go hand-to-hand. If the exploration
has a positivistic inclination, then the data collection and the data analysis strategies will in
all likelihood be quantitative. If the investigation situates in a phenomenological worldview,
both the data collection and data analysis techniques will in general be qualitative.
THE QUANTITATIVE DATA ANALYSIS

Quantitative data alludes to all information that can be deduced in numerical qualities,
going from the numerical recurrence of event to complex introduction of information in
terms of diagrams and graphs (Creswell 2014). To convey meaning, the information or data
should be analysed and interpreted. To put it plainly, collecting and analysing information
with quantitative systems incorporates understanding the relationship among factors using
clear and inferential statistics.
This process will require the researcher to:
• Seek advice regarding statistics and statistical analyses should they not have
knowledge in the field.
• Utilise, if possible, computer-based analysis software and seek if necessary, the
assistance of experts in the field.
• Study the statistical concepts relevant to the needs of the study.
77
Hence, descriptive statistics enable a concise portrayal of the information regarding
measurements, for example rate, frequencies, means and standard deviations. Inferential
statistics/measurements go further. While descriptive statistics describe a sample’s
attributes based on the information gathered from respondents, inferential measurements
are utilised to obtain information about the population from which the sample was drawn
based on the data outlined in the descriptive measurements (Denzin & Lincoln, 2011)
Mind map 6.1 list the different types of quantitative data and their characteristics.
Mind map 6.1: Types of quantitative data

In analysing quantitative data, it is important to understand the inherent nature of the data
to collect, because this will determine the type of analysis that is appropriate and legitimate
in the context of the study and the data collection
Four categories of quantitative data:
Nominal measures are descriptive measures that serve only to indicate the alternative
states of the variable. For example, in measure of gender, a respondent may be male or
female or in measure of religion, a respondent may be Christian, Jewish, Hindu, Moslem,
78
Buddhist or belong to some other unspecified faith. The respondent is either male or
female, either a Christian or not a Christian.
Nominal measures in this manner have the particular qualities of thoroughness and shared
restrictiveness. They represent the most reduced conceivable dimension of measurement.
In endeavouring to evaluate such information, try to convert it and express the findings/
discoveries as frequencies or percentages. Although it is usual practice to appoint numerical
codes to these attributes to facilitate computer analysis, these numbers cannot be used for
mathematical purposes.
Ordinal measures are rank estimates, usually reflect choices made by the subject or
categories predetermined by the researcher. Ordinal measures can be logically rank-
ordered and the different attributes represent relatively more or less of the specific variable.
As with nominal data, there is little scope for treating such data mathematically.
Frequencies and percentages are calculated, but not the arithmetic mean and statistical
analysis which are largely precluded.
Interval measures refer to those variables of which the attributes are not only rank-ordered,
but they are separate by a uniform distance between them. An example would be the IQ
scale or temperature scales. Interval measures allow some degree of mathematical and
statistical treatment. Thus, the arithmetic mean IQ of a group of respondents with a range
of IQs can be calculated and correlated and regression analyses can be carried out.
Ratio measures are based on an absolute scale, which has a fixed zero point. This means
that the scale readings are exactly proportional to the variables being measured. Ratio
measures represent the highest possible level of precision and are amenable to all forms
of statistical analysis. Saunders et al. (2003:328) stated that quantitative data can also be
divided into two distinct categories:
• Categorical data cannot be measured numerically but can be classified into sets
(categories) according to specified criteria (e.g. gender, religion, profession,
qualification) or placed in rank order (e.g. level of experience, consumer preference,
etc.). Nominal and ordinal data fall into this group.
• Quantifiable data is data of which the values can be measured numerically. The more
precise the measurement the greater the range of statistical techniques that can be
used to analyse the data. Interval and ratio measures fall into this group. Generally it
is better in quantitatively-oriented studies to collect data that enables highest possible
level of statistical analysis.
Coding of data
All data should be recorded using numerical codes to categorise responses to each item
on the research instrument. Simultaneously, a codebook should be designed to maintain a
record of the codes for each variable. For instance, for the gender of respondents, the code
79
used may be 1=male and 2=female or for an item which uses a Likert scale, 1=strongly
agree, 2=agree, 3-uncertain, 4=disagree and 5=strongly disagree. All missing data should
be indicated through codes. For example, if a respondent did not indicate his/her sex, the
code 9 may be used. Items with missing data are then excluded from subsequent analysis
of data.
Statistical analysis
Once the data has been coded into a format that can be entered on a spreadsheet or a
statistical analysis package, the appropriate procedure may be used to process the data
into a format that can be analysed (frequencies, tables, diagrams, etc.).
The tables and diagrams most relevant in addressing the needs of the study will eventually
appear in the student’s/researcher’s dissertation. Tables and diagrams can be used in an
exploratory analysis of data to identify trends, show proportions and the distribution of
values and to visually compare the relationship among variables.
With descriptive statistics, the researcher can describe (and compare) variables numerically
with means and standard deviations, while with inferential statistics, the researcher can
reach conclusions about how the data collected relates to the original research objectives
and hypothesis and how these results might be generalised to the research population.
Guidelines for the successful application of statistics in the analysis of data

