Slide 5.

Chapter 5
Formulating the research design

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.2

Research Design
The research design needs

• Clear objectives derived from the research question

• To specify sources of data collection

• To consider constraints and ethical issues

• Valid reasons for your choice of design

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.3

The Process of Research Design

❑ Your research design is the general plan of how you will go about answering
your research question(s) (the importance of clearly defining the research
question cannot be overemphasised).
❑ It will contain clear objectives derived from your research question(s),
specify the source or sources from which you intend to collect data, how you
propose to collect and analyse these, and discuss ethical issues and the
constraints you will inevitably encounter (e.g. access to data, time, location
and money).
❑ Crucially, it should demonstrate that you have thought through the elements
of your particular research design.

• Research choices
• Research strategies
• Time horizons

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.4

Research Design and Tactics

The research onion

Saunders et al, (2009)

Figure 5.1 The research ‘onion’
Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.5

Research Choices

• One way of differentiating quantitative research from qualitative research is to

distinguish between numeric data (numbers) and non-numeric data (words,
images, audio recordings, video clips and other similar material).
• In this way, ‘quantitative’ is often used as a synonym for any data collection
technique (such as a questionnaire) or data analysis procedure (such as graphs or
statistics) that generates or uses numerical data.
• In contrast, ‘qualitative’ is often used as a synonym for any data collection
technique (such as an interview) or data analysis procedure (such as categorising
data) that generates or uses non-numerical data.
• This is an important way to differentiate this methodological choice; however,
this distinction is both problematic and narrow.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.6

Research Choices

Quantitative research designs

• Quantitative research examines relationships between variables, which are measured
numerically and analysed using a range of statistical and graphical techniques.
• A quantitative research design may use a single data collection technique, such as a
questionnaire, and corresponding quantitative analytical procedure. This is known as a mono
method quantitative study (Figure 5.2). A quantitative research design may also use more than
one quantitative data collection technique and corresponding analytical procedure. This is
known as a multi-method quantitative study (Figure 5.2). You might, for example, decide to
collect quantitative data using both questionnaires and structured observation, analysing these
data statistically.
Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.7

Research Choices

Qualitative research designs

• Qualitative research studies participants’ meanings and the relationships between them, using a
variety of data collection techniques and analytical procedures, to develop a conceptual framework
and theoretical contribution.
• In qualitative research, meanings are derived from words and images, not numbers. Since words
and images may have multiple meanings as well as unclear meanings, it is often necessary to
explore and clarify these with participants.
• A qualitative research design may use a single data collection technique, such as semi-structured
interviews, and corresponding qualitative analytical procedure. This is known as a mono method
qualitative study. A qualitative research design may also use more than one qualitative data
collection technique and corresponding analytical procedure. This is known as a multi-method
qualitative study.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.8

Classification of the research

purpose-Recognising the purpose of
your research design

• Exploratory research
• Descriptive studies
• Explanatory studies
• Evaluative studies
• Combined studies

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.9

Exploratory research
• An exploratory study is a valuable means to ask open questions to discover what is happening and
gain insights about a topic of interest.
• Research questions that are exploratory are likely to begin with ‘What’ or ‘How’. Questions that
you ask during data collection to explore an issue, will also be likely to start with ‘What’ or ‘How’.
• An exploratory study is particularly useful if you wish to clarify your understanding of an issue,
problem or phenomenon, such as if you are unsure of its precise nature. It may be that time is well
spent on exploratory research, as it might show that the research is not worth pursuing!
• There are a number of ways to conduct exploratory research.
• These include a search of the literature; interviewing ‘experts’ in the subject; conducting in-depth
individual interviews or conducting focus group interviews.
• Because of their exploratory nature, these interviews are likely to be relatively unstructured and to
rely on the quality of the contributions from those who participate to help guide the subsequent
stage of your research.
• Exploratory research has the advantage that it is flexible and adaptable to change. If you are
conducting exploratory research, you must be willing to change your direction as a result of new
data that appear and new insights that occur to you.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.10

