Research Methods

for Business and Social Sciences

Pandelis Ipsilandis
Professor Emeritus, University of Thessaly
 Contents
1. Formulating and clarifying the research topic
2. Critically reviewing the literature
3. Formulating the research design
4. Selecting Samples
5. Using secondary data
6. Primary Data thru Observation
7. Primary Data thru Interviews
8. Primary Data thru Surveys
9. Analysing Quantitative data
10. Analysing Qualitative data
11. Ethics
 Sources

Presentations are based on materials from Saunders M.,

Lewis P., Thonhill A., “Research Methods for Business
Students” (2016), as well as other authors listed in the content
and personal experiences
 Part 1

Formulating and clarifying the

research topic
 Formulating and clarifying the
Research topic
Important steps
• Identifying the attributes of a good research topic

• Generating ideas that help you select a suitable

topic

• Turning ideas into clear research questions and

objectives

• Writing your research proposal

 Attributes of a good research topic (1)

Capability: Is it feasible?
• Are you fascinated by the topic?
• Do you have the necessary research skills?
– Theoretical background, Academic writing skills
– Knowledge of English language
– Relevant tools (e.g. statistical software)
– Project management
• Can you complete the project in the time available?
• Will the research still be current when you finish?
• Do you have sufficient financial and other resources?
• Will you be able to gain access to data?
– Sometimes access to data is difficult. Permissions / Regulations
/ fees
 Attributes of a good research topic (2)

Appropriateness: Is it worthwhile?
• Will the examining institute's standards be met?
• Does the topic contain issues with clear links to theory?
– It may require further study in theory?

• Will the proposed research provide fresh insights into

the topic?
• Are the findings likely to be symmetrical (similar value
whatever the outcome)?
• Does the research topic match your career goals?
– See it as an opportunity to advance your career
Attributes of a good research topic (3)

and - (if relevant)

Does the topic relate clearly to an idea

you were given -

possibly by your organisation ?

 Generating research ideas

Useful Techniques

Rational thinking Creative thinking

Searching the literature Scanning the media

Articles, reports, books e.g. “most of workers
conference proceedings feel overqualified”

Brainstorming Relevance Trees

Exploring past thesis Discussions

Select 6 you like and 3 you don’t like
Write what is appealing or not, Why is good/bad
Keeping a notebook of ideas
 Relevance trees
Example
A relevance tree allows you to map out your initial ideas on a topic, in
this case ‘demand for transport’, and think through various sub-topics in
order to help you identify a specific area to research.
 Refining research ideas

• Using the Delphi Technique

with people who are involved or interested in research idea
• Conducting a preliminary study
– Literature
– Get greater understanding
• Continually testing out your ideas
• Integrating ideas
– Get a clear direction
– Can you express your research questions clearly?

• Refining topics given to you by your organisation

 Writing research questions

Write research questions that are

• Consistent with expected standards

• Able to produce clear conclusions
• At the right level ( not too difficult )
• Not too descriptive
• Use the ‘Goldilocks Test’
Decide if research questions are too big (demand too many
sources), too small (insufficient substance), too hot
(sensitivities aroused as a result of doing the research), or
just right for investigation at this time by this researcher in
this setting.

Clough and Nutbrown (2002)

 Turning ideas into research projects (1)

Examples of research ideas

and their derived focus questions

The use of Internet Banking ?????

?????

Saunders, et al. Business Research Methods

 Turning ideas into research projects (2)

Useful techniques

• Start with a general focus question

• Use the ‘Russian Doll’ principle to reach the essence
of the question
• Discuss areas of interest with your tutor

You are interested in doing research on the interaction

between Business organizations and Technical Schools
• Think about some research questions that may be
appropriate
 Turning ideas into research projects (3)

Writing clear research objectives

• Check your examining body’s preferences for

stated objectives

• Use a general focus question to achieve precise

objectives

Saunders et al. (2009)

Turning ideas into research projects (3)

Research Questions and Research

Objectives
Research Question Research Objective
Why have organizations introduced To identify organizations’ objectives
team briefing? for team briefing schemes
How can the effectiveness of team To establish suitable effectiveness
briefing schemes be measured? criteria for team briefing schemes
How can the effectiveness of team To determine the factors associated
briefing be explained? with the effectiveness criteria for
team briefing being met
To estimate whether some of those
factors are more influential than
others

Saunders et al. (2009)

Turning ideas into research projects (4)

