Kwame Nkrumah University of

Science & Technology, Kumasi, Ghana

Business Research Methods

Research Design

Presenter’s Name here

Prof. Nathaniel Boso KNUST School of Business, Kumasi

RECOGNIZING THE TYPES AND PURPOSE OF
RESEARCH AND CHOICE OF DESIGN

The choice of research design is informed by the purpose of the

research.

Research can be designed to fulfil either:

an exploratory,
A descriptive,
An explanatory (Causal relationship) or an evaluative purpose, or
some combination of these.
 EXPLORATORY RESEARCH

Conducted to clarify ambiguous situations or discover ideas that may be potential business
opportunities.
Initial research conducted to clarify and define the nature of a problem.
Does not provide conclusive evidence
Subsequent research expected
Thus, the purpose of exploratory study is 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’.
 DESCRIPTIVE RESEARCH
Describes characteristics of objects, people, groups, organizations, or environments.
Addresses who, what, when, where, why, and how questions.
Considerable understanding of the nature of the problem exists.
Does not provide direct evidence of causality.
Diagnostic analysis
Seeks to diagnose reasons for market outcomes and focuses specifically on the beliefs and feelings
consumers have about and toward competing products.
Thus, the purpose of descriptive research is to gain an accurate profile of events, persons or
situations.
’.
Examples
The average Weight Watchers’ customer
Is a female about 40 years old
Has a household income of about $50,000
Has at least some college education
Is trying to juggle children and a job
Characteristics of leaders
Empathetic
Resourceful
Ability to delegate
CAUSAL RESEARCH
• Research conducted to identify cause and effect relationships
(inferences).
• Evidence of causality:
– Temporal sequence—the appropriate causal order of events.
– Concomitant variation—two phenomena vary together.
– Nonspurious association—an absence of alternative plausible explanations
(false and not what it appears to be).
The purpose is to establish causal relationships between variables.
 EVALUATIVE RESEARCH
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’.
METHODOLOGICAL CHOICE: THE USE OF A QUANTITATIVE,
QUALITATIVE OR MIXED METHODS RESEARCH DESIGN
 METHODOLOGICAL CHOICE: THE USE OF A QUANTITATIVE,
QUALITATIVE OR MIXED METHODS RESEARCH DESIGN

Qualitative Research: is primarily exploratory research. It is used to gain an understanding of

underlying reasons, opinions, and motivations. It provides insights into the problem or helps to
develop ideas or hypotheses for potential quantitative research.
Thus, research whose findings are not subject to quantification or quantitative analysis. Its research
conclusions are not based on precisely, measurable statistics but on more subjective observations and
analysis.
In practice, much qualitative research also uses an abductive approach to theory development where
inductive inferences are developed and deductive ones are tested iteratively throughout the research.

Qualitative research is more for depth of knowledge about a phenomenon and not breadth, and quantitative
is just the opposite.
Quantitative Research Method

Quantitative Research: is a formal, objective, systematic process in which numerical data

are used to obtain information about the world.

Research that uses mathematical (statistical) analytical procedures. Typically research analysis is
done using measurable and numeric standards to make sense of objective reality.

This research method is used: to describe variables; to examine relationships among

variables.
MIXED METHODS
Mixed methods research is the branch of multiple methods research that integrates the
use of quantitative and qualitative data collection techniques and analytical procedures
in the same research project.
Approach to Theory/Research Approach

This includes:
Deductive: testing existing theory, or testing hypothesis

Inductive: developing new theory

Abductive: modification and subsequent testing of an

existing theory
Deductive approach
It involves :
Putting forward a tentative idea, a premise, a hypothesis or set of hypotheses to form a theory
Examining the premises and the logic of the argument that produced them, comparing this argument with
existing theories to see if it offers an advance in understanding
Testing the premises by collecting appropriate data to measure the concepts or variables and analysing them.
If the results of the analysis are not consistent with the premises (the tests fail!), the theory is false and must
either be rejected or modified and the process restarted.
If the results of the analysis are consistent with the premises then the theory is corroborated
 INDUCTION
An alternative approach to developing theory on retail store employee
absenteeism would be to start by interviewing a sample of the employees
and their line managers about the experience of working at the store.
The purpose here would be to get a feel of what was going on, so as to
understand better the nature of the problem.
Your task then would be to make sense of the interview data you collected
through your analysis.

The result of this analysis would be the formulation of a theory, often

expressed as a conceptual framework.
 ABDUCTION
Instead of moving from theory to data (as in deduction)
or data to theory (as in induction), an abductive approach
moves back and forth, in effect combining deduction and
induction (Suddaby 2006).
 Research Designs
o Quantitative methodology – for descriptive and explanatory studies
o Case study: single vs multiple | holistic vs embedded
o Survey: cross-sectional vs longitudinal
o Experiment: laboratory vs natural/field | Independent measures/between
vs Repeated measures/within-subjects design
o Archival

o Qualitative methodology – for exploratory studies

o Case study
o Archival research
o Action research
o Grounded theory
o Ethnography
o Narrative enquiry
 UNIT OF ANALYSIS (1/2)
A unit of analysis is the entity that you wish to be able to say something about at the end of your study, probably
what you’d consider to be the main focus of your study.
Your unit of analysis is the “who” or the “what” that you are analyzing for your study.
Your unit of analysis could be an individual student, a group, or even an entire program
Always know your unit of analysis!

Unit of analysis
• “…defines boundaries of the study,
• determines what is in and what is not,…
• enables researchers to clearly identify prospective key respondents.”