1. Statistics must be appropriate to integrate into the study and not use as a device to
create an impression of scientific analysis and objectivity.
2. The researcher must develop a good working knowledge of the principles underlying the
statistical procedures in the study to analyse data to enable appropriate use and meaningful
interpretation of the results.
3. The researcher who has access to statistical software packages such as SPSS for
Windows should first work through examples of coding and analysing research instruments
before proceeding with an analysis of the research data.
4. Before the researcher embarks on any kind of statistical analysis, they should determine
the characteristics of the data in terms of its type (i.e. nominal, ordinal, interval or ratio) and
its distribution (normal or skewed) since these inherent properties will determine what kind
of statistical test is possible to use.
80
The analysis of univariate data
Univariate data analysis involves the analysis of a single variable, usually with descriptive
statistics such as the calculation of:
• frequencies
• percentages
• means (the arithmetic ‘average’ of data)
• median and mode
• standard deviations.
The analysis of bivariate data

In most research, the investigation frequently requests the analysis of the connection
between two factors. One helpful way of doing this is to apply recurrence analysis and then
put data in a matrix or table. For instance, a specialist may wish to determine the
connection among gender and advancement to senior positions in the school management
in Astana. Prior examination demonstrated that there are respondents in this example with
no missing information for either factor. The table data on these two factors might be
introduced as follows:
Rank Male Female Row rates
Principals/ Deputies 10 6 16
HoD’s 50 40 90
Teaching staff 98 104 202
Column totals 158 150 308
In such tables, which present the data for two variables through a process referred to as
cross-tabulation, it is possible to examine if the variables are significantly associated. The
degree of fit can be statistically tested by using the Chi-squared (x2) test, a non-parametric
test that can be used with any data type. The degree of fit between two variables can also
be measured with correlation coefficients.
Another common procedure in the analysis of two variables is to test the significance of a
difference between the means of two groups for the same variable. A number of statistical
procedures can be used for this purpose: “students’” t-test, analysis of variance (ANOVA)
and the Mann Whitney U-test,
81
The researcher must become familiar with the appropriate statistical procedures so that
the data can be correctly analysed to address the needs of the topic.
ANALYSIS OF QUALITATIVE DATA

The analysis of subjective data gives the researcher an alternate arrangement of systems,
which mirror the philosophical presumptions that support the objective and approach of
qualitative research. The examination of subjective information is not the same as the
quantitative data. While the analysis of quantitative data depends on implications,
qualitative data focuses on implications communicated through words and analysis is
conducted using conceptualisation
Saunders, Lewis and Thornhill (2003) stated that the nature of qualitative data has
implications for both its collection and its analysis. According to Hussey and Hussey (1997),
there are three related elements in the analysis of qualitative data:
• Reducing the data to condense the material in some systematic way to make it more
manageable
• Structuring data in terms of themes, patterns and interrelationships
• Decontextualizing the data by converting extended text into more manageable forms
such as summaries, charts, diagrams and illustration.
Strategies for qualitative analysis

