Chapter - 4 - Research Design

lOMoARcPSD|2932478
Chapter 5 Formulating the Research Design-SV
Quantitative Business Analysis (ESLSCA Business School Paris (Egypt))
StuDocu is not sponsored or endorsed by any college or university

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)
lOMoARcPSD|2932478
Formulating the Research

Design
Chapter 5

lOMoARcPSD|2932478
Learning Outcomes
By the end of this chapter you should:
 understand the importance of having thought carefully about your
research design;
 identify the main research strategies and explain why these should not
be thought of as mutually exclusive;
 explain the differences between quantitative and qualitative data
collection techniques and analysis procedures;
 explain the reasons for adopting multiple methods in research;
 consider the implications of adopting different time horizons for your
research design;
 explain the concepts of validity and reliability and identify the main
threats to validity and reliability;
 understand some of the main ethical issues implied by the choice of
research strategy. Downloaded by Giang Nguyen (leokoo.giang@gmail.com)
lOMoARcPSD|2932478
Chapter 5 Tree
5.1 Introduction
5.2 Purpose of Research

Research Design
5.3 Research Strategy
5.4 Multiple Methods Choices
5.5 Time Horizons
5.6 Credibility of Research Findings
5.7 Ethics of Research Design

lOMoARcPSD|2932478
4.1 The Research Onion

Mark Saunders, Philip Lewis and Adrian Thornhill 2008

lOMoARcPSD|2932478
5.2 Purpose of the Research
Exploratory
Descriptive
Explanatory

lOMoARcPSD|2932478
(Robson 2002:59)
Exploratory Study
 Finding out ‘what is happening; to seek new
insights; to ask questions and to assess
phenomena in a new light’
 Useful if you wish to clarify your understanding
of a problem, such as if you are unsure of the
precise nature of the problem
 You must be willing to change your direction as
a result of new data that appear and new
insights

lOMoARcPSD|2932478
Exploratory Study
Three principal ways of conducting exploratory
research:
Interviewing Conducting
A search of the
‘experts’ in the focus group
literature
subject interviews

lOMoARcPSD|2932478
Exploratory Study (Example)

Exploring how the employee–organisation relationship affects the linkage
between perception of developmental HRM practices and employee
outcomes
Contemporary research on ‘best practice’, high performance, high-
commitment, high involvement, progressive, and human-capital-enhancing
human resource management (HRM) suggests that such practices (e.g.
training opportunities, career development) lead to organisations offering
resources and opportunities that improve the motivation, skills, attitudes and
behaviours of their employees. Most of these models suggest that human
resource (HR) practices or systems deliver performance through the effect they
have on employees, but some studies conclude that the positive implications
for employees are at best uncertain. For example, one influential review
(Wright and Boswell 2002) argues that the dearth of research aimed at
understanding how multiple (or systems of) HR practices impact individuals
certainly suggests an opportunity for future research.
lOMoARcPSD|2932478
(Robson 2002:59).
Descriptive Study
 ‘to portray an accurate profile of persons, events or
situations’
 It is necessary to have a clear picture of the
phenomena on which you wish to collect data prior
to the collection of the data.
 Description in management and business research
has a very clear place. However, it should be thought
of as a means to an end rather than an end in itself.
 If your research project utilises description it is likely to be a
precursor to explanation. Such studies are known as descripto-
explanatory studies.
lOMoARcPSD|2932478
Explanatory Study
 Studies that establish causal relationships between
variables.
 The emphasis here is on studying a situation or a
problem in order to explain the relationships between
variables.
 You might collect qualitative data to explain the reasons why
customers of your company rarely pay their bills according to the
prescribed payment terms.

lOMoARcPSD|2932478
Explanatory Study (Example)

Ian wanted to study the relationship between the written accounts of
environmental policies which organisations present in their annual report
and the actual practices of organisations. He wanted to establish the
closeness of the match between the public face of organisations and
practical reality. In particular, he wanted to know the extent to whether it
was the public statements which were the key influence upon practice or
whether written accounts were based on careful research about what went
on in the organisation. This research adopted a case study strategy. Ian
examined three organisations in some detail. The data collected were
mainly qualitative, although some secondary quantitative data were used.
What emerged was that the written accounts of environmental policies had
little effect on what happened on the ground. Actual practice was a
function largely of pressure from external sources (e.g. legislation) and a
combination of internal and external sources (e.g. ‘good’ practice).
lOMoARcPSD|2932478
5.3 The Need for a Clear Research Strategy

