lOMoARcPSD|480616

Marketing Research Lecture Notes

Marketing Research (University of Technology Sydney)

StuDocu is not sponsored or endorsed by any college or university

Downloaded by An Nguyen (annayye_@hotmail.com)
 lOMoARcPSD|480616

Marketing Research Lecture Notes. 04/20/2020

Lecture 1: Marketing Research

Value of watching shoppers?

 improve the customer experience
 increase customer satisfaction
 increase business performance

Why watch shoppers

Anticipate shoppers needs and desires
Discover the points of engagement and friction in shopping process
Improve the retail experience and measure how shoppers respond
= SHOPPABILITY
How can shoppers be studied ?
- consumer tracking – via technology and software

Shoppable stores…
 Clearly communicate the benefits & value of brands
 Provide a convenient and enjoyable shopping experience
 Satisfy consumers salient & latent needs


Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

What are possible concerns re watching shoppers?

- Privacy concerns

What is Market Research

Market research is one of the main factors used in maintaining

competitiveness over competitors. Market research provides important
information which helps to identify and analyse the needs of the market,
the market size and the competition. Market-research techniques
encompass both qualitative techniques such as focus groups, in-depth
interviews, and ethnography, as well as quantitative techniques such as
customer surveys, and analysis of secondary data

Marketing research is the business function that links an

organisation to its markets through the generation of information that
facilitates optimal solutions to decision problems. • Principal tasks
involved with conducting marketing research – establishing the
boundaries of the research – designing the research – executing the
research – communicating the results of the research

Decision problems
Decision problem is a situation in which management has to decide
on a course of action that will help to accomplish a specific objective

Marketing research is the function for generating interpretable

information that is accurate, relevant and timely to solve decision
problems

Decision problem instances

 In many instances, a decision problem is a weakness or threat,
or a strength or opportunity Decision problem instances

 Strength e.g. organisations’ capability to attract clientele with a

willingness to pay top prices for product quality
 Weakness e.g. ineffective marketing mix or mismatch of product,
price, promotion, distribution
 Opportunity e.g. competitor has decided to exit the market

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Threat e.g. changing laws, increases in direct competition,

increased consumer demand

Decision problems comes in disguise

 What often appears to be a problem could actually just be a
symptom of the true problem
o Example:
 Decline in sales volume that follows a 10% decrease
in the unit price of a certain product is NOT the
problem, but a symptom of poor pricing policy and
associated analysis
 Poor pricing policy is the real problem that requires
decision-making

Deciding on marketing research

 Upon identification of the decision problem, need to determine
the scope for marketing research
 Can the marketing research information tell the decision
maker something not already known?
 Will the marketing research information provide significant
insights?
 How valuable is the marketing research information once
collected?
 Further marketing research should be conducted only when the
expected value of the information to be obtained exceeds the
total cost of conducting the research

Growing complexity of marketing research

 Digital technologies bring a great deal of opportunity and
challenges for conducting marketing research
 Current variety of available tools and techniques makes choosing
a method for a particular research project increasingly
challenging
 Companies are choosing hybrid research techniques, involving
multiple research methods, to overcome the weaknesses
inherent in single methodologies

Transforming data into information Data

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Data is analysed to provide decision-makers with useable

information
 Data
o Primary/Secondary
o Words, numbers or observations collected through
research
 Data structure
o Consolidated and structured
o Tables or figures
 Information
o Managerial interpretations
o Story telling Data is analysed to provide decision-makers
with useable information

Marketing research phases

Step 1: Determine the scope for marketing research
Step 2: Select the research method
Step 3: Collect and prepare the data
Step 4: Analyse the data
Step 5: Transform the results into information

Scope of marketing research

 Determining the scope for marketing research consists of four
interrelated tasks
o 1. Defining the decision problem

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o 2. Specifying the research question

o 3. Defining the research objective
o 4. Evaluating the likely benefit of the expected information

Lecture 2: Decision problems, research

questions, research objectives and information

value & primary data or secondary data: A Case

for the Latter

Growing complexity around marketing research and making

marketing decisions.
 Technological advances and growing internet usage driving
developments in marketing research
 Growing emphasis on the collection, analysis and interpretation
of existing data
 Widespread expansion of firms into global markets opening up
new cultural, social and changing market considerations
 Increased use of gatekeeper technologies

Marketing research process

 Development and successful promotion of goods and services
involves
o Understanding consumer decisions
o Careful planning through a sound marketing research
process
 Marketing research planning involves
o Identifying a business decision problem
o Determining the scope of marketing research

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Defining the decision problem

 Decision problem is a situation in which management has to
decide on which course of action to take. –
o What should we do now? Which is the best option?