There are different approaches to the commencement of the process. If the researcher
commences from a deductive position, they will seek to use existing theory to shape the
process of analysis. In contrast, if the researcher adopts an inductive approach, they will
seek to develop a theory, which emerges from the analysis of the data.
Should the researcher adopt a deductive approach, they must first establish a theoretical
or descriptive framework that incorporates the main variables, components, themes and
issues in the study and the presumed relationship among them. This framework acts as
the means to guide the data analysis process.
The inductive strategy, in contrast, would require the researcher to collect the data and then
to explore it to see which themes or issues to follow up or concentrate on. Generally, this
is the more difficult approach requiring a high investment of time and material and human
sources. As Creswell (2012) pointed out, where the researcher adapts this approach, they
must be guided by this design from the data collection till the data analysis stage. The
researcher analyses data as they collect it and develops the conceptual framework to be
used during the data analysis stage.
82
Categorisation in qualitative research
Generally, a field of three approaches can result from this qualitative data analysis procedure.
The first is a ‘journalistic’ approach that is characterised by minimal researcher intervention
and the lowest level of patterning, abstraction and interpretation. The participants in the study
are allowed to speak for themselves as much as possible. The second is the ‘interpretive
descriptive’ approach where the researcher makes some effort at identification of patterns,
establishing interrelationships and general interpretation of patterns and interrelationships.
The third is the ‘grounded theory’ or ‘grounded hypothesis’ approach, which embodies the
highest level of abstraction and interpretation, where building a theory is the primary aim.
ANALYSING CASE STUDY DATA

In analysing case study data, two methods are most fruitful: patterns matching and time
series analysis, as listed in Figure 6.1 here.
Figure 6.1: Analysing case study data
83
Regardless of whether the systematic method is patterns matching or time-series analysis,
the closer the ‘fit’ between the expected and the observed information, the more one can
accept that the contextual analysis is yielding helpful outcomes. Disparities between the
hypothesis and the empirical data can lead to an amendment of the hypothesis, and after
that a perfect correlation can be ascertained. Whenever required, this procedure can be
repeated and the hypothesis refined after some time because of expanding alterations and
corrections that emanate the procedure. In this way, the researcher can consistently
reappraise the hypothesis to check whether it is helpful for translating ‘this present reality’
context of the study.
DATA PRESENTATION AND REPORT WRITING FOR CASE STUDIES

When presenting qualitative data, a number of formats can be used, including the following:
• Linear-analytic presentation
• Comparative structures
• Chronological structures
• Theory-building structures.
The linear-analytic presentation incorporates the examination questions and the
clarifications of techniques that will be used for the study – discoveries from the information
are clarified. This is a standard methodology, found in most journal articles and expositions
displaying contextual analysis findings. The chronological approach follows the case in a
time sequence from start to finish, enabling the researcher to reach conclusions effectively
about the causal connection between components of the investigation.
A dissertation on a case study methodology should include the following:
• Data collection that is thorough, generally using several data collection strategies
• Careful substantiation of any claims relating to relationships among variables, with
the alternate explanations carefully considered
• Comprehensive and engaging presentation of information with case details to support
key points.
84
CHAPTER SEVEN: THE RESEARCH REPORT
Outcomes
• Effectively plan the writing of a research report
• Apply the basic principles of structuring a research report.
INTRODUCTION
The research report is a brief description or a condensed form of the research work done
by the researcher. Several steps are involved to present the report in both the required
and ethical format. Normally, the purpose of a research report is for publication in journals,
articles or to present at conferences.
OBJECTIVES OF RESEARCH REPORT WRITING

