07-02-2025
1
Business Research Methods
Prof. PraveshPadamwar
Course Instructors:
2005-2010 2011-2014
Why do we do Business Research?
Why do we do Business Research?
For the purpose of improving decision-making related to the
–identification and
–solution of problems and opportunities in business.
Business researchis the systematic and objective
–identification
–collection
–analysis
–dissemination
–and use of information
1 2
3 4
07-02-2025
2
“Re”“Search”
Knowledge Creation
Business Research Process
Step 1: Defining Business opportunities and problems
Step 2: Idea and theory development
Step 3: Generating and evaluating alternative courses of action
Step 4: Searching for information (Data collection)
Step 5: Data analysis and interpretation
Step 6: Reporting findings: Decision making
Step 7: Monitoring performance
Knowledge Creation
“Re”“Search”
Business Research
Market Research
Sales
New product development
OB HR Research
Employee retention
HR policy
Employee training
Financial & Economic Research
Economic environment
Financing (capital management) strategies
Operation Research
Supply chain
Inventory management
Manufacturing or service delivery process
Production oriented
Widely available and inexpensive products
Product oriented
Best quality, performance, features
Sales oriented
Buyers if left alone won’t buy enough
Market oriented -
Customer Centric
Find the right products for your customers, not the right customers for your products.
Selling focuses on the needs of the seller; marketing on the needs of the buyer.
Evolution of “sales” and “marketing”
5 6
7 8
07-02-2025
3
Business Research
When is business research needed?
Time constraints
Data availability
Nature of decision
Benefits versus cost
Business Research
Applied business research is conducted to address a specific
business decision for a specific firm or organization.
Basic (academic) business research is conducted without a
specific decision (solution to a particular problem) in mind that
usually does not address the needs of a specific organization. It
attempts to expand the limits of knowledge in general.
Basic research is useful in solving particular business problems.
Applied and basic research are done using scientific methods
Business research is the application of the scientific method in
searching for the truth to solve business problems.
Knowledge Creation
Maslow’s hierarchy of needs
Psychological
needs
Basic needs
Self-fulfilment needs
Theories are simple generalizations that help us better understand reality.
Hertzberg’s dual-factor theory/Two-factor theory/ Motivation-hygiene theory
Intrinsic factor
Extrinsic factor
“There is Nothing More Practical Than A Good Theory” (Kurt Lewin)
9 10
11 12
07-02-2025
4
Business Research
Godrej Mumbai
Housing facilities for Godrej employees improve employee retention.
L&T
More growth opportunities will improve employee retention.
mid-management level employees
entry-level employees
Quarterly bonuses will improve employee retention.
mid-management level employees
entry-level employees
Performance-based quarterly bonuses will improve employee retention.
mid-management level employees
entry-level employees
Fulfillment of a higher-level need will motivate an individual only when his
or her lower-level needs are fulfilled.
Fulfillment of basic needs (Extrinsic factor or hygiene factor) will not
motivate an individual.Theory of Planned Behaviour (TPB)
Intentions BehaviourBehaviour
Subjective
norm
Attitude
Behavioural
belief
Behavioural
belief
Normative
belief
Normative
belief
Perceived
behavioural
control
Resources
&
Opportunities
Resources
&
Opportunities
Theory of
Reasoned Action
(TORA)
Technology
Acceptance Model
(TAM)
SERVQUAL
Model
Theories are simple
generalizations that help us
better understand reality.
“There is Nothing More Practical Than A Good Theory” (Kurt Lewin)
Constructs in Social Science
Aconstructisatheoreticalconcept,anabstractionthatresearchersusetorepresenta
phenomenonthat'susuallynotdirectlymeasurable.
It’saconceptthatexistsnotinobjectiverealitybutasaresultofhumaninteraction.
Constructsareconsideredlatentvariablesbecausetheycannotbedirectlyobservedor
measured.
Constructscanbeconceptuallydefined.
Researchersdevelopindicatorsoritemstomeasuretheconstructbasedonthe
definitionoftheconstruct.
Constructsareconsideredthebasicunitfortheorydevelopment.
13 14
15 16
07-02-2025
5
Research Propositions and Hypotheses
Propositions
Statements explaining the logical linkageamong certain concepts (constructs and other variables)
by asserting a universal connection between concepts.