Include SMART Personal objectives

S pecific What precisely you want to achieve

M easurable What measures you use to

determine whether you achieved it
A chievable Is it achievable given all constraints

R ealistic Given all other demands upon your time,

can you still have time and energy to achieve it
T imely Can you complete the research within the
allowed time framework?
 The importance of theory

• Asking for opinions and gathering facts – 'what' questions

(descriptive research)
• Using questions that go beyond description and require
analysis – 'why' questions
Phillips and Pugh (2005)
In order to:
Explain phenomena Analyse relationships

Predict outcomes Compare and generalise

Theory is not References, Data, Lists of variables, Diagrams,
Hypotheses and predictions
But a formulation regarding cause and effect relationships
 Theory vs. Intelligence gathering

• In research the importance of theory must be recognized

and made explicit.
• The purpose of examining relationships between two or
more variables is to explain and predict the relationship
For example, employee opinion surveys
much research yields ambiguous conclusions because they ask
questions which reveal the state of affairs as it is.
What they do not ask is questions which help those who use the
research results to draw meaningful conclusions as to why the
state of affairs is it is
• Radio with no knobs
 Threefold typology of theories

Grand, middle range and substantive theories

Creswell (2002)
• A clear theoretical position is developed prior to collection of data
(deductive approach) – not always the case
• Developing theory after the data have been collected (inductive
approach)
 Writing your research proposal

Purposes of the research proposal

• To organise your ideas

• To convince your audience

• To contract with your client (your tutor)

• To meet ethical requirements

 Content of your research proposal (1)

• Title - likely to change during the process

• Background - context within the literature

• Research questions and objectives - what you seek

to achieve
 Content of your research proposal (2)

• Method - can be in two parts: research design and

data collection

• Timescale and Resources - (finance, data access,

equipment)

• References - include key literature sources

 Evaluating research proposals

• How the components of the proposal fit together

• Viability of the proposal

• Absence of preconceived ideas

 Discussion

1. What is your proposed research topic?

2. Which of the attributes of those discussed, does your topic
possess?
3. What research questions are suggested by your research topic?
4. What research objectives are suggested by your research topic?
5. To what literature does your research topic relate?
6. What are the key dependent and independent variables in your
proposed study?
7. What relationship between the dependent and independent
variables do you think (or expect) you will find?
 Summary: The best research topics

• Formulate and clarify the topic

• Meet the requirements of the examining body
• Use a variety of techniques when generating
research ideas
• Are focused on clear questions based on relevant
literature
• Are theory dependent
• Have a proposal containing organised ideas
Tell the reader:
• What will be done and why
• How it will be achieved
 Part 2

Critically reviewing the literature

 Reasons for reviewing the literature

• To conduct a ‘preliminary’ search of existing

material

• To organise valuable ideas and findings

• To identify other research that may be in progress

• To generate research ideas

• To develop a critical perspective

 Categories of Literature Sources

• Primary (published and unpublished)

– Reports, thesis, conference proceedings,
company reports, government publications,
etc. (Grey literature)
• Secondary
– Journals, books, newspapers, some
government publications
• Tertiary (help locating primary and
secondary)
– Search tools (indexes, abstracts, catalogues,
citation indices, etc.)
 Literature sources available
Literature sources available

Saunders et al. (2009)

Figure 3.2 Literature sources available
 Planning your literature search strategy

• Define a research strategy (discuss it

with your supervisor)
• Parameters
– Language, Subject area, Business sector,
Geographical area, Publication period,
Literature type
• Key words and search items
– Basic terms that describe research questions.
• Will help searching tertiary literature
– Discussion, initial readings, brainstorming,
relevance trees
The literature review process

Source: Saunders et al. (2003)

 The Critical Review (1)

Distinguish between Approaches used

Inductive -
Explores the data to develop theories which are
then tested against the literature

Impossible to collect every single piece of literature before

starting data collection.
Review most relevant and significant research
New findings, new theories will emerge
 The Critical Review (1)

Distinguish between Approaches used

Deductive -
Develops a conceptual framework from the
literature which is then tested using the data

Develop a theoretical and conceptual framework, which

you subsequently test using data
 The Critical Review (2)
Key purposes
• To further refine research questions and objectives
• Highlight research possibilities that have been
overlooked by other researchers
• To discover recommendations for further research
• To avoid repeating work already undertaken
• Gaining insight into aspects of research questions and
objectives that considered newsworthy
– Current opinions in newspapers, professional and trade
journals.
• To provide insights into strategies and techniques
appropriate to your research objectives
Based on Gall et al. (2006)
 Adopting a critical perspective (1)