 Each strategy can be used for exploratory, descriptive and
explanatory research (Yin 2003).
 Some of these strategies clearly belong to the deductive
approach, others to the inductive approach.
 Your choice of research strategy will be guided by your
research question(s) and objectives, the extent of existing
knowledge, the amount of time and other resources you
have available, as well as your own philosophical
underpinnings.
 Research strategies are not mutually exclusive.
 You may use the survey strategy as part of a case study.
lOMoARcPSD|2932478
5.3 Different Research Strategies

Experiment
Survey
Research Strategy
Case Study
Action Research
Grounded Theory
Ethnography
Archival Research
lOMoARcPSD|2932478
Research Strategies: Experiment

 Used to study causal links; whether a change in one
independent variable produces a change in another
dependent variable (Hakim 2000).
 The simplest experiments are concerned with whether there is a
link between two variables.
 More complex experiments also consider the size of the change
and the relative importance of two or more independent
variables.
 Used in exploratory and explanatory research to
answer ‘how’ and ‘why’ questions.
lOMoARcPSD|2932478

 The purpose is to study causal links; whether a
change in one independent variable produces a
change in another dependent variable (Hakim 2000).
 The simplest experiments are concerned with whether there is a
link between two variables.
 More complex experiments also consider the size of the change and
the relative importance of two or more independent variables.
 Experiments therefore tend to be used in exploratory
and explanatory research to answer ‘how’ and ‘why’
questions.
 In a classic experiment (Figure 5.2), two groups are
lOMoARcPSD|2932478

 Two groups are established and members assigned at random
to each. This means the two groups will be exactly similar in
all aspects relevant to the research other than whether or not
they are exposed to the planned intervention (manipulation).
 The experimental group: some form of planned
manipulation, such as a ‘buy two, get one free’ promotion, is
made subsequently.
 The control group, no such intervention is made.
 The dependent variable (purchasing behaviour), is measured
before and after the manipulation of the independent
variable (the use of the ‘buy two, get one free’ promotion) for
both the experimental group and the control group.
lOMoARcPSD|2932478
Figure 5.2 – A Classical Experiment Strategy

Control Group Experimental Group
Time (t)
Group members assigned at random
Dependent Variable Measured t0
Intervention of Dependent Variable
t+1
Dependent Variable Measured
lOMoARcPSD|2932478
Internal Validity (because you

High have full control over your
variables)
Low
External Validity

lOMoARcPSD|2932478
Research Strategies: Survey

 Associated with the deductive approach, and used
for exploratory and descriptive research.
 Used to answer who, what, where, how much and
how many questions.
 Allow the collection of a large amount of data from
a sizeable population in a highly economical way,
obtained by using a questionnaire, and data are
standardised, allowing easy comparison.
 Provide more control over the research process and
it is possible to generate findings that are
representative of the whole population.
lOMoARcPSD|2932478
Research Strategies: Survey

The questionnaire, however, is
not the only data collection
technique that belongs to the
survey strategy. There are also:
 Structured Observation, used in
behavioural research
 Structured Interviews, where
standardised questions are asked
of all interviewees

lOMoARcPSD|2932478
Research Strategies: Case Study

 Robson (2002:178) defines case study as ‘a strategy
for doing research which involves an empirical
investigation of a particular contemporary
phenomenon within its real life context using
multiple sources of evidence’.
 This is the complete opposite of the experimental strategy,
where the research is undertaken within a highly controlled
context.
 It also differs from the survey strategy, where the ability to
explore and understand this context is limited by the number of
variables for which data can be collected.
lOMoARcPSD|2932478

 Used if you wish to gain a rich understanding of the
context of the research and the processes being
enacted (Morris and Wood 1991).
 Has considerable ability to generate answers to the
question ‘why?’, ‘what?’ and ‘how?’ questions,
although ‘what?’ and ‘how?’ questions tend to be
more the concern of the survey strategy.
 For this reason the case study strategy is most often
used in explanatory and exploratory research.

lOMoARcPSD|2932478

(Method Triangulation)
Using different data collection
techniques within one study in
order to ensure that the data
are telling you what you think Question
they are telling you. naires
Qualitative data collected using
semi-structured group interviews Observati
on
may be a valuable way of
triangulating quantitative data Docume
collected by a questionnaire. Interview
s
ntary
Analysis
lOMoARcPSD|2932478
Research Strategies: Action Research