Treating employees better will make them more loyal employees.
Increasing customer value leads to higher customer satisfaction.
Hypothesis
Formal statement of an unproven propositionthat is empirically testable.
Giving employees one Friday off each month will result in lower employee turnover.
Increasing retirement benefits will reduce the intention to leave the organization.
In addition to the existing system, launching bots to handle customer service will increase
sales.
Satisfaction
Loyalty
On avg300 tubs sold
Caramel Popcorn
On avg700 tubs sold
Salted Popcorn
Cheese Popcorn
Similarity hypothesis
Regularity condition
Violation of regularity condition and similarity hypothesis
500/-Large
(100gm)
450/-Medium
(80gm)
200/-Small
(30gm)
DecoyTarget
Competitor
17 18
19 20
07-02-2025
6
Asymmetric-dominance/Attraction effect
S
M
L
500/-Large
(100gm)
450/-Medium
(80gm)
200/-Small
(30gm)
The Role of Theory in Applied Research
Role of TheoryResearch Task
Provides a conceptual foundation and understanding of the basic processes
underlying the problem situation. These processes will suggest key dependent
and independent variables.
1. Conceptualizing and
identifying key
variables
Theoretical constructs (variables) can suggest independent and dependent
variables naturally occurring in the real world.
2. Operationalizing key
variables
Causal or associative relationships suggested by the theory may indicate
whether a causal or descriptive design should be adopted.
3. Selecting a research
design
The theoretical framework may be useful in defining the population and
suggesting variables for qualifying respondents, imposing quotas, or
stratifying the population.
4. Selecting a sample
The theoretical framework (and the models, research questions, and
hypotheses based on it) guide the selection of a data analysis strategy and the
interpretation of results.
5. Analyzing and
interpreting data
The findings obtained in the research project can be interpreted in the light of
previous research and integrated with the existing
body of knowledge
.
6. Integrating findings
Academic Research
https://scholar.google.com/
Top marketingresearch journals
•Journal of Consumer Research
•Journal of Consumer Psychology
•Journal of Marketing
•Journal of Marketing Research
•Management Science
•Marketing Science
•Journal of Retailing
European Journal of Marketing
International Journal of Research in Marketing
Journal of Business Research
Journal of Consumer Behaviour
Journal of Consumer Marketing
Marketing Letters
Psychology & Marketing
Journal of Service Research
Journal of Services Marketing
Academic Research
https://scholar.google.com/
21 22
23 24
07-02-2025
7
Literature Review
Literature Review
A literature review helps in understanding existing knowledge in the context of research questions.
It helps in understanding what is knownand what is unknown.
The unknown is called the “
research gap
”
Based on what is known, we deduce expectations (propositions and hypotheses) for the research
gap.
The above helps in identifying the right research directionto progress in filling the research gap
(or getting the answers to research questions).
By getting the answer to what is unknown, we create new knowledge or contribute to the body
of knowledge.
Knowledge Creation
Literature Review-References
To acknowledge the existing knowledge (or to produce proof of our literature
review), we cite the past findings (research paper, news article, research report,
etc.) in our research report and provide the details (bibliography) in the references
section.
Common referencing styles in academic research
APA (American Psychological Association)
Harvard
IEEE
Reference manager software (automation)
Business
Research
Process
25 26
27 28
07-02-2025
8
Process of
Defining
Problem
Inadequate problem definition
is a leading cause of failure
of research projects.
A problem well-defined is a
problem half-solved.
Interviews
Focus Grp
Case studies
Economic
Market
Global
Process of
Defining
Problem
Management decision makers’ (DM)
problems ask what DM needs to do.
Should the market be segmented
differently?
Should a new product be launched?
Should the promotion budget be
increased?
Research questions entail determining
what informationis needed and how to
get it in the most feasible way.
Identifying Symptomsto
understand the situation
Identifying Problems
from Symptoms
Business Research ProblemManagement Decision
Problem
Causal research to be undertaken for
determining the reason for declining
sales.
Symptom: Declining sales.
Problem: What should be done to
increase sales?
Test market to be organized.
Sampling
Should the launch of a new product at
the national level be restricted to some
states?