Skills for effective reading

• Previewing looking around the text before reading to establish its
purpose and how it may help in your literature review
• Annotating conducting a dialog with yourself, the author and the
issues and ideas at stake
Replace highlighter with pencil / mark up margins with words(ideas,
notes, reminders) that connect to your research objectives / Develop
your own symbol system / Get in the habit of hearing yourself asking
questions https://guides.library.harvard.edu/sixreadinghabits
• Summarising stating in your own words
• Comparing and contrasting how your thinking has been
altered, how it has affected your response to issues and themes of
research
 Adopting a critical perspective (2)

What is critical reading?

• Capacity to evaluate what you read
• Capacity to relate what you read to other information
Critical questions in reading
• Why am I reading this?
Stick to the purpose of reading and not get side-tracked too much by
the author’s agenda
• What is the author trying to do in writing this?
Helps in deciding how valuable the writing maybe for your purposes
• What is the writer saying that is relevant to what I want to find
out?
• How convincing is this?
Is the argument based on a conclusion which is justified by evidence
• What use can I make of this reading?
Wallace and Wray (2006)
 Content of the critical review
You will need to

• Include key academic theories within your area of

research

• Demonstrate current knowledge of the area

• Use clear referencing for the reader to find the

original cited publications

• Acknowledge the research of others

 Is your literature review critical?

Evaluating the content

• Have you ensured that the literature covered relates
clearly to your research questions & objectives
• Have you covered the most relevant and significant
theories and recognized experts in the area?
• Have you covered the most relevant and significant
literature or at least a representative sample?
• Have you included up-to-date literature?
• Have you referenced all the literature used in the
appropriate format?

Saunders et al. (2009)

 Is your literature review critical? (1)

Evaluating whether the review is critical

• Have you shown that research questions are related
to review?
• Have you assessed strengths and weakness of
previous research?
• Have you been objective in your discussion and
assessment of previous research?
• Have you included references that is counter to your
opinion?
• Have you made reasoned judgement about the value
and relevance of other research

Saunders et al. (2009)

 Is your literature review critical? (2)

Evaluating whether the review is critical

• Have you justify clearly your own ideas?
• Have you highlighted those areas where your
research is needed to provide fresh ideas?
– Inconsistencies in current knowledge and understanding
– Omissions or bias in published research
– Research findings need to be further tested
– Evidence is lacking, inconclusive, contradictory or limited

• Have you justified your arguments by referencing

correctly published research

Saunders et al. (2009)

 The key to a critical literature review

• Demonstrate that you have read, understood and

evaluated your material

• Link the different ideas to form a cohesive and

coherent argument

• Make clear connections to your research

objectives and the subsequent empirical material
 Structure of the literature review

Three common structures

• A single chapter
• A series of chapters
• Throughout the report
Caution
• Avoid to produce a list of uncritical listing of previous
research
• Need to contrast different author’s ideas and form
your own opinion and conclusions
• Start drafting early. Can update and revise as you
reading more
Evaluating the structure of literature review
• Does your literature review have a clear title which describes the
focus of your research rather than just saying “literature review”?
• Have you explained precisely how you searched the literature
and the criteria used to select those studies included?
• Does your review start a general level before narrowing down?
• Is your literature review organized thematically around the
areas contained in the research being reviewed, rather than the
researchers?
• Are your arguments coherent and cohesive - do your ideas
link in a way that will be logical to reader?
• Have you used sub-headings within the literature review?
• Does the way you have structured your literature review draw
your reader’s attention to those issues which are going to be
the focus of your research
• Does your literature review lead your reader into subsequent
sections of your thesis
 Recording the literature

Make notes for each item you read

• Bibliographic details
– According to referencing style required
– Enable anyone to access the information

• Brief summary of content

• Supplementary information
– Quotation / Source / Tertiary resource used / Comments /
Date for internet sources) / Filename

Sharp et al. (2002)

 Tools for literature management

To access, organize, read, cite and share

scholarly research
• EndNote
• RefWorks
• Papers
• Mind Map software
• Unpaywall (Firefox plugin)
• Zotero (Android app, desktop program, or Firefox
plugin)
 Evaluating the literature

• How do I know what I am reading is relevant?