Descriptive research
• The purpose of descriptive research is to gain an accurate profile of events, persons or situations.
• Research questions that are descriptive are likely to begin with, or include, either ‘Who’, ‘What’,
‘Where’, ‘When’ or ‘How’.
• Questions that you ask during data collection to gain a description of events, persons or situations
will also be likely to start with, or include, ‘Who’, ‘What’, ‘Where’, ‘When’ or ‘How’ .
• Descriptive research may be an extension of a piece of exploratory research or a forerunner to a
piece of explanatory research.
• It is necessary to have a clear picture of the phenomenon on which you wish to collect data prior to
the collection of the data.
• One of the earliest well-known examples of a descriptive survey is the Domesday Book, which
described the population of England in 1085. Often project tutors are rather wary of work that is
too descriptive. There is a danger of their saying ‘That’s very interesting . . . but so what?’ They
will want you to go further and draw conclusions from the data you are describing. They will
encourage you to develop the skills of evaluating data and synthesising ideas. These are
higher-order skills than those of accurate description.
• Description in business and management research has a very clear place. However, it should be
thought of as a means to an end rather than an end in itself. This means that if your research
project utilises description it is likely to be a precursor to explanation. Such studies are known as
descripto-explanatory studies.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.11

Explanatory studies
• Studies that establish causal relationships between variables may be termed explanatory research.
• Research questions that seek explanatory answers are likely to begin with, or include, ‘Why’ or
‘How’.
• Questions that you ask during data collection to gain an explanatory response will also be likely to
start with, or include, ‘Why’ or ‘How’ .
• The emphasis in explanatory research is to study a situation or a problem in order to explain the
relationships between variables.
• You may find, for example, that a cursory analysis of quantitative data on manufacturing scrap
rates shows a relationship between scrap rates and the age of the machine being operated. You
could analyse these data using a statistical test such as correlation in order to get a clearer view of
the relationship.
• Alternatively, you might collect qualitative data to explain the reasons why customers of your
company rarely pay their bills according to the prescribed payment terms.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.12

Evaluative studies
• The purpose of evaluative research is to find out how well something works.
• Research questions that seek to evaluate answers are likely to begin with ‘How’, or include
‘What’, in the form of ‘To what extent’.
• Evaluative research in business and management is likely to be concerned with assessing the
effectiveness of an organisational or business strategy, policy, programme, initiative or process.
This may relate to any area of the organisation or business: for example, evaluating a marketing
campaign, a personnel policy, a costing strategy, the delivery of a support service.
• Questions that you ask during data collection to seek an evaluative understanding will be likely to
start with, or include, ‘What’, ‘How’ or ‘Why’.
• As part of your evaluative study you may also make comparisons between events, situations,
groups, places or periods, so that you ask questions that include ‘Which’, ‘When’, ‘Who’ or
‘Where’. Asking such questions would help you to compare the effectiveness of, say, an
advertising campaign in different locations or between different groups of consumers.
• In this way, evaluative research allows you to assess performance and to compare this.
• An evaluative study may produce a theoretical contribution where emphasis is placed on
understanding not only ‘how effective’ something is, but also ‘why’, and then comparing this
explanation to existing theory.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.13

Choosing a research strategy or

strategies –
Different Research Strategies

• Experiment
• Survey
• Archival and documentary research
• Case study
• Ethnography
• Action Research
• Grounded Theory
• Narrative Inquiry.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.14

Experiment
• We start with discussion of the experiment strategy because its roots in natural science,
laboratory-based research and the precision required to conduct it mean that the ‘experiment’ is
often seen as the ‘gold standard’ against which the rigour of other strategies is assessed.
• Experiment is a form of research that owes much to the natural sciences, although it features
strongly in psychological and social science research.
• The purpose of an experiment is to study the probability of a change in an independent variable
causing a change in another, dependent variable. Table 5.4 provides a description of types of
variable.
• An experiment uses hypothetical explanations, known as hypotheses, rather than research
questions. This is because the researcher hypothesises whether or not a relationship will exist
between the variables. Two types of (opposing) hypotheses are formulated in a standard
experiment: the null hypothesis and the hypothesis (also referred to as the alternative
hypothesis).
• The null hypothesis is the explanation that there is no difference or relationship between the
variables.
An example of a null hypothesis is: User satisfaction of online customer support is not related to
the amount of training support staff have received.
• The hypothesis is the explanation that there is a difference or relationship between the variables.
An example of a (directional) hypothesis is: User satisfaction of online customer support is related
to the amount of training support staff have received.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.15

Experiment
• In an experiment, the compatibility of the data with the null hypothesis is tested statistically.
• The statistical test is based on the probability of these data or data more extreme occurring by
chance (Wassenstein and Lazer, 2016) and in effect measures the probability that the data are
compatible with the null hypothesis.
• The smaller the probability (termed the p-value), the greater the statistical incompatibility of the
data with the null hypothesis. This ‘incompatibility’ is interpreted as casting doubt on or
providing evidence against the null hypothesis and its associated underlying assumptions.
• Where this probability is greater than a prescribed value (usually p = 0.05), the null hypothesis
is usually accepted and the hypothesis is rejected.
• Where the probability is less than or equal to the prescribed value (usually p = 0.05), this
indicates that the hypothesis can be accepted.
• 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
‘what’, ‘how’ and ‘why’ questions.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.16

Survey
• The survey strategy is usually associated with a deductive research approach.
• It is a popular strategy in business and management research and is most frequently used to
answer ‘what’, ‘who’, ‘where’, ‘how much’ and ‘how many’ questions.
• It therefore tends to be used for exploratory and descriptive research.
• Survey strategies using questionnaires are popular as they allow the collection of standardised
data from a large number of respondents economically, allowing easy comparison.
• In addition, the survey strategy is perceived as authoritative by people in general and is
comparatively easy both to explain and to understand.
• Every day a news bulletin, news website or newspaper reports the results of a new survey that is
designed to find out how a group of people thinks or behaves in relation to a particular issue.
• The survey strategy allows you to collect data which you can analyse quantitatively using
descriptive and inferential statistics.
• Using a survey strategy should give you more control over the research process and, when
probability sampling is used, it is possible to generate findings that are statistically
representative of the whole population at a lower cost than collecting the data for the whole
population.
• Structured observation, of the type most frequently associated with organisation and methods
(O&M) research, and structured interviews, where standardised questions are asked of all
interviewees, also often fall into this strategy.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.17

Survey: key features

• Popular in business research

• Perceived as authoritative
• Allows collection of quantitative data
• Data can be analysed quantitatively
• Samples need to be representative
• Gives the researcher independence
• Structured observation and interviews can be used

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.18

Archival and documentary research

• The digitalisation of data and the creation of online archives, along with open
data initiatives by governments and businesses, have increased the scope for you
to use an archival or documentary research strategy.
• This means it is now possible to access such sources online from around the
world.
• These potentially provide you with considerable scope to design a research
project that capitalises on the wide range of secondary data sources.
• There are limitations in attempting to use this strategy and we briefly consider
these after outlining types of documentary sources and discussing their attributes.
It is difficult to describe adequately the range of archival and documentary
materials potentially available. Lee (2012: 391) suggests that ‘a document is a
durable repository for textual, visual and audio representations’.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.19

Archival and documentary research

• This illustrates the wide range of materials encompassed by this definition.
Categories of textual documents include:
• • communications between individuals or within groups such as email, letters,
social media and blog postings; • individual records such as diaries, electronic
calendars and notes;
• • organisational documents such as administrative records, agendas and minutes
of meetings, agreements, contracts, memos, personnel records, plans, policy
statements, press releases, reports and strategy statements;
• • government documents such as publications, reports and national statistics data
sets;
• • media documents including printed and online articles and other data

• Documents used for research are considered secondary sources because they
were originally created for a different purpose (see the earlier bullet-point list).
• Researchers using an archival or documentary research strategy therefore need to
be sensitive to the fact that the documents they use were not originally created for
a research purpose.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.20

Case Study
• A case study is an in-depth inquiry into a topic or phenomenon within its real-life
setting (Yin 2018).
• The ‘case’ in case study research may refer to a person (e.g. a manager), a group
(e.g. a work team), an organisation (e.g. a business), an association (e.g. a joint
venture), a change process (e.g. restructuring a company), an event (e.g. an
annual general meeting) as well as many other types of case subject.
• Choosing the case to be studied and determining the boundaries of the study is a
key factor in defining a case study (Flyvberg 2011). Once defined, case study
research sets out to understand the dynamics of the topic being studied within its
setting or context (Eisenhardt 1989; Eisenhardt and Graebner 2007).
• ‘Understanding the dynamics of the topic’ refers to the interactions between the
subject of the case and its context.
• A case study strategy has the capacity to generate insights from intensive and
in-depth research into the study of a phenomenon in its real-life context, leading
to rich, empirical descriptions and the development of theory (Dubois and Gadde
2002; Eisenhardt 1989; Eisenhardt and Graebner 2007; Ridder et al. 2014; Yin
2018).