Conduct an exploratory research to
determine viability of the proposed
shopping mall.
Whether to set up a shopping mall in a
city?
To determine the effectiveness of the
current advertising campaign.
Should the advertising campaign be
changed?
29 30
31 32
07-02-2025
9
Business Research Problem
Management Decision
Problem
Asks what information is needed
and how it should be obtained
Asks what the decision maker
needs to do
InformationorientedActionoriented
Focuses on the underlying causesFocuses on symptoms
Process of
Defining
Problem &
Developing
an Approach
Step 2: Approach to the
problem
Ananalyticalmodelisasetofvariables
andtheirrelationshipsdesignedto
representsomerealsystemorprocess.
Research Questions and Hypotheses
•Research questions(RQs) are refined statements of the specific components of
the problem.
•Ahypothesis(H) is an unproven statement or proposition about a factor or
phenomenon that is of interest to the researcher. Often, a hypothesis is a possible
answer to the research question.
RQ1: Is the quality of food the cause of declining sales of McDonald’s?
H1a
0
: the taste of food at present is the same as the previous year.
H1b
0
: the taste of food at McDonald’s is the same as its competitor.
H1c
0
: McDonald’s food taste is inferior to its competitors.
RQ2: Is service quality the cause of declining sales at McDonald’s?
H2a
0
: the perceived service quality at present is the same as the previous year.
H2b
0
: the perceived service quality of McDonald’s is the same as its competitor.
H2c
0
: the perceived service quality of McDonald’s is inferior to its competitor.
Decision-Making
Situations
Shallwestartabotfor
customerservice?
33 34
35 36
07-02-2025
10
Process of
Defining
Problem &
Developing
an Approach
Step 3: Research Design
Classification of Research Designs
Conclusive ResearchExploratory Research
Blank
To test specific hypotheses and
examine relationships
To provide insights and understandingObjective:
Information needed is clearly
defined.
Research process is formal and
structured.
Sample is large and representative.
Data analysis is quantitative.
Information needed is defined only
loosely.
Research process is flexible and
unstructured.
Sample is small and
nonrepresentative.
Analysis of primary data is qualitative.
Characteristics:
ConclusiveTentativeFindings:
Findings used as input into decision
making
Generallyfollowed by further
exploratory or conclusive research.
Sometimes, the decision is made in this stage.
Outcome:
Uses of Exploratory Research
•Formulate a problem or define a problem more precisely
•Identify alternative courses of action
•Develop hypotheses
•Isolate key variables and relationships for further examination
•Gain insights for developing an approach to the problem
•Establish priorities for further research
37 38
39 40
07-02-2025
11
Use of Descriptive Research
•To describe the characteristics of relevant groups, such as consumers, salespeople,
organizations, or market areas
•To estimate the percentage of units in a specified population exhibiting a certain
behavior
•To determine the perceptions of product characteristics
•To determine the degree to which marketing variables are associated
•To make specific predictions
Uses of Causal Research
•To understand which variables are the cause (independent variables) and which
variables are the effect (dependent variables) of a phenomenon
•To determine the nature of the relationship between the causal variables and the
effect to be predicted
•METHODs
1.Experiments: to prove causality
2.Correlation based (regression) analysis : to make causal inferences
CausalDescriptiveExploratoryBlank
Clearly definedPartially definedHighly ambiguous
Amount of
uncertainty in
decision
situation
Determine cause-and-
effect relationships
Describe market
characteristics or functions
Discovery of ideas and
insights
Objective:
Highly structuredstructured
Unstructured, semi-
structured
Research
approach
“Will sales double if we
offer a 20% discount”
“Who are our and
competitors’ customers”
“What features are
important to the customers”
“Sales are declining”
“What new products
customers are interested
in?”
Examples
CausalDescriptiveExploratoryBlank
Determine cause-and-
effect relationships
Describe market
characteristics or functions
Discovery of ideas and
insights
Objective:
Manipulation of one or
more independent
variables
Marked by the prior
formulation of specific
hypotheses
Flexible, versatileCharacteristics:
Measure the effect on
dependent variable(s)
Control of other
moderating variables
Preplanned and structured
design
Often the front end of total
research design
Characteristics:
Experiments
Causal inferences
•Surveys
•Secondary data
Surveys
Secondary data
•Cross-sectional
•Panel
•Time series
Qualitative research
•Conversations or
interviews
•Expert opinion
•Case studies
Secondary data
Methods:
41 42
43 44
07-02-2025
12
Process of
Defining
Problem &
Developing
an Approach
Step 3: Research Design
Research Design
•A research design is a framework orblueprint for conducting the
research project.