• How do I know when I have read enough?
• Define the scope of your review
– For some questions the is no so much closely
related literature – review more broadly
• Assess relevance and value
– How recent? / Are any references to this item? /
research question-objectives close to yours / Item
supports or contradict your argument (either way
include it)
– Biased / methodological omissions / Sufficient
precision / guidance for future research
• Assess sufficiency
– When further searches do not provide new
references
 Plagiarism
Four common forms

• Stealing material from another source

• Submitting material written by another

• Copying material without quotation marks

• Paraphrasing material without documentation

Adapted from Park (2003), cited in Easterby-Smith et al. (2008)

 Key words – Relevant literature

Brainstorming on the following research questions

Finding key words, literature…

– How effective is profit related pay

as a motivator?

– How do opportunities available to a first-time house

buyer through interpersonal discussion influence the
process of selecting a financial institution for the
purposes applying for a house purchase loan?

– To what extent go new methods of direct selling of

financial services pose a threat to existing providers?
 Summary: Part 2

The critical literature review

• Sets the research in context
• Leads the reader into later sections of the report
• Begins at a general level and narrows to specific topics
A literature search requires
• Three main categories of sources
• Clearly defined research questions and objectives
• Defined parameters
• Use of techniques – ( brainstorming and relevance trees)
 Part 3

Formulating the research design

Understanding your research philosophy
‘Research philosophy is an over-arching term relating
to the development of knowledge
and the nature of that knowledge’

• This is what exactly what you are doing when

embarking on doctoral studies.
Perhaps not as dramatic as the theory of Human Motivation

Adapted from Saunders et al, (2009)

Research Philosophy, Design and Tactics
The research onion

Saunders et al, (2009)

 Research philosophies (1)
Positivism
• Working with an observable social reality and the product
of such research can be law-like generalizations
Example
Theoretical proposition: Increased costs may negate the productivity
gains from home working
Specific Hypotheses:
i. Increased costs for computer hardware, software will negate productivity
gains from home working
ii. Home workers will require additional support from on-site employees (e.g.
technicians) which will negate productivity gains from home working
iii. Work displaced to other employees and increased supervisory
requirements will negate productivity gains from home working
iv. Reduced face to face access by home workers to colleagues will result in
lost opportunities to increase efficiency which will negate productivity gains
from home working
 Research philosophies (2)
Realism
• Relies on the idea of independence of reality from the
human mind. This philosophy is based on the assumption
of a scientific approach to the development of knowledge
• Direct realism, (also known as naive realism)
– “what you see is what you get”. Portrays the world through
personal human senses. In business context, the world operates
at one level: the individual, the group, the organization (observed
directly)
• Critical realism
– According to critical realism, sensations and images of the real
world can be deceptive and they usually do not portray the real
world. In business context critical realism will look into interaction
of three levels (what we don’t observe directly)
 Research philosophies (3)
Interpetivism
• Rich insights into a complex world are lost if such
complexity is reduced entirely into law-like generalization
• It is necessary for the researcher to understand
differences between humans as social actors
– Actors play a part and interpret it in way that could be their own or
the director’s
– The researcher has to adopt an empathetic attitude
– Could be highly appropriate in the case of business and
management research, especially in areas like organizational
behaviour, marketing, human resource management. Business
situations are complex and unique most times.
 Research philosophies (4)
Pragmatism
• Thinking about solving problems in a practical and
sensible way, rather than by having fixed ideas and
theories (oxford dictionary)
The word pragmatism is derived from the Greek pragma (“action,” or “affair”).
The Greek historian Polybius (died 118 bc) called his writings “pragmatic,”
meaning thereby that they were intended to be instructive and useful to his readers.
• The most important determinant of the epistemology,
ontology, and axiology you adopt is the research question
John Dewey was a leading proponent of the American school of thought known
as pragmatism, a view that rejected the dualistic epistemology and metaphysics of
modern philosophy in favor of a naturalistic approach that viewed knowledge as
arising from an active adaptation of the human organism to its environment.
Research Philosophy, Design and Tactics
The research onion

Saunders et al, (2009)

 Research Approaches (1)
Induction
Building theory by –
• Understanding the way humans build their world
• Permitting alternative explanations of what’s
going on
• Being concerned with the context of events
• Using more qualitative data
• Using a variety of data collection methods
 Inductive Research Approach (2)
When there is little to no existing literature on a topic, it is common to
perform inductive research because there is no theory to test. The
inductive approach consists of three stages:

Limitations: A conclusion drawn on the basis of an inductive method

can never be proven, but it can be invalidated.
 Research Approaches (3)

Deduction
5 sequential stages of testing theory
i. Deducing a hypothesis
ii. Expressing the hypothesis operationally
iii. Testing the operational hypothesis
iv. Examining the specific outcome of the enquiry
v. Modifying the theory (if necessary)

Adapted from Robson (2002)

 Research Approaches (4)

Characteristics of Deduction

• Explaining causal relationships between variables

• Establishing controls for testing hypotheses

• Independence of the researcher

• Concepts operationalised for quantative measurement

• Generalisation
 Deductive Research Approach (5)
In deductive research, you always start with a theory. Reasoning
deductively means testing these theories. If there is no theory yet,
you cannot conduct deductive research.

Limitations: Conclusion of deductive reasoning can only be true if all the

premises set in inductive study are true
 Choosing your research approach

The right choice of approach helps you to

• Make a more informed decision about the

research design

• Think about which strategies will work for your

research topic

• Adapt your design to cater for any constraints

Adapted from Easterby-Smith et al. (2008)

 Combining research approaches

Things worth considering

• The nature of the research topic

• The time available

• The extent of risk

• The research audience

 Deductive and Inductive research
Major differences between these approaches

Saunders et al, (2009)

Table 4.2 Major differences between deductive and inductive approaches to
research
 The Process of Research Design

• Research choices

• Research strategies

• Time horizons
Research Philosophy, Design and Tactics
The research onion

Saunders et al, (2009)

 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

Good research, like a good building, is attributed to its
architect Robson (2002)
 Classification of the research purpose

• Exploratory research
– Finding out “what is happening” seek new insight”
– Could be time well spend even if it shows that it is
not worth pursuing the research
– Search literature / interviewing “experts” / focus
groups
• Descriptive studies
– Get a clear picture of the phenomena
– It is the means not the end
• Explanatory studies
– Establishing causal relationships
 Research Strategies

Experiment Action research

Grounded theory Survey

Ethnography Case study

Archival research
 Research Strategies

An experiment will involve

• Definition of a theoretical hypothesis

• Selection of samples from know populations
• Random allocation of samples
– Control and Experimental groups
• Introduction of planned intervention
• Measurement on a small number of dependent
variables
– Control of all other variables
 Research Strategies
A classic experiment strategy

Saunders et al, (2009)

 Research Strategies
Survey: key features
• Popular in business research
• Perceived as authoritative
– Easy to explain and understand
– Sometimes could go really badly
• Allows collection of quantitative data
• Data can be analysed quantitatively
• Samples need to be representative
• Gives the researcher independence
• Other forms of survey besides questionnaires
– Structured observation (organization and methods research)
– Structured interviews
 Research Strategies
Case Study: Key features
• Provides a rich understanding of a real life context
– Boundaries between phenomenon and context not clear
– Generate answers related to “why” as well as to “what”
and “how” (concerning mostly surveys)
• Uses and triangulates multiple sources of data
Categorised in four ways based on two dimensions:
single case v. multiple case
holistic case v. embedded case
• Reluctance because of “unscientific” feel
• Enable to challenge existing theory source of new
research questions
Yin (2003)
 Research Strategies
Action research: Key features

• Research IN action - not ON action

• Involves practitioners in the research
• The researcher becomes part of the organisation
• Promotes change within the organisation
• Answers the “how” question
• Can have two distinct focii (Schein, 1999) –
the aim of the research and the needs of the sponsor
Research Strategies
The action research spiral

Saunders et al, (2009)

 Research Strategies
Grounded theory: key features
• Theory is built through induction and deduction
• Helps to predict and explain behaviour
– e.g. consumer’s behaviour, employees satisfaction
• Develops theory from data generated by
observations
- not an excuse to ignore literature or defer until data is collected
- not a presentation of raw data. Draw conclusion that contain
theoretical insight
- it is not theory testing, content analysis
- not routine application of formulaic procedures to data
- not mechanical involving techniques and procedures
- highly creative
• It is an interpretative process, not a logico-deductive
one
Suddaby (2006)
 Research Strategies
Grounded theory: An example

Stefan Seidel, Jan Recker (2009)

Important but under-researched IS domain, business process
management, is characterized by an abundance of conceptual work
with very little thorough theory development.
Use of grounded theory
Illustrative case study shows how grounded theory allowed the
development of theories about creative organizational
processes, and the influence of creativity requirements on the
management of such processes. Based on the experiences
gathered, a set of key issues that highlight why and when
grounded theory can be particularly suitable for the study of
phenomena associated with the business process management
domain is suggested.
 Research Strategies

Ethnography: key features

• Aims to describe and explain the social world
inhabited by the researcher. An inductive
approach
• Takes place over an extended time period.
Immerse in the social world being researched.
• Is naturalistic. Researching the phenomenon
within the context in which it occurs.
• Involves extended participant observation. Not
oversimplifying with questionnaire surveys
 Research Strategies

Archival research: key features

• Uses administrative records and documents as

the principal sources of data

• Allows research questions focused on the past

• Is constrained by the nature of the records and

documents
 Research Strategies
The role of the practitioner-researcher
Key features

• Research access is more easily available

• The researcher knows the organisation
• Has the disadvantage of familiarity
• The researcher is likely to their own assumptions
and preconceptions
• The dual role requires careful negotiation
Multiple research methods
Research choices

Saunders et al, (2009)

 Multiple research methods
Reasons for using mixed method designs:
• Triangulation
– Corroborate research findings
• Facilitation
– Use one method to facilitate application of another method
(e.g. interview followed by questionnaire survey)
• Complementarity
– Different aspects can be fit together (e.g. quantitative and
qualitative)
• Generality
– Independent sources to contextualize study, provide a sense
of relative importance
• Aid interpretation
– Qualitative analysis to help interpret quantitative findings
• Study different aspects
– Quantitative for macro aspects, qualitative for micro
• Solving a puzzle – alternative methods when deadlock w/ initial
Source: developed from Bryman (2006)
 Time Horizons

Select the appropriate time horizon

• Cross-sectional studies
– Most probably for doctoral projects

• Longitudinal studies
– Study change over time
– Mostly economy related data for academic
research
– Other examples: study changes in content and
style of TV shows over time
 Credibility of research findings
Important considerations
• Reliability
– Consistent findings
– Same results in other occasions
– Same results reached by other observers?
– Transparency in how findings are derived from raw
data
– Participant errors (questionnaires regarding job
satisfaction completed at different days of the week)
– Participant bias (ensure anonymity)
– Observe error (questions asked differently)
– Observer bias
 Credibility of research findings
Important considerations
• Validity
– Timing (recent or expected events)
– Testing (respondent may think that answers will affect
their position)
– Instrumentation (practices changes during the
observation period)
– “Mortality” (respondents dropping out of study)
– Maturation (events affect behaviour of respondents)
– Ambiguities about causal direction (poor performance
and negative attitude)
 Credibility of research findings
Important considerations

• Generalisability
– Are results equally applicable to other settings

• Logic leaps and false assumptions

– Identification of research population
– Data collection
– Data interpretation
 Research design ethics

Remember

‘The research design should not subject the

research population to embarrassment, harm or
other material disadvantage’

Adapted from Saunders et al, (2009)

 Research strategies and design

Brainstorming on Research design issues

 Research strategies and design

Brainstorming on Research design issues

 Research strategies and design

Brainstorming on Research design issues

 Research strategies and design

Brainstorming on Research design issues

 Summary: Part 3
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
Research projects may be
Cross-sectional Longitudinal
Important considerations
• The main research strategies may combined in the
same project
• The opportunities provided by using multiple methods
• The validity and reliability of results
• Access and ethical considerations
 Part 4

Selecting Samples
 Selecting samples
Population, sample and individual cases

Source: Saunders et al. (2009)

 The need to sample

Sampling- a valid alternative to a census when

• A survey of the entire population is impracticable

• Budget constraints restrict data collection

• Time constraints restrict data collection

• Results from data collection are needed quickly

 Overview of sampling techniques
Sampling techniques

Source: Saunders et al. (2009)

Figure 7.2 Sampling techniques
 Probability sampling

The four stage process

1. Identify sampling frame from research objectives

2. Decide on a suitable sample size

3. Select the appropriate technique and the sample

4. Check that the sample is representative

 Identifying a suitable sampling frame

Key points to consider

• Problems of using existing databases

– Incomplete (businesses listed in chamber of commerce dbase)
– Inaccurate information (not updated continuously
• Extent of possible generalisation from the sample
– Can conclusion be generalized
• Validity and reliability
• Avoidance of bias
– The case of landline telephone directory
– Data bases provided commercially by various companies may
lead to biased samples (e.g. if they contain internet users)
 Identifying a suitable sampling frame

Example
Research topic:
The effect of internationalization in SMEs performance
Objectives:
Explore the effects of internationalization, an entrepreneurial
strategy employed by small and medium‐sized enterprises (SMEs),
on firm performance. Relate the extent of foreign direct investment
(FDI), exporting activity, and use of alliances, to the corporate
performance of internationalizing SMEs.