Research in action
Purpose of the
rather than research
Research
about action
Involvement of Collaboration between

Four Practitioners in the practitioners and
Common research researchers
Themes of
Action Diagnosing, Planning,
The iterative nature of
Research Taking Action and
the process
Evaluating
Should have
The results could
implications beyond
inform other contexts
the immediate project

lOMoARcPSD|2932478
Fig. 5.3 The Action Research Spiral

lOMoARcPSD|2932478
(Glaser and Strauss 1967)
Research Strategies: Grounded Theory

 ‘Theory Building’ through a combination of
induction and deduction.
 Helpful to predict and explain behaviour, the
emphasis being upon developing and building theory.
 Data collection starts without the formation of an
initial theoretical framework. Theory is developed
from data generated by a series of observations. These
data lead to the generation of predictions which are
then tested in further observations that may confirm,
or otherwise, the predictions.
lOMoARcPSD|2932478
Research Strategies: Ethnography

 Rooted firmly in the inductive approach. It emanates
from the field of anthropology.
 The purpose is to describe and explain the social
world of the research subjects.
 Very time consuming and takes place over an
extended time period as the researcher needs to
immerse in the social world being researched.
 The research process needs to be flexible and
responsive to change since the researcher will
constantly be developing new patterns of thought
about what is being observed.
lOMoARcPSD|2932478
Research Strategies: Ethnography

 May be very appropriate if you wish to gain insights
about a particular context and better understand and
interpret it from the perspective(s) of those involved.
 Prior to commencing research using this strategy, you
will need to find a setting that will enable you to
answer your research question and meet your research
objectives and then negotiate full access.
 Subsequently you will need to build a high degree of
trust with your research participants and, finally,
develop strategies to cope with being a full-time
member of the social context and a researcher.
lOMoARcPSD|2932478
Research Strategies: Archival Research

 Makes use of administrative records and documents
as the principal source of data.
 Archival research strategy should not be confused
with secondary data analysis.
 All research that makes use of data contained in administrative
records is inevitably secondary data analysis. This is because these
data were originally collected for a different purpose, the
administration of the organisation.
(Hakim 2000
 When these data are used in an archival research strategy they are
analysed because they are a product of day-to-day activities. They
are, therefore, part of the reality being studied rather than having
been collected originally as data for research purposes.
lOMoARcPSD|2932478
Research Strategies: Archival Research

 An archival research strategy allows research
questions which focus upon the past and changes
over time to be answered, be they exploratory,
descriptive or explanatory.
 However, your ability to answer such questions will
inevitably be constrained by the nature of the
administrative records and documents. Even where
these records exist, they may not contain the precise
information needed to answer your research
question(s) or meet your objectives.
lOMoARcPSD|2932478

Research Choices
Mono Multiple
Methods Methods
Mixes
Multi-Method
Methods
Mixed-Method
Quantitative
Research
Mixed-Model
Qualitative
Research
lOMoARcPSD|2932478

Multi-Method Qualitative Study
Darren wanted to establish how new supervisors learned to do
the job. This involved him in:
 Shadowing a new supervisor for a week (qualitative data);
 Interviewing a day and a night shift supervisor to establish any
differences in approach (qualitative data);
 Interviewing the managers to whom these two supervisors reported
(qualitative data).
He was then able to draw on the valuable data he had collected
to complete his main research task: interviewing new supervisors
to discover how they learned to do the job. This provided
further qualitative data.
lOMoARcPSD|2932478

Mixed-Method Research
Phil conducted an employee attitude survey in a small insurance
company, using mixed method research. Two of his choices were
qualitative and one was quantitative. The research consisted of
four stages:
1. In-depth interviews with senior managers
2. Discussion groups with six to 10 employees representing
different grades and occupations in the company
3. A questionnaire that was administered to 100 of the 200
head-office employees.
4. Semi-structured group interviews with further representative
employee groups Downloaded by Giang Nguyen (leokoo.giang@gmail.com)
lOMoARcPSD|2932478

Mixed-Method Research
In-depth Interviews: to get a picture of the important issues
(contextual data).
Discussion Groups: to establish the types of issues that were
important to staff (the content of the questionnaire).
A Questionnaire: This provided quantitative data which when
analysed statistically allowed the attitudes of different employee
groups to be compared for differences by age, gender, length of
service, occupation and grade groupings. This was particularly
important to the company.
Semi-structured Group Interviews: analysed qualitatively to
clarify the content of some of the questionnaire results an get at
lOMoARcPSD|2932478
5.5 Time Horizons

