Nicholas Walliman

Research Methods: The

Basics, vol. 3
Kate Zonberga
Business Administration
Erasmus+, study year 3
COLLECTING AND
ANALYSING
SECONDARY DATA
PART II
The main research methods
Though many sources of data are free, others are costly to
acquire and may be difficult to access.

When using data from a variety of sources, there are likely to

be mismatches in terminology and the way the data has been
collected and analyzed, making aggregation of the data difficult
or open to challenge.

"Wherever there exists a body of recorded information, there

are subjects for study."
Data is a permanent resource on
which to base your research.
All research studies require secondary data for the background to the study,
primary data at some research levels can even be optional.
As a researcher, you will face several problems when
seeking previously recorded historical and data.
The main of these are that of:
- locating and accessing them
- authenticating the sources
- assessing credibility
- gauging how representative they are
- selecting methods to interpret them
 • Written materials – organizational records,
communications, publications

Types • Non-written materials - television and radio

and sources programmes, tape recordings, video tapes,
films, works of art, historical artefacts etc.
of secondary
• Survey data – government census of population,
data employment, household surveys, economic data,
organizational surveys of markets, sales, economic
forecasts, employee attitudes.
 The principle types
and sources of secondary data

Data sets online - online sites that provide access to data (statistics,
maps, charts) sites from a variety of sources.

Documentary data - cultural texts, libraries, museums, archives,

commercial and professional bodies.
 The meaning of the term ‘cultural texts’ has
been broadened from that of purely literary
works to that of the many manifestations of
cultural exchange, be they formal such as
opera, TV news programmes, cocktail parties
Cultural texts etc., or informal such as how people dress or
converse.
The main criterion for cultural texts is that
one should be able to ‘read’ some meanings
into the phenomena, including tactile, smells,
visuals, tastes and aural aspects.
 Local libraries - data of local interest.
Museums, galleries and collections - efficient
cataloguing systems for research.
Libraries, Larger museums - research departments.
museums and Also much valuable historical material is
contained in more obscure and less organized
other archives collections, in remote areas and old houses
and specialist organizations, or even private,
restricted collections.
 Often hold statistical information, both
current and historic.
Commercial and Difficult to access unless you are a trusted
employee.
professional Some forms of information (general statistics,
bodies employment trends, income data etc.) can be
published or accessed through a company
web page.
 • Do measures match those you need, e.g.
economic, demographic, social statistics?
• Coverage – is there sufficient data of required
type, and can unwanted data be excluded?
• Population – is it the same as required for your
Stability of chosen research?
data for your • What variables are covered – the precise
nature of these might not be so important for
project descriptive work but could be essential for
statistical tests or explanatory research?
• Will benefits be greater than your costs?
• Will you be allowed access?
 Research methods used

Sampling method used

Authentification
and credibility Response rate of surveys
(issues to be assessed
when checking data
credibility)
Context in which the data was collected and/or
recorded

Analythical methods used to process data

Analyzing secondary data

• Analysis of secondary data can aim at looking for patterns or trends across the
results, to track progressions through time, or to seek out repetition of certain
results to build up a strong case.
• Of the many different ways to analyse secondary data, many are no
different from those used for primary data.
• However, it is worth mentioning three methods that are particularly suitable for
secondary sources: content analysis, data mining and meta-analysis.
 Quantitative form of analysis that consists of
an examination of what can be counted.

The analysis is done very often, but not

necessarily, from secondary sources.
Content analysis
It is done by counting the frequency of
phenomena within a case in order to gauge its
importance in comparison with other cases.
 State the Employ sampling Devise the units
research problem methods of analysis

Stages of Describe and Do quality checks

content number the
codes (measures)
Retrieve coded
fragments
and
interpretation
analysis
Analyze the data
 Quantitative form of analysis that consists of
an examination of what can be counted.

It is done by counting the frequency of

phenomena.

Coding A coding schedule, coding manual and

tabulation of results is used.

This form of analysis allows large quantities of

data to be analysed in order to make
generalizations and to discover the affects
on audience.
 Technique used extensively by business
managements to extract meaningful
information from huge databases generated
by electronic and other methods.

Data mining uses statistical tools to explore

Data mining the data; this involves pattern discovery and
the prediction of trends and behaviours.

More complex mining operations employ

fuzzy logic, genetic algorithms and fractal
based transformations.
 Consists of making an analysis of the results of
a number of results of previous research - a
statistical analysis of the accumulated data
from the results of previous studies.
Meta-analysis
It is not flawless, but it is a useful way to
assimilate the results of numerous studies
dedicated to one issue.
 Find common
Collect the studies
Define the issue to methods and
acording to the
be investigated variables used to
issue defined
detect relationships

Stages of Select the purpose

of analysis of result
Carry out the Report the results,
statistical analysis discuss limitations
meta-analysis data

Recommend
further resarch in
the subject
PART II
The main research methods

QUALITATIVE
DATA ANALYSIS
This type of research is based on data expressed mostly in the
form of words rather than on numbers and is common
whenever people are the focus of the study.

Frequently the situation or process under study is not

sufficiently understood, therefore repeated bursts of data
collection and analysis allow adjustments.

"There is still an element of ‘art’ in dealing with

qualitative data."
Ten steps to take when carrying out
qualitative research
Clearly state the research issues or questions.

Collect background information to help understand the relevant context, concepts and theories.

Suggest several interpretations or answers to the research problems or questions based on this
information.

Use these to direct your search for evidence that might support or contradict these. Change the
interpretations or answers if necessary.

Continue looking for relevant evidence. Eliminate interpretations or answers that are contradicted,
leaving, hopefully, one or more that are supported by the evidence.
Ten steps to take when carrying out
qualitative research
‘Cross examine’ the quality and sources of the evidence to ensure accuracy and consistency.

Carefully check the logic and validity of the arguments leading to your conclusions.

Select the strongest case in the event of more than one possible conclusion.

If appropriate, suggest a plan of action in the light of this.

Prepare your report as an account of your research.

To convince others of your conclusions, there must
be a good argument to support them.
In fact, you will be acting rather like a lawyer presenting a case, using a quasi-judicial
approach such as used in an enquiry into a disaster or scandal.
 1. Data reduction
2. Data display
3. Conclusion drawing/ verification
Steps in
analysing the Data reduction through coding, clustering and
summarizing provides the first step to simplification,
data followed by arranging the compacted data into
diagrams and tables which can display the data in a
way that enables you to explore relationships and
gauge the relative significances of different factors.
Clasification from: Miles and Huberman (1994: 10–12)
Preliminary analysis during
data collection

The process of data reduction and analysis

should be a sequential and continuous
procedure, simple in the beginning stages of
the data collection, and becoming more
complex as the project progresses.
For example, making small, critical and summarized notes when doing a
field research and afterwards processing the information to make it clear
and useful, beginning with a one-page summary which, when processed,
can turn into a multiple page source of information.
Typologies and taxonomies

Typologies and taxonomies - classification by types or

properties thereby forming subgroups within the general
category at a nominal level of measurement.
Even a simple classification can help organize information and identify patterns in the data. Then,
noting the differences in terms of behaviour patterns between these categories can help generate
the kinds of analysis that will form the basis for the development of explanations and conclusions.

After creating and adapting typologies and taxonomies, next

step that follows is coding (previously described).
Pattern coding

A method of pulling together the coded

information into more compact and meaningful
groupings - smaller analytical units such as
themes, causes/explanations, relationships
among people and emerging concepts.

Generating pattern codes is surprisingly easy, as

it is the normal way that we process
information every day.
Interim summary

A few pages long provisional report that

summarizes everything known so far,
usually created about one third of the
way through data collection.

It is a useful tool to reflect on the work

done and to discuss with colleagues and
supervisors
 As the traditional text-based reports are lenghty,
it is time-consuming and difficult to overlook
everything both for the writer and the reader so
a good way to overcome this is by using graphical
displays - matrices/tables and networks.
Analysis during
and after data Matrices and tables – summerize a substantial
amount of information in an easily
collection understandable way by using simplified codes.

Networks - detailed and sophisticated display of

data summaries that allow comparisons to be
made easily across cases.
Qualitative methods of analysis of
texts, documents and discourse

Interrogative Problem-solution Membership

insertion discourse categorization

Rethorical
Narrative analysis Semotics
analysis

Discourse analysis
PART II
The main research methods

WRITING THE PROPOSAL

AND WRITING UP THE
RESEARCH
 Formulating a successful research proposal
Research proposal – explains the nature of the research, its context and why it is needed.

Clarifying aims of the reaserch – helpful to both the researcher and reader to understand what
needs to be done.

The proposal is followed by a statement of the aims and objectives of the research and how it
will be carried out, finally followed by a description of required resources for carrying out the
work.
The research proposal, once approwed, works as a contract outlining the basis of agreement
between parties involved.
 Academic research proposals are usually
composed of the following elements:
• the title;
• aims of the research;
The main • the background to the research;
• a definition of the research problem;
ingretients and • outline of methods of data collection and
sequence analysis;
• possible outcomes;
• timetable of the project and description of
any resources required;
• list of references.
 The function of the title is to encapsulate in a
few words the essence of the research.

The title is likely to include the main concept and

The title variables, and limits to the scope.

Phrases as ‘an investigation into’, ‘a study of’,

‘aspects of’, should be left out as these are
obvious attributes of a research project.
 This section includes one main aim, and perhaps
two or three subsidiary aims resulting from it.

Aims of the Precision is essential – too many or vague aims

research indicate woolly thinking and will be difficult or
impossible to achieve within the available
resources and time.
 This explains to the reader the background from
which the research problem emerges.
The context –
beckground and It should explain the major factors which
surround the problem, and of any significant
previous literature which relates to it.
research
It also has the function of capturing the interest
of the reader.
 Provides the focus of the research project.

The research It is the culmination of the background work and

the initiator of the specific research tasks.
problem
It must be very clearly defined to explain the
nature of the problem and why it is significant.
 Explains briefly what you are going to do in order
to carry out your research, based on your chosen
research approach.
Outline of
methods These have to be specifically tailored to
efficiently collect and analyse data relevant to
the specific research problem and to produce the
outcomes aimed at.
 The formulation of a timetable is essential in
order to allocate time limits to the sequence of
tasks that you need to accomplish in order to
hand the finished report or dissertation in on
Timetable of the time.
project and
description of Resources that are essential to the project, such
as equipment, transport, skills, software etc.
any resources should be listed and availability assured in order
to convince the reader (and yourself) of the
required practicality of achieving the aims of the project.
 The location of the cited work of others must be
meticulously recorded in this list.
List of
Not only does this ensure that the writer cannot
references be accused of plagiarism but also demonstrates
that the writer is aware of the latest thinking in
the subject.
 • There is no need for the research.
• The scale of the proposed research is too big so an
adequate conclusion cannot be reached.
• The aims and objectives are vague or impractical or do
not match, or are expressed as personal goals.
• The research problem is not clearly defined so the
Why might a research work has no adequate focus.
• The procedures are confused with the objectives.
proposal be • There is a lack of logic in the argument in the proposal,
rejected? so the link between the research aims and outcomes is
broken.
• The project is formulated on an emotional or a political
agenda rather than a factual or a theoretical basis.
• Not enough information is provided about the details
of the project.
• Access to information, equipment or other resources
are uncertain or impossible.
Writing up a dissertation or research project

Whatever the subject, there must be a central issue that is being investigated which provides the focal point
of the text.

The body of the dissertation will then revolve around this focal point, perhaps considering it from different
perspectives, or examining causes or finding explanations.

This will lead to some conclusions at the end, and this is why argument is required. These conclusions
should be based on evidence, and a reasoned argument from this evidence leads to your conclusions.
When to start writing up
Creating a proposal

Preparing a structure to follow

Collect notes, observations, data

Create the first draft by inserting information into the structure

Fill in the gaps

Revision
 The framework for the dissertation is most easily
created by making a list of possible chapter or
section headings, e.g.:

• Introduction
• Background and previous research
• The main issues and research problem
Frame and
• Research methods – how you will investigate the
fill problem
• A description of the research actions and their
results
• Conclusions in relation to the research problem
 The whole point of collecting data and analysing it to
come to some conclusions that are relevant to the
research problem and achieve the aims of the
project.

It is unlikely that the problem chosen is simple, with

questions raised that can be answered with a simple
Coming to yes or no.

conclusions
Throughout the research project conclusions should
be made for each chapter so that at the end of the
research paper all these could be just summerized
and simplefied.
 Revision can be done at different levels:
• The more general levels are concerned with
getting the structure and sequence right;
• At a more detailed level, one might look at the
sequence of paragraphs – does each
Revisions concentrate on one point, do they follow each
other in the right sequence?
• At the most detailed level one will be looking at
grammar, punctuation, vocabulary and
spelling.
Thank you for
your attention!