•It details the proceduresnecessary for obtaining the information
needed to structure or solve research problems.
Components of a Research Design
•Define the information needed.
•Design the exploratory, descriptive, and/or causal phases of the research.
•Specify the measurement and scaling procedures.
•Prepare and Pretest(pilot) a questionnaire (interviewing form) or an
appropriate form for data collection.
•Specify the sampling process and sample size.
•Develop a plan for data analysis.
Business
Research
Process
Step 2: Define Business opportunities and problems
Step 3: Idea and theory development
Step 4: Generating and evaluating alternative courses of action
Step 7: Searching for information (Data collection)
Step 8: Data analysis and interpretation
Step 9: Reporting findings: Decision making
Step 10: Monitoring performance
Exploratory,
Descriptive, Causal.
Step 1: Understand the situation (based on Symptoms & Trends)
Step 5: Developing an Approach to the Problem
Step 6: Formulating a Research Design
Questionnaire
design etc.
Knowledge Creation
45 46
47 48
07-02-2025
13
Business Research
Business Research is the systematicand objective method of
•identification
•collection
•analysis
•dissemination
•and use of information
For the purpose of improving decision-making related to the
identificationand solution
of problemsand opportunitiesin business.
Secondary Data in Research
Secondary Vs Primary Data
Primary dataare originated by a researcher for the specific purpose
of addressing the problem at hand.
Secondary dataare data that have already been collected for purposes
other than the problem at hand.
Is census primary or secondary data?
How is CENSUS data collected?
Secondary DataPrimary DataBlank
For other problemsFor the problem at handCollection purpose
Rapid and easyVery involvedCollection process
Relatively lowHighCollection COST
ShortLongCollection TIME
Secondary data analysis
Role of
Secondary Data
in Research
49 50
51 52
07-02-2025
14
Scanner panel data
Euromonitor’s clients
McKinsey
IKEA
Mondelez
Unilever
Pepsico
Mastercard
Visa
J&J
BCG
Bain &Company
PWC
EY
Accenture
Qualitative Research
Qualitative Research Methods in MR
Focus groups
•Focus groups is a frequently used qualitative research method in MR.
In-depth (unstructured/semi-structured) interviews of individuals.
•Useful in advertisement design, new product development
Projective Techniques
Observation
Case study
Ethnography
Netnography
53 54
55 56
07-02-2025
15
Qualitative Research Methods
Whenever a new business research problem is being addressed, quantitative research should be
preceded by appropriate qualitative research.
The findings of qualitative research are misusedwhen they are regarded as conclusive and are used
to make generalizations about the population of interest.
Focus Groups
6 to 12Group size
Homogeneous; respondents prescreenedGroup composition
Relaxed, informal atmospherePhysical setting
Zoom, Google Meet, MS teamOnline setting
1 to 3 hoursTime duration
Audio and videoRecording
Observational, interpersonal, and communication
skills of the moderator.
Kindness with firmness.
Moderator
In depth interviews of individuals
Why ‘In depth interviews of individuals’?
Focus groups generate innovative ideas because of group synergy and
dynamics. However, peer pressure/group influence can bias the response.
Focus groups provide broad insights. However, it can’t uncover greater
depth and hidden motives.
Focus groups are fasteras six or more respondents can participate together.
However, Sensitive topics can’t be discussed in a group.
Professionals and seniorrespondents may not agree to participate in FG.
In depth interviews of individuals
Interview (Probing) techniques
•Laddering
•Hidden Issue Questioning
•Symbolic Analysis
57 58
59 60
07-02-2025
16
'Laddering' an interview (Probing) technique
•It is used in order to find subconscious motives (or product elements personal values for end user).
•Focus on a certain product or service and its attributes and probe towards ‘WHY’questions.
•What would you prefer, Innova or XUV 700?
•Why do you prefer that?