These objectives are listed in Figure 7.1.
Figure 7.1: Objectives of writing a research report
85
Characteristics of the research report
• Accuracy
• Clarity
• Conciseness
• Honesty
• Completeness
Types of reports
Depending on the set-up and organisation, the research report varies greatly in size, length
and the problem the research wants to address. Generally, there are three types of
research report, namely the technical report, popular report and oral report. Kothari (2004:
351) stated that the method of presentation to be used depends on the particular scenario
and the nature of results.
Below are three types of reports adopted from Kothari’s (2004: 353) research methodology
strategies:
• Technical report – is used to give a full written report of the scientific study carried out
for record keeping. It mostly emphasises the method employed and the detailed
presentation of the findings which include the supporting data and study limitations.
• Popular report – emphasises attractiveness and simplicity of the information and
findings presented. It is clear, with few technical terms, details and liberal use of
charts and diagrams. Emphasis is on the practical aspects and policy implication of
the report.
• Oral report – is effective where policy recommendations are ascertained by the
project results. The oral report provides an open a platform for giving and taking
decisions that lead to the overall understanding of the findings and their implication
to the organisation.
Mind map 7.1 below lists some useful suggestions for a clear style in reports. This is
followed by the usual steps in writing the report.
86
Mind map 7.1: Tips for clear, readable style achievement
Steps in writing report

• Logical analysis – is the development of the subject through mental connection and
organisation between two things by means of analysis. Thus, it involves the
development from a simple to complex structure.
• Preparation of the final outline – a framework from which information is compiled from
the long list of points. It is an aid to the organisation of the work in logical manner.
• Preparation of rough draft – the researcher has to write down the procedure followed in
collecting the study materials, the limitations faced, what technique was adopted and
how it was applied to collect data, followed by the analysis thereof and the findings.
87
• Polishing and rewriting report – the careful revision of the work by looking or checking
the report for weaknesses in the logical development. The researcher should check
the language usage, grammar and spelling.
• Final draft – the researcher has to prepare the final report. It must be written in a
concise and clear manner by avoiding abstract terminologies and jargon. The report
must communicate to people and show originality.
• Bibliography – the researcher has to check for and append all the resources
consulted in writing the report. The bibliography should be arranged in alphabetical
order (Kothari 2004:347-348) based on the referencing methodology selected (e.g.
Harvard).
IMPORTANT RESEARCH TERMS

Theory
Theories use propositions (statements about concepts or variables) as building blocks and
intend to explain as opposed to rationalizes, criticise or ridicule the pattern of phenomena
of the real world. A theory is a set of related concepts that combine to explain some
phenomena or set of phenomena.
Variable
All propositions are changed to hypotheses for testing to occur; the researcher is likely
to deal with variables. In practice, the term variable is used as a synonym for the individual
components of the phenomena under study. The researcher’s interest lies in the
relationships among the variables.
Abstract
An abstract (or summary) is a page of the report. It is written after the paper has completed.
The reason is that it is a distillation of the important points covered in the body of the report.
It tells the reader what the research is about in one succinct paragraph.
References
References are an alphabetical listing of all sources of information from which the
researcher drew information during the research writing. The researcher must list only
those references that have been actually discussed or cited.
This is not a bibliography (that is, a comprehensive listing of everything on the subject) but
a compilation of the materials of authors in the research writing.
88
Appendices
The purpose of the appendix is to display the raw material and any calculations of the
study. Appendices also comprise any questionnaires or tests constructed which are placed
at the end of the report and not presented in the main body of the report.
Moderate variable
A moderate variable (MV) is an independent variable because the researcher may believe
that it may have a significant moderating effect on the relationship between the primary
independent variable links.
Hypothesis
A hypothesis is a tentative, testable statement about the relationship between two or more
variables.
89
BIBLIOGRAPHY AND FURTHER READINGS
Cooper, D.R. and Schindler, P.S. (2003) Business Research Methods. 8th Edition, McGraw-
Hill Irwin, Boston
Creswell, J. W. (2012). Educational research: Planning, conducting, and evaluating
quantitative and qualitative research (Laureate custom ed.). Boston, MA: Pearson
Education.
Creswell, J.W. 2014. Research Design. Qualitative, Quantitative, and Mixed Methods
Approaches. Los Angeles: SAGE Publications, Inc.
Denzin, N. K., & Lincoln, Y. S. (2011). The SAGE handbook of qualitative research (4th ed.).
Thousand Oaks, CA: Sage.
Hussey, J. and Hussey, R. 1997. Business Research: a practical guide for undergraduate
and postgraduate students. London: MacMillan
Kothari, C, R., 2004. Research methodology. Second Edition. New Delhi, New Age
International Publisher, India.
Saunders, M., Lewis, P. and Thornhill, A. (2003) Research Methods for Business Students.
Harlow: Pearson Education Limited
Saunders, M., Lewis, P., and Thornhill, A. 2000. Research methods for Business students.
Second Edition. London: Prentice Hall.
Singleton, R. A. 1993. Approach to Social Research. New York: Oxford University Press.
Yin, R. K. (2009). Case study research: Design and methods (4th ed.). California: Sage.
Bloomsburg University guide on literature (2018), http://guides.library.bloomu.edu/english
90
View publication stats