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.21

Case Study: key features

A case study can be categorised in four ways

and based on two dimensions:

single case v. multiple case

holistic case v. embedded case
Yin (2003)

A single case is often used where it represents a critical case or,

alternatively, an extreme or unique case. Conversely, a single case may
be selected purposively because it is typical or because it provides you
with an opportunity to observe and analyse a phenomenon that few have
considered before. A single case study approach is chosen because of
the nature of the case (i.e. because it is a critical, unique or typical case
etc.)
Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.22

Yin (2018) proposes that a multiple case study strategy may combine a small
number of cases chosen to predict literal replication and a second small number
chosen to predict theoretical replication. Where all of the findings from these cases
are as predicted, this would clearly produce very strong support for the theoretical
propositions on which these predictions were based. This particular approach to
case study strategy therefore commences deductively, based on theoretical
propositions and theory testing, before possibly incorporating an inductive or
abductive approach. Where the findings are in some way contrary to the predictions
in the theoretical propositions being tested, it would be necessary to reframe these
propositions and choose another set of cases to test them. A multiple case study
approach is chosen to allow replication.

Yin’s second dimension, holistic versus embedded, refers to the unit of analysis.
For example, you may have chosen to use an organisation in which you have
been employed or are currently employed as your case. If your research is
concerned only with the organisation as a whole, then you are treating the
organisation as a holistic case study. Conversely, even if you are only researching
within a single organisation, you may wish to examine a number of logical
sub-units within the organisation, such as departments or work groups. Your case
will inevitably involve more than one unit of analysis and, whichever way you
select these units, would be called an embedded case study.
Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.23

Ethnography: key features

• Aims to describe and explain the social world inhabited by
the researcher.
• Ethnography is used to study the culture or social world of
a group.
• Takes place over an extended time period
• Is naturalistic
• Involves extended participant observation
• Ethnography is relevant for modern organisations. For
example, in market research ethnography is a useful
technique when companies wish to gain an in-depth
understanding of their markets and the experiences of their
consumers (Arnould and Cayla 2015; Cayla and Arnould
2013; IJMR 2007)

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.24

Action research: key features

The purpose of an Action Research strategy is to promote
organisational learning to produce practical outcomes through
identifying issues, planning action, taking action and evaluating
action.

• Research IN action - not ON action

• Involves practitioners in the research
• The researcher becomes part of the organisation
• Promotes change within the organisation
• Can have two distinct focii (Schein, 1999) –
the aim of the research and the needs of the sponsor

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.25

Research Strategies
The action research spiral

Saunders et al, (2009)

Figure 5.3 The action research spiral
Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.26

Research Strategies
Grounded theory: key features

• Theory is built through induction and deduction

• Helps to predict and explain behaviour

• Develops theory from data generated by

observations

• Is an interpretative process, not a

logico-deductive one
Based on Suddaby (2006)

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.27

Narrative Inquiry
• A narrative is a story; a personal account which interprets an event or sequence of
events.
• Using the term ‘narrative’ requires a distinction to be drawn between its general
meaning and the specific meaning used here.
• A qualitative research interview inevitably involves a participant in storytelling. In
this way, the term ‘narrative’ can be applied generally to describe the nature or
outcome of a qualitative interview.
• As a research strategy, however, Narrative Inquiry has a more specific meaning and
purpose. There will be research contexts where the researcher believes that the
experiences of her or his participants can best be accessed by collecting and analysing
these as complete stories, rather than collecting them as bits of data that flow from
specific interview questions and which are then fragmented during data analysis.
• In Narrative Inquiry, the participant is the narrator, with the researcher adopting the
role of a listener facilitating the process of narration.
• While in-depth interviews are the primary method to collect stories, other methods
may be used by the narrative researcher to record stories as they occur naturally, such
as participant observation in the research setting ( Coffey and Atkinson 1996 ;
Gabriel and Griffiths 2004 ). Other sources of narratives include autobiographies,
authored biographies, diaries, documentation and informal discussions.

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.28

Time Horizons

Select the appropriate time horizon

• Cross-sectional studies

• Longitudinal studies

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.29

Credibility of research findings

Important considerations

• Reliability

• Validity

• Generalisability

• Logic leaps and false assumptions

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009
Slide 5.30

Summary: Chapter 5
Research design turns a research question and
objectives into a project that considers

Strategies Choices Time horizons

Research projects can be categorised as

Exploratory Descriptive Explanatory Evaluative Combined

Research projects may be

Cross-sectional Longitudinal

Saunders, Lewis and Thornhill, Research Methods for Business Students, 5th Edition, © Mark Saunders, Philip Lewis and Adrian Thornhill 2009