•Response:comfort, space, reliability……
•Why is comfort (or space, reliability….) important to
you?
•Response:long distance travel
•Why do you travel long distances in your personal car?
•Response:freedom, flexibility, family, cost, hygiene
•Why is freedom (or flexibility, family ….) important to
you?
•Response:………
•Interviewer: "Why x?"
•Subject: "Because z"
•Interviewer: "Why z?"
•Subject: "Because b"
•Interviewer: "Why b?"
Product
characteristic
User
characteristic
Product
benefits
Motivation
Product
Attributes
Product
characteristic
Dependability
(12)
Self Esteem (23)
Acceptability
(4)
Location (8)Status (6)Credit Limit (5)Availability (9)
Support Community
(20)
Credit History
(17)
Confidence (21)Independence
(16)
Security (19)
Power (18)
Peace of Mind (25)
Independence (16)
Attribute Value Mapping for credit card
User
characteristic
Product
benefits
Motivation
Product
Attributes
Attribute Value Mapping
Attribute Value Mapping is an exercise that seeks to establish links between a
product's attributes and the needsof the target market.
Needs are expressed as benefitsthat ladder up to more abstract values and
emotions that are satisfied when a consumer uses the product.
'Hidden Issue Questioning' an interview (Probing) technique
If you suddenly inherited 100 crore rupees and didn't have to work, how would
you spend your time? How would you spend your money?
What was the happiest time in your life? Why? The unhappiest time? Why?
Just for fun, if you could live in any time in history, when would that be? Why?
61 62
63 64
07-02-2025
17
'Hidden Issue Questioning' an interview (Probing) technique
Why ‘Hidden Issue Questioning’?
In a direct questioning technique (e.g., laddering), there is no certainty that
respondents are ableor willingto give true answers.
The response may be biasedas respondents want to appear to be rational, intelligent,
and respectable.
Most of the findings from direct questioning are standard comments about the
product/service. It doesn’t provide much information here about buyer motivesthat
is very inspiring.
It focuses on deeply felt personal concerns.
Focus groups and Laddering (especially FGs) focus on socially shared values.
'Symbolic Analysis' an interview (Probing) technique
What would it be like if you could no longer use this product? What would
you use in its place?
What is someone like who never uses this product?
Suppose this product was taken away from a large number of people. How
would it affect them? How would their lives be different?
List opposite types of products from the one being studied and indicate how
they are opposites.
'Symbolic Analysis' an interview (Probing) technique
Why ‘Symbolic Analysis’?
To identify novelproduct meaningsand ideas.
Projective Techniques
In projective techniques, respondents are asked to interpret an object or the behavior of others.
In interpreting an object or the behavior of others, respondents indirectly project their own
motivations, beliefs, attitudes, or feelings into the situation.
Deeply held attitudes and motivations are often not verbalized by respondents when questioned directly. Indeed,
respondents may not even be aware that they hold these particular attitudes or may feel that their motivations reflect
badly on them. Projective techniques allow respondents to project their subjective or true opinions and beliefs onto
other people or even objects. The respondent's real feelings are then inferred from what s/he says about others.
65 66
67 68
07-02-2025
18
Projective Techniques
word association
Villages: Serene, Conservative, Friendly, Reliable
Cities: Rushed, Liberal, Modern
Completion
Fill in the blank.
Construction
Cartoon
Expressive
Role playing
Comparison of Focus Groups, in-depth interviews, and Projective Techniques
Projective
TechniquesDepth InterviewsFocus GroupsCriteria
Relatively lowRelatively
medium
Relatively highDegree of structure
MediumHighLowProbing of individual respondents
Low to highRelatively highRelatively mediumModerator bias
Relatively highRelatively
medium
Relatively lowInterpretation bias
HighMedium to highLowUncovering subconscious
information
LowMediumHighDiscovering innovative information
HighMediumLowObtaining sensitive information
YesTo a limited extentNoInvolve unusual behavior/questioning
Somewhat usefulUsefulHighly usefulOverall usefulness in Marketing
Research
Case study
•Case studies involve an intensive examination of a few selected cases of the
phenomenon of interest.
The cases could be firms, websites, stores, consumers, etc.
•The data are obtained from the following sources:
Company and external secondary sources
Unstructured interviews and Focus Groups with people knowledgeable about
the phenomenon of interest.
Ethnography
Anthropology + Culture (Ethnicity)
69 70
71 72
07-02-2025
19
Ethnography
Anthropology + Culture (Ethnicity)
•Study from the point of view of the subject.
Subject’s behavior in the given social situation is examined through observations.
Also, subject’s own interpretation of above behavior in the group (society) is
examined.
In-depth interviews
Observations
Focus group
Ethnography Process
Planning
Objective, research question, target sample
Entrée
Be a part of the community, get accepted in the community.
Data Collection
Observational notes, interviews.
Analysis
Reporting
Research Ethics
Ethnography in Marketing Research
https://www.youtube.com/watch?v=nV0jY5VgymI
Ethnography in Marketing Research
Knowing consumer culture provide insights about…
Whypeople buy (needs)
Whyconsumer choose us (Competition)
Howpeople like us (Brand perception)
Whoconsumers are (Segments)
Howpeople respond to our ads (ROI)
73 74
75 76
07-02-2025
20
Ethnography
WhyEthnography
Naturalistic and Unobtrusive.
Multi method –higher validity.
Netnography
Ethnography in OnlineCommunities.
It provides information on the symbolism, meanings, and consumption patterns.
Netnography
https://www.youtube.com/playlist?list=PLFxTrxIbBo-piqlzHYt2PrW6uwbcowe_c
NetnographyProcess
Planning
Objective, research question
Identify relevant online communities.
Entrée
Learn about forums, groups, and individual participants in online communities.
Be a part of the community, get accepted in the community. Or just be an observer.
Data Collection
Identify informational and on topic messages and Inscribe or Just copy paste.
Analysis
Reporting
77 78
79 80
07-02-2025
21
Netnography
Why
Netnography
Faster, Simpler, and Less Expensive.
It does not require considerable skill and substantial investments of researcher
resources.
Because ethnography involves in person researcher participant observation, it is
intentional and unavoidably intrusive method.
Netnographyis unobtrusive observation of naturally situated consumer behavior.
Qualitative Data Analysis
•In Big data analysis, the data is staticallyanalyzed. Thus, it focuses on Precision.
•In contrast, the Manual coding of qualitative data focuses more on Meaningthan on Precision.
We dive deeper into the observed data (conversations, recorded observation of behavior, etc.) to uncover the
meanings.
We don’t focus on how many people repeat something. We focus on who, how, and why something is said or
observed.
The inferred meaning of one case (interview, company, focus group, focus group member), that is, in
contrast to all other cases, is given a lot of importance in qualitative research (with manual coding). Usually,
the same leads to the exploration of novel findings.
Qualitative Content Analysis
Searching out of underlying
themes
and sub-themesin the collected data
The processes through which the themes are extracted are usually left implicit
Themes and sub-themes keep evolvingin the analysis process
•The above process of thematic analysis also called “Coding”
You assign labels to phrases that represent important (and recurring) themes.
These labels can be words, phrases, or numbers.
Qualitative Data Analysis Process
1.Managing and organizing the data
Labeling of data for each case (participants, company, focus group, etc.)
2.Reading and Memoingemerging ideas
Inductive coding
•Tagphrases of the data using different colors.
•Each color-coded phrase is to be given certain intuitive headings.
•These headings (codes) are usually described in one to four words.
•Use the “comment” tool of MS Word to document the above codes
3.Describe and classify codes into themes
Classify related codes into a theme.
4.Developing and assessing interpretations
Analyze the data of each theme to make some logical interpretations.
5.Presentation of qualitative data analysis
Thick DescriptionsCodesTheme
“copy and paste some of the selected exact phrases from the raw data”Write all the codes pertaining to the respective theme.Theme 1
Theme 2
81 82
83 84
07-02-2025
22
Qualitative Data Analysis Process
Inductive Coding
1.Break your qualitative dataset into smaller samples.
2.Read a sample of the data.
3.Create codes that will cover the sample.
4.Reread the sample and apply the codes.
5.Read a new sample of data, applying the codes you created for the first sample.
6.Note where codes don’t match or where you need additional codes.
7.Create new codes based on the second sample.
8.Go back and recode all responses again.
9.Repeat from step 5 until you’ve coded all of your data.
The code should be genericenough to apply to multiple comments, but specificenough to be useful in your analysis.
Try to create codes that contrast with each other to track both the positiveand negativeelements of a topic separately.
Strike a balance between too much and too little information.
Qualitative Data Analysis Software
https://www.maxqda.com/
https://getthematic.com/
https://www.qsrinternational.com/nvivo-qualitative-data-analysis-software/home
•Software can expeditemanual content analysis process.
•Software uses ML, AI, and natural language processing (NLP).
•Manually coding is prone to the coder’s cognitive/behavioral biases.
•Whyand whento go for manual(vs automated) qualitative data analysis?
Reliability and Validity of Research
Reliability
and
Validity of
Research
85 86
87 88
07-02-2025
23
Reliability and Validity of Research
Validity
“Accuracy”
“Are we measuring what we think we are?”
“The degree to which a test measures what it is intended to measure”
Reliability
“An ability to measure consistently”
“Reproducibility of the measurements … stability”
Reliabilityin Qualitativeresearch
Use multiple coders
Intercoder agreement
Multiple researchers analyzing the same data independently can check
individual bias and variance in data interpretation.
Follow data collection protocol
The data collectorsshould be aware about the purpose of the study and well
trained about the data collection procedure.
Reliabilityin qualitative research is not as pressing an issue as validity, because
replication is rarely the goal of qualitative research.
Validityin Qualitativeresearch
Triangulationof data sources and methods.
Combining methods and data sources (i.e., triangulation) can minimize the intrinsic bias that
comes from single-methods and single-observer.
The strengths of one method are assumed to compensate for the weaknesses of another.
If the same trends and themes emerge from different participant groups and data collection
methods, the validity of the findings is substantially increased.
Brainstorming specific questions to be included can reduce individual bias.
The findings should be Intuitive and Supported by theory/past findings.
Inductive research and deductive research
Inductive research and deductive research are two different approaches to research that use different methods and reasoning processes.
Deductive researchInductive research
Starts with a theory, develops hypotheses, and
then collects and analyzes data to test those
hypotheses
Starts with observations, looks for patterns, and
then theorizes about those patterns
Uses quantitative methodsUses qualitative analysis, such as textual or visual
analysis
Tests and confirms a theory or hypothesisIdentifies new connections and explanations that
can lead to new theories and hypotheses
Examine if employee retention can improve the
bottom line.
Studying customer preferences for a new product
to discover unexpected patterns
89 90
91 92
07-02-2025
24
Quantitative Research
Advantages and Disadvantages of Quantitative (vs Qualitative) Studies
Resources
time&money
Competencyofresearcher
Accuracyoffindings
samplesize
biasesofsubjectsandresearchers
Dataanalysis
Amountofinformationgathered
Qualitative Versus Quantitative Research
Quantitative ResearchQualitative ResearchBlank
To quantify the data and
generalize the results from the
sample to the population of
interest
To gain a qualitative
understanding of the underlying
reasons and motivations
Objective
Large number of representative
cases
Small number of
nonrepresentative cases
Sample
StructuredUnstructured/ Semi-structuredData collection
StatisticalNonstatisticalData analysis
Recommend a final course of
action
Develop an initial understandingOutcome
Statedversus RevealedPreferences
Revealedpreference
Realdata
Scannerpaneldata
CensusData
DemographicCharacteristics
HousingCharacteristics
EconomicCharacteristics
SocialCharacteristics
Dataarecollectedforeachunitofthepopulation
93 94
95 96
07-02-2025
25
Measurement and Scaling
Measurementand Scaling
Measurement means assigning numbersor other symbolsto characteristicsof
objectsaccording to certain pre-specified rules.
Scale Characteristics
1.Description
•Unique labels (or descriptors) to designate each value of the scale.
2.Order
•Relative sizes or positions of the descriptors.
3.Distance
•Absolute differences between the descriptorsare known and may be expressed in units.
4.Origin
•The scale has a fixed true zero point.
Scaling involves creating a continuum upon which measured objects are located.
Amount of information
F=32+C*9/5
K=273.15+C
Primary Scales of Measurement
Amount of information
97 98
99