A Guide To Research Writing: David Annan

Uploaded by

Copyright:

Available Formats

A Guide To Research Writing: David Annan

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

A Guide To Research Writing: David Annan

Uploaded by

Copyright:

Available Formats

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

A GUIDE TO RESEARCH WRITING

Book · May 2019

Exploring outlook of South Sudan development after independence View project

Small business/ entrepreneurial Management View project

The user has requested enhancement of the downloaded file.

Printing company «FLASH PRINT»

CHAPTER ONE: INTRODUCTION TO RESEARCH ................................................. 9

Figure 1.2: Features of scientific research

Mind map 1.1: Research proposal content

STEPS TO DETERMINE THE RESEARCH METHOD

Mind map 1.3: Steps in research method

Step 1. Identify the research problem

Table 1.1 Concepts of induction and deduction

Step 4. Examine the data collected for the underlying patterns

Figure 1.5: Research paradigms

METHODOLOGY AND METHODS

Mind map 1.4: Research paradigm differences in research methodology

THE PURPOSE OF THE LITERATURE REVIEW

Mind map 2.1: The purpose of the literature review

Mind map 2.2: Functions of the literature review

Provide a context for the study

Create a conceptual frame of reference

Report the status of current research

Demonstrate theoretical and conceptual gaps in the field

Figure 2.1: Types of literature sources

Mind map 2.3: Identifying the scope of the literature review

Mind map 2.4: Criteria for evaluating a literature review

Mind map 2.5: Steps in writing literature review

Mind map 3.1: Research process

Develop an appropriate research design

Phenomenological (qualitative) research

Mixed research approach

RESEARCH PROCESS WITHIN A MIXED METHOD FRAMEWORK

Positivist research strategies/experimental design

Phenomenological research strategies

Figure 3.3: Case study data collection methods

Mixed research strategies

THE WHYS OF A SAMPLE POPULATION

Mind map 4.1: Reasons for sampling

The sampling cycle

Mind map 4.3: Types of sampling design

• The interval is calculated=

Mind map 4.4: Various types of sampling

Figure 4.1: Merits and demerits of sampling

IMPLEMENTING THE PLAN

Interaction with participants in the study

DATA COLLECTION METHODS

Mind map 5.1: Designing questionnaires

Reliability of a research instrument refers to the consistency or repeatability of the

Figure 5.2: Types of reliability

Figure 5.3: Types of interview

Use of case study methodology

Gathering data for the case study

The structured interview

The role of the interviewer

Mind map 5.5: Interviewer bias

Mind map 5.6: Principles of good question writing

• Avoid jargon, slang and abbreviations