The study of a particular The study of a particular
phenomenon at a particular time, phenomenon over a period
data is collected at one shot of time, data is collected at
multiple stages

lOMoARcPSD|2932478
5.6 Credibility of Research Findings

Reliability Validity Generalizability
Concerned with
The extent to whether the
which your data Whether your
findings are really
collection findings may be
about what they
equally applicable
techniques or appear to be
to other research
analysis about. Is the
settings, such as
procedures will relationship
other
yield consistent between two
organisations
variables a causal
findings relationship?
lOMoARcPSD|2932478
Credibility of Research Findings:

Logic Leaps and False Assumptions
Identification of the Research Population
•If the intention is to be able to generalise the

conclusions across the whole population, is the
choice of population logical?
•If your research project is in the National Health
Service, for example, it would be fanciful to assume
that the findings were valid for software houses or
advertising agencies.
lOMoARcPSD|2932478

Data Collection
•Is it logical to assume that the way you are

collecting your data is going to yield valid data?
•If you interview top bosses you are likely to
encounter the ‘good news’ syndrome.
•If you collect press cuttings from newspapers, how
can you assume there has been no political bias put
on them?
lOMoARcPSD|2932478

Data Interpretation
•You must choose an appropriate theoretical

framework. It is essential that you ask yourself
‘Why am I using this theory and not another which
may be equally, or more, appropriate?’
•Making viable recommendations are the result of
clear conclusions based on a set of findings.
lOMoARcPSD|2932478

Development of Conclusions
•‘Do my conclusions (or does my theory) stand up
to the closest scrutiny?’
•If the declared theory in the police appraisal study
is that the introduction of pay to appraisal will lead
to the appraisal process being useful for pay
purposes only, does this apply to all police
appraisals? Will it be true for younger as well as
older police and for all grades and locations?
•In other words, are you asking your readers to make
logic leaps? Downloaded by Giang Nguyen (leokoo.giang@gmail.com)
lOMoARcPSD|2932478
5.7 Ethics of Research Design

 It is a matter of judgement as to whether the strategy and
data collection method(s) suggested by ethical considerations
will yield valid data.
 Not to embarrass, harm, or disadvantage your subjects.
 Your research design may need to consider the extent to
which you should collect data from a research population
that is unaware of the fact they are the subject of research
and so have not consented.
 If the topic you were researching was one where it might be
beneficial for your research that the fact that you were
collecting data on individuals was not disclosed, then this
would pose a similar ethical dilemma.

Chapter - 4 - Research Design

Uploaded by

Copyright:

Available Formats

Chapter - 4 - Research Design

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

Chapter - 4 - Research Design

Uploaded by

Copyright:

Available Formats

lOMoARcPSD|2932478

Chapter 5 Formulating the Research Design-SV

Quantitative Business Analysis (ESLSCA Business School Paris (Egypt))

StuDocu is not sponsored or endorsed by any college or university

Formulating the Research

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

5.2 Purpose of Research

5.3 Research Strategy

5.4 Multiple Methods Choices

5.5 Time Horizons

5.6 Credibility of Research Findings

5.7 Ethics of Research Design

4.1 The Research Onion

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

5.2 Purpose of the Research

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Exploratory Study (Example)

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Explanatory Study (Example)

5.3 The Need for a Clear Research Strategy

5.3 Different Research Strategies

Research Strategies: Experiment

Research Strategies: Experiment

Research Strategies: Experiment

Figure 5.2 – A Classical Experiment Strategy

Group members assigned at random

Dependent Variable Measured t0

Intervention of Dependent Variable

Research Strategies: Experiment

Internal Validity (because you

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Research Strategies: Survey

Research Strategies: Survey

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Research Strategies: Case Study

Research Strategies: Case Study

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Research Strategies: Case Study

Research Strategies: Action Research

Involvement of Collaboration between

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

Fig. 5.3 The Action Research Spiral

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

(Glaser and Strauss 1967)

Research Strategies: Grounded Theory

Research Strategies: Ethnography

Research Strategies: Ethnography

Research Strategies: Archival Research

Research Strategies: Archival Research

5.4 Multiple Methods Choices

5.4 Multiple Methods Choices

5.4 Multiple Methods Choices

5.4 Multiple Methods Choices

5.5 Time Horizons

Downloaded by Giang Nguyen (leokoo.giang@gmail.com)

5.6 Credibility of Research Findings

Credibility of Research Findings: