Week 6: Mixed Methods –
Quantitative + Qualitative Research
Module: BUSINESS PROJECT
|WEEK 1||Introduction to the Module/Assessment Strategy/The Nature of Business Management Research|
|WEEK 2||Planning a Research Project|
|WEEK 3||Critically Reviewing the Literature|
|WEEK 4||The Nature of Qualitative Research|
|WEEK 5||The Nature of Quantitative Research|
|WEEK 6||(a) Mixed Methods Research (b) e-Research|
|WEEK 7||(a) Analysing Qualitative Data (b) Qualitative Analysis – Nvivo|
|WEEK 8||(a) Analysing Quantitative Data (b) Quantitative Analysis – SPSS|
|WEEK 9||(a) Writing up Business Management Research (b) Writing up Business Research Outputs|
|WEEK 10||Assessment Week – Submission of INDIVIDUAL RESEARCH PROPOSALS|
1. Discuss the distinction between quantitative and qualitative
2. Explain problems with the quantitative/qualitative divide
3. Learn how to breakdown the quantitative/qualitative divide and
use both to mitigate the disadvantages of the other
4. Be aware of strategies to address the main criticisms of
quantitative and qualitative research
• Distinction between quantitative and qualitative research
• But the connections between epistemological / ontological
commitments and research methods are not deterministic
• Research methods are more ‘free-floating’ than has been
• Practicality of a method needs consideration
The natural science model and qualitative
• Characterization of the natural sciences as inherently positivistic
• Problems with this:
• no agreed epistemological basis of natural sciences: realism as an alternative (Bhaskar, 1975)
• disparity between scientists’ written accounts and actual work practices (Gilbert & Mulkay, 1984)
• negative connotations of ‘positivism’ (Platt, 1981)
Quantitative research, interpretivism and
• Quantitative researchers also study the social meanings
people give to the world
• surveys and questionnaires attempt to measure attitudes or elicit
accounts of action / events
• Reports of qualitative research rarely demonstrate that
interpretative understanding has been achieved
• Quantitative content analysis can reveal patterns of
representation in mass media texts
• Quantitative and qualitative research strategies tend to
reflect different epistemological and ontological beliefs
• Some say these commitments are inevitable
• choice of method reflects assumptions about the nature of
knowledge and of social phenomena (Morgan & Smircich, 1980)
• But the dominance of mixed methods case study research
blurs the ideology
Problems with the
Four dimensions of the contrast:
1. Behaviour versus meaning;
2. Theory tested in research versus emergent from data;
3. Numbers versus words;
4. Artificial versus natural.
Behaviour versus meaning
• The distinction is sometimes drawn between a focus on behaviour and a
focus on meanings.
• However, quantitative research frequently involves the study of meanings in
the form of attitude scales etc.
• Qualitative researchers often want to interpret people’s behaviour in terms
of the norms, values, and culture of the group or community in question.
• Quantitative and qualitative researchers are typically interested both in what
people do and what they think but go about the investigation of these areas
in different ways.
Theory tested in research versus emergent
• The suggestion that theory and concepts are developed prior to
undertaking a study in quantitative research is true only up to a point.
• Quantitative research is far less driven by a hypothesis-testing strategy
than is frequently supposed, e.g. exploratory survey research.
• The suggestion that quantitative research is concerned solely with the
testing of ideas that have previously been formulated (such as
hypotheses) fails to recognize the creative work that goes into the
analysis of quantitative data and into the interpretation of findings.
Numbers versus Words
Qualitative researchers sometimes undertake limited quantification of
• to help uncover the generality of the phenomena being described
(Silverman, 1984, 1985).
• So that greater precision into estimates of frequency can be given,
using terms like ‘many’, ‘often’, and ‘some’.
Artificial versus natural
• Whereas quantitative research may be seen to give an
artificial account of how the social world operates, qualitative
research is often viewed as more naturalistic.
• However, when qualitative research is based on interviews, the
depiction ‘natural’ is possibly less applicable, because
interviews and focus groups still have to be arranged and
interviewees have to be taken away from their normal
• Atkinson and Silverman (1997) suggest the obsession with the
semi-structured interview in qualitative research leads to
reports not much better than journalism.
Developments in quantitative and qualitative
research allow each to be used to analyse the
• Qualitative analysis of quantitative data
• Quantitative analysis of qualitative data
Qualitative analysis of quantitative data
The writings of quantitative researchers can be
treated as ethnographic accounts in themselves.
Ethnostatistics (Gephart, 1988) treats statistics as
rhetoric, becoming sensitive to the ways in which
statistical arguments are deployed to bestow
credibility on research for target audiences.
Quantitative analysis of qualitative data
• ‘The fundamental contribution of the systematic analysis of
documentary accounts is that it creates an analytic link
between the in-depth accounts of professional observers and
the statistical methods of quantitative researchers’ (Hodson
• In other words, the application of quantitative methods to
qualitative research may provide a meeting ground for the
two research strategies
Quantification in qualitative research
(undertaking a search for themes in transcripts or field notes):
• The criteria employed in the identification of themes are often unclear
(Bryman and Burgess, 1994)
• One possible factor is the frequency of occurrence of certain incidents,
words, phrases, that denote a theme
• So a theme is more likely to be identified the more times the
phenomenon it denotes occurs in the course of coding
• Thus a kind of implicit quantification may be in operation that influences
the identification of themes and the elevation of some themes over
Combating anecdotalism through limited
o The publications of qualitative research are often seen as anecdotal
o Numbers can be used to give a fairly straightforward indication of the scale of the
research project or to interpret the significance of qualitative data
o Computer-assisted (or aided) qualitative data analysis software (CAQDAS)
may make qualitative research more respectable within the scientific community and
more acceptable to ‘gatekeepers’ of research, i.e., funding bodies (Weaver and
Breaking down the
The argument against multi-strategy research
• The embedded methods argument:
• research methods carry epistemological and ontological
• thus multi-strategy research is not feasible or even
• The paradigm argument:
• quantitative and qualitative research are separate,
• thus even when combined they are incompatible
Two versions of the debate
• Epistemological version
• incompatible epistemological principles of quantitative and qualitative research
• e.g. embedded methods /paradigm arguments
• Technical version
• quantitative and qualitative research strategies can be combined
• relative strengths and weaknesses of each for data collection / analysis
of approaches to mixed methods research
a) The logic of triangulation;
b) Qualitative research facilitates quantitative research;
c) Quantitative research facilitates qualitative research;
d) Filling in the gaps;
e) Static and processual features;
f) Research issues and participant’s perspectives;
g) The problem of generality;
h) Qualitative research may facilitate interpretation;
i) Studying different aspects of a phenomenon;
j) Solving a puzzle.
(a) The logic of triangulation
• Results of one method/research strategy can be cross-checked against the results of another
• e.g. Stiles (2000): impact of boards of directors on corporate strategy
• structured interviews, questionnaire survey, case studies – all provided different perspectives
• Planned or unplanned?
• What happens if results are inconsistent?
• treat one set of results as definitive
(b) Qualitative research facilitates quantitative
By providing hypotheses: an unstructured, open-ended
approach is helpful in generating hunches for testing
through experimentation or survey.
By aiding measurement: focus groups and semi-structured
interviews can provide the measurements of concepts to be
tested in quantitative research, leading to much more
appropriate specification of questions.
(c) Quantitative research facilitates
By providing a basis for representative sampling in
samples of people or companies, with
particular sets of characteristics, for indepth interviewing or case study.
(d) Filling in the gaps
• When neither research strategy can provide all the answers
• e.g. particular methods do not provide access to required information / groups of
• Quantitative and qualitative methods both compensate for the other’s weaknesses
• e.g. when ethnographers use structured interviewing or self-completion questionnaires,
because not everything of research interest is accessible through observation.
(e) Static and processual features
▪ Quantitative research can uncover regularities
▪ Qualitative research reveals social processes
▪ e.g. Zamanou and Glaser (1994) used a questionnaire survey to provide a
static picture of organizational culture before and after the intervention
of a communication programme designed to change the culture, followed
by interviews to explore perceptions of culture in the process of change.
Quantitative methods test researcher’s
Qualitative methods make participants’
meanings the center of attention;
Some research studies require both
(f) Researchers’ and
(g) The problem of generality
▪ Some quantification of findings from
qualitative research can help to uncover
the generality of phenomena
▪ Case study research often uses mixed
methods to enhance generality.
▪ Quantification can counter criticisms of
anecdotalism in qualitative studies.
(h) Qualitative research
may facilitate interpretation
Quantitative researchers constantly face
the problem of explaining the relationships
Qualitative research can discover the
presence and role of intervening variables.
(i) Studying different aspects of a phenomenon
• Quantitative research is better suited to the study of ‘macro’
phenomena (such as social mobility)
• Qualitative research is better suited to the study of ‘micro’
phenomena (such as small group interaction)
• Different phases in a research study suit one strategy more than
another, because of the different aspects studied
• Different kinds of research questions are better answered by one
strategy more than another
• Leading to choices of methods – and how they should be
interweaved – in mixed methods research
(j) Solving a puzzle
• Research outcomes can yield unexpected results, inconsistent data and puzzling surprises.
• Sometimes anticipated results fail to materialize, such that findings are inconsistent with the
• So using a second method can help to explain data (unplanned triangulation),
• Or can provide a ‘salvage operation’ as an alternative to reconstructing the hypothesis or simply
filing them away.
Hammersley’s (1996) classification
1. Triangulation: referring to the use of quantitative research to corroborate
qualitative research findings or vice versa.
2. Facilitation: arises when one research strategy is employed in order to aid
research using the other research strategy.
3. Complementarity: occurs when the two research strategies are employed in
order that different aspects of an investigation can be dovetailed.
Morgan’s (1998) classification
The priority decision: How far is a qualitative or a quantitative method the
principal data-gathering tool or do they have equal weight?
The sequence decision: Which method precedes which? In other words,
does the qualitative method precede the quantitative one or vice versa or is
the data collection associated with each method concurrent?
Morgan’s types of mixed methods in
terms of priority and sequence
Reflections on mixed methods research
• Increasingly common in business research
• research methods seen as autonomous
• softening of feminist attitudes to
• Not inherently superior to mono-method or
Indicators of quality in
mixed methods research
o Is it well designed and conducted?
o Are the methods appropriate to the research questions?
o Is there an explicit rationale for the mixture?
o Are the separate components integrated?
o Is there a detailed account of the entire research process?
o Are resources spread too thinly, or unevenly?
o Are the researchers more skilled in one
strategy than another?
Read the Case Study “Case 7e – Comparing UK and French perceptions and
expectations of online supermarket shopping”, then answer the case questions.
1 Outline the problems Daniel is likely to face by using his Marketing assignment as his pilot
2 Discuss how the distribution of a link to the Internet questionnaire using Facebook via email
might jeopardise the statistical representativeness of Daniel’s findings.
3 Identify a sampling technique that could enable Daniel to collect reliable data from which he
could make statistical inferences. Give reasons for your choice and explain the steps you would
take to select your sample.