Identify sampling frame

 Identifying a suitable sampling frame

Check list
• Are cases listed in sampling frame relevant to your
research topic. Will help in answering research
questions
• How recently sampling frame compiled
• Does sampling frame include all cases
• Does the sampling frame contain correct information
• Does the sampling frame exclude irrelevant cases
• Can you establish and control haw sample is selected
(published data bases)
 Sample size

Choice of sample size is influenced by

• Confidence needed in the data (represent the population)
– (usually 95%, sometimes 99%)
• Margin of error that can be tolerated in estimates
• Types of analyses to be undertaken
– Grouping based on qualitative variables, number of variables, etc.
• Size of the Margin of error

sample Population 5% 3% 1%

population 50 44 48 50

and distribution 100 79 91 99

. 200 132 168 196

1000 278 516 906
10000 370 964 4899
100000 383 1056 9513
 The importance of response rate

Key considerations

• Non- respondents and analysis of refusals

– Total response rate = total responses / (sample size - ineligible)

• Obtaining a representative sample

– Who are the non respondents

• Calculating the active response rate

– Active response rate = total responses / (sample size - ineligible -
unreachable)

• Estimating response rate and sample size

– Include estimate in adjusting sample size
 Selecting a sampling technique
Five main techniques used for a probability sample
• Simple random
– Assign random numbers (easy if sample is stored in a database)
– Select N largest or N smallest random numbered cases (it makes
no difference)
• Systematic
– Compute sampling fraction (sample size / population size). If
sampling fraction is 0.05, pick one randomly and select every 20th
case
• Stratified random (Modification of random sampling)
– Division of population in strata based on stratification variable. Apply
simple random or systematic random selection in each strata
• Cluster
– Similar to stratified. Division of population in natural clusters.
Sampling frame is the list of clusters. Select clusters randomly
• Multi-stage
 Checking that sample is representative

• Compare data you collected in the sample with

data from another source for the population
– E.g. compare on the age and socioeconomic
characteristics with country or regional population as
recorded in the last census
– For a sample of employees compare for industry type,
salary level, etc. depending on the research questions
• Could use statistical test (e.g. Kolmogorov) to test
statistical significance
• For longitudinal studies compare samples at
different points in time
 Non- probability sampling (1)

Key considerations

• Deciding on a suitable sample size

• Selecting the appropriate technique

 Non- probability sampling (2)

Sampling techniques
• Quota sampling (larger populations –sampling frame
not possible)
– Similar to stratified. A certain quota from each group.
• Purposive sampling
– Use judgement to select cases that will best enable
answering your questions (small sampling frames)
– Grounded theory research
– Extreme case sampling
– Heterogeneous / maximum variation sampling
– Critical case sampling (if happens there, will happen
everywhere)
– Typical case sampling (illustrative profile)
 Non- probability sampling (2)

Sampling techniques
• Snowball sampling
– Difficult to identify population. Contact 1-2 members. Ask
them to identify other cases and so on.
• Self-selection sampling
– Publicize need for cases. Individuals identify their desire to
participate
• Convenience sampling
– Select those cases that are easier to obtain for your sample.
Sampling Techniques
Sampling Techniques
 Summary: Part 4

• Choice of sampling techniques depends upon the research

question(s) and their objectives
• Factors affecting sample size include:
- confidence needed in the findings
- accuracy required
- likely categories for analysis
• Probability sampling requires a sampling frame and can be
more time consuming
• When a sampling frame is not possible, non- probability
sampling is used
• Many research projects use a combination of sampling
techniques
All choices depend on the ability to gain access to cases
 Part 5

Using secondary data

 Using secondary data for research (1)

Types of secondary data

• Documentary – written and non-written

• Surveys – subtypes include:

censuses, regular and ad hoc
Using secondary data for research (2)
Types of secondary data

Source: Saunders et al. (2006)

 Using secondary data for research (3)

Multiple – source secondary data

• Documentary , survey, or an amalgam of both

• Times series for longitudinal studies

• Cohort studies

• Area-based data sets

 Locating secondary data

Finding the data - a two stage process

1. Establishing that the required secondary data

is available

2. Locating the precise data required

 Availability of secondary data (1)

Sources

• References in publications (books, journal articles)

• Within organisations (unpublished sources)