“Failing to specify a unit of analysis that is consistent with the research question will
compromise the alignment of the various aspects of the research process and can lead to
spurious results.”

(Krause et al. 2018, p. 46)

 UNIT OF ANALYSIS (2/2)
The level at which the study's central concepts (normally, the
dependent variable) conceptualized and analyzed

Examples:
o Individuals
o Teams
o Business units or processes or departments
o Organizations
o Relationships
o Supply chains
o Societies/communities
o Countries
o Products/services

• UoA determines the study population/sample (size)

• The study inferences and conclusions are made the UoA
 STUDY POPULATION | EMPIRICAL
SETTING (1/2)
The target population vs Accessible population
The target population is who the researcher wants to study.
Accessible population is who the researcher can actually study.

Resource restrictions such as budget constraints, geographical

location and time contribute to the need for a limited research
population.
 STUDY POPULATION | EMPIRICAL
SETTING (1/2)
• Target Population – Clearly defined cases or elements of interest in a
research.

• Know your unit of analysis, know your population

• The population has to be explained or described in terms of its salient

characteristics

• The population should be appropriate for the research question

• The researcher should argue or demonstrate why the chosen population
is suitable

• Data on the key characteristics of the population (demographics should be

collected and analyzed to show the kind of population being used to reach
certain conclusions in the study.
 STUDY POPULATION | EMPIRICAL
SETTING (1/2)
• Target Population – Clearly defined cases or elements of interest in a
research.

• Know your unit of analysis, know your population

• The population has to be explained or described in terms of its salient

characteristics

• The population should be appropriate for the research question

• The researcher should argue or demonstrate why the chosen population
is suitable

• Data on the key characteristics of the population (demographics should be

collected and analyzed to show the kind of population being used to reach
certain conclusions in the study.
STUDY POPULATION | EMPIRICAL
SETTING (1/2
Empirical setting
• Context in which evidence is sought for
• Or context in which the study population is embedded
• Can be geographical, product, industry,
organizational, etc.

• Like the population, this should be explained and

strongly justified.

• You can weave the target population and the empirical

setting together
 SAMPLING FRAME
• Logically arranged completed list of the elements within a
population from which you can sample.

• Find out if it’s available and accessible

• Sometimes, you can create one by drawing on different databases
and appropriate sample inclusion criteria
• Studies from developing economies where database of firms or
individuals are hard-to-obtain normally do this. See
https://www.ghanayello.com/

• Lack of sampling frame makes the application of probability

sampling techniques almost impossible
 Sample and Sampling
• Sample – A fraction of the population to be studied
• The sample should be typical of the population, in terms of the key
characteristics (i.e. representative)

• Probability sampling
• Simple random
• Systematic random
• Stratified random
• Cluster
• Non-probability sampling
• Quota
• Purposive
• Snowballing
• Self-selection

Justify your choice and align it with prior related research!

 Sample Size
• There is no consensus on suitable sample size for qualitative or quantitative
studies
• Always consult what prior related studies normally use or report!

• The larger, the better; too large can be problematic

• Caveat: the sample size should be representative of the population to allow

for inferences!

For quantitative studies, see discussions in Hair J.F.J., Black, C. W., Babin,
J.B., Anderson, E.R. 2014. Multivariate Data Analysis, seven ed. Pearson
Education Ltd, Harlow.
 (Key) Respondent/Informants

• Who should provide what data for the study, and why?
• Align your choices with prior related studies!

• Note that sometimes, the respondents will be different from the unit of
analysis.

• Where the respondents are not the same as the unit of analysis, key
informants – people who are experienced and have extensive knowledge about
the unit of analysis and issues being studied – should be used.
• Single key informants
• Multiple key informants

See Krause, Daniel, Davide Luzzini, and Benn Lawson. "Building the case for a single key informant in
supply chain management survey research." Journal of Supply Chain Management 54.1 (2018): 42-50.
 Sources of Data
• Clearly explain and justify the type of data you’re using to
address your research objectives/questions

• If possible, carefully use multiple sources of data to:

• enhance validity and reliability of results
• reduce common method bias
 SOURCES OF DATA
• Primary data – collected for the present study using

• Questionnaires for descriptive and explanatory studies

• Interviews for qual studies

• Focus group discussions for qual studies

• Structured and unstructured observations for quant and qual

studies, respectively.

• Literature surveys – systematic literature review and

metanalysis studies
 SOURCES OF DATA
• Secondary data – existing data useful for addressing the present
study’s objectives or questions.

• Don’t confuse this with source of literature!

• Note that secondary data is built via primary means such as

interviews, questionnaires, observations, etc.

• Talk to senior scholars in your field to help you with where and
how to obtain relevant and authoritative secondary data
• See Ellram, L. M., & Tate, W. L. (2016). The use of secondary
data in purchasing and supply management (P/SM) research.
Journal of Purchasing and Supply Management, 22(4), 250-254.
 MEASUREMENT OF
VARIABLES/CONSTRUCT
(OPERATIONALIZATION)
• Think carefully about how you’re going to measure the concepts/variables in your
research to address your research questions

• Detail and justify the sources of the measures and the measurement or
instrument development procedures
• Follow how it has been presented (see the methodology section)

• Ideally, survey the measurement indicators for the study concepts from key past
studies

• In situations where existing measures don’t exist, follow recommended

procedures for developing and validating new measures to generate your own
measures:
 Define each concept and make sure the measures you’re using to capture the concepts are
consistent with their operational definitions (face/content validity)