• Tertiary literature –
( indexes and catalogues in archives or online)
 Availability of secondary data (2)

Finding secondary data

• References in published guides (Table 8.1)

• Data held by organisations

• Data on the Internet (Table 8.2)

 Evaluating secondary data (1)
Advantages
• Fewer resource requirements
– Higher quality, Get data quickly, more time for analysis
• Unobtrusive
– Higher quality, Get data quickly, reliable, inconspicuous
• Longitudinal studies may be feasible
– Published periodically
• Provision of comparative and contextual data
– Used as basis for comparisons with data you selected, place
your data in more general context, triangulate findings
• Unforeseen discoveries may occur
– Link between cancer and smoking was established through
analysis of medical records that were not collected for this
purpose
• Generally permanent and available
 Evaluating secondary data (2)
Disadvantages
• Purpose of data collection may not match the
research needs
– May not be totally appropriate for your research. Research
questions will be answered partially
• Access may be difficult or costly
– Some not available electronically, others are not available
free
• Aggregations and definitions may be unsuitable
– Most of the data are aggregated at a level not suitable for
the research
• No real control over data quality
– Most of higher quality but still data sources must be
evaluated
• Initial purpose may affect data presentation
– Especially in reports. Authors select and emphasize parts of
the data
 Evaluating secondary data (3)

Ensure that data sources

• Enable the research question(s) to be answered

• Enable research objectives to be met

• Have greater benefits than their associated costs

• Allow access for research

 Evaluating secondary data (3)
Evaluating potential secondary data sources

Figure 8.2 Evaluating potential secondary dataSource:

sourcesSaunders et al. (2009)
 Suitability of secondary data (1)

Overall suitability: points to consider

• Precise suitability, including reliability and validity
- assessment of collection methods
- clear explanation of collection techniques
• Measurement validity
- Is it clear what the numbers represent
e.g. Sales ? (orders, value, volume
- Check how other researchers coped with
the same data
• Measurement bias and deliberate distortion
- Mostly in non-numerical data
- Reports, minutes
 Suitability of secondary data (2)

Overall suitability: points to consider

• Coverage and unmeasured variables

- ensure exclusion of unwanted data
- ensure sufficient data remain for analysis

• Costs and benefits

 Evaluating your secondary data
sources
Overall suitability Checklist
• Does the data set contain the information you require to answer
your research questions and meet your objectives
• Do the measures used match those you require
• Is the data set proxy for the data you really need
• Does the dataset cover the population that is the subject of your
research
• Does the dataset cover the geographical area that is the subject
of your research
• Can data about the population that is the subject of your
research separated from unwanted data
• Are the data for the same period or sufficiently up to date
• Are data available for the variables you require to answer your
research questions and meet your purpose
 Evaluating your secondary data
sources
Precise suitability Checklist (1)
• How reliable is the data you are thinking of using?
• Is it clear, what the source of the data is? How credible is it?
• Do the credentials (author, institution or organization sponsoring
the data) suggests it is likely to be reliable?
• Do the data have an associated copyright statement?
• Do associated published documents exist?
• Does the source contain contact details for any further
information about the data?
• Is the method clearly described? If sampling used, what were
the associated sampling errors and response rates?
 Evaluating your secondary data
sources
Precise suitability Checklist (2)
• Who was responsible for collecting for recording/
• Is a copy of the questionnaire or interview checklist included?
• Is it clear how data was analysed and compiled?
• Are data likely to contain measurement bias?
• What was the original purpose for which the data was collected?
• Who was the target audience and what was its relationship to the
data collector or compiler?

Saunders et al. (2009)

 Using secondary data

• Research question
“How would UK’s import and export trade
be affected by possible Brexit”
• List arguments to convince someone of the
suitability of secondary data
 Using secondary data

• Suggest possible secondary data

I. “to what extend do organization’ employee-relocation
policies meet the needs of employees”

II. How have consumer-spending patterns have changed

in the last 10 years
 Summary: Part 5
• Secondary data consists of three main types - documentary,
survey and multiple sources
• The data can be used in a variety of ways
• Secondary data may be less current and collected for a
purpose that does not match your research question(s)
• Secondary data needs to be located and its availability
established
• Data sources should be assessed for suitability, measurement
validity and coverage
• Evaluation of secondary data should include reliability and any
measurement bias
• Costs and benefits of using secondary data should be
evaluated and compared with alternative sources
• Although secondary data may contain some bias, it can help
to answer your research question