 Inadequate decision problem is the leading cause of failure of

marketing research projects
o – ‘The truly serious mistakes are made not as a result of
wrong answers but because of asking the wrong question

Defining the decision problem

Defining the decision problem includes five interrelated activities
 1. Determine the decision-maker’s purpose for the researches
 2. Understand the complete problem situation
 3. Identify measurable symptoms
 4. Determine the unit of analysis
 5. Determine the relevant variables or constructs

Why Churn is a Bigger Problem as You Grow

1. Why should a decision-maker worry about churn?
 Churn absolutely destroys everything
 For every customer that churns you have acquire a customer to
make up for that customer adjourned and then also acquire more
customers if you want any chances of growth
 Acquisitions are harder

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

2. What are important variables or constructs that help

predict and address churn
 active cancellations – product and customer research why
customers are churning
 delinquencies – always have this to make sure things like
o e.g. failed credit cards aren’t making the companies growth
stall

Specifying the research question

 Redefine and reformulate the decision problem into research
question(s)
o Decision problems are broken down into an overarching
research question, or a series of specific research questions
o Research questions are those specific when, where, who,
why, what and how statements about the problem areas
that the research will attempt to investigate
o Research questions have to be scientific and measurable

Defining the research objective

 A blueprint of the research project’s activities
 Precise statements of what the research project will achieve
 Specification of information required to assist in management’s
decision-making capabilities
 Allows to document concise, measurable and realistic events
 Some fundamental questions in defining research objectives
o Can complete data be collected at all?
o Can the information tell me something I don’t already
know?
o Will the information provide significant insights?

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o What benefits will be delivered from this information?

Benefits of the expected information

 Need for information
o Can the decision-making problem be resolved without any
further research effort?
o Can the research question(s) be answered immediately
(without collecting data)?
 Nature of the decision
o Both strategic and tactical decisions are critical to a
company’s operations and bottom-line profitability
objectives
o Does the problem situation have strategic or tactical
importance?
 Availability of data
o Does adequate information for addressing the defined
decision problem already exist?
o Does new data need to be collected?
o No need to collect new data, if company and external data
is available, or can be accessed or purchased from other
companies
 Advances in technology and cross-functional sharing
of information provides great amount of operation
data (e.g. sales, costs and profitability by products,
brands, sales region, customer groups
 Time constraints
o Decision-makers may need information in real time but, in
many cases, systematic research that is required to deliver
high-quality information is time-consuming
o Is there enough time to conduct the research?
 Resource requirements
o Availability of marketing resources (e.g. money, staff,
skills, facilities) is a key consideration
o Is money budgeted for formalised research?
 Cost versus benefits

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o Marketing research should be conducted only when the

expected value of the information to be obtained exceeds
the cost of obtaining it
 Does the benefits of having the information outweigh
the costs of gathering the information?
o Costs of doing marketing research can be estimated with
some certainty, and mostly objective in nature
o Predetermining the managerial value of the expected
information remains subjective in nature

Should you conduct the research?

 If conducting the research may give competitors the opportunity
to formulate competitive responses
 If research findings may not be implemented (affordability, big
change, staffing, etc.)
 If research design does not represent reality
 If critical variables of the study cannot be properly defined or
measured
 If research is politically motivated

Marketing research data

 Primary data is originated by a researcher for the specific
purpose of addressing the problem at hand
 Secondary data has already been collected for purposes other
than the problem at hand

Secondary data research tasks

 Secondary data often is the starting point in defining the
research that needs to be conducted.
o Provide historical background and reveal existing
information
o Analyse existing ‘growing’ and ‘stored’ data
 Secondary data is historical in nature and already assembled or
published.

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Secondary data is available in many different forms

o Examples include existing research, data tables, full text,
summary, statistics, broadcast video streams (TV ads or
news reports), online and offline databases.
 The researcher determines whether useful secondary data
already exists, the relevance of the data and how to obtain the
data

Types of secondary data

 Internal secondary data is data collected by a company for
business purposes or marketing activity reports on customer
knowledge. Internal secondary data collection plays a significant
support role for
o sales presentations
o decision-making functions
o cases where documentation for necessary primary
research activities is required.
 External secondary data consists of data collected by outside
agencies such as the government, trade associations, reports,
industry whitepapers, magazines, audits, consumer panels and
marketing research firms

Internal secondary data sources

 Internal data can be used to analyse:
o product performance
o customer satisfaction
o distribution effectiveness
o target market strategies
 Internal data also is useful for planning:
 new-product introductions
 product deletions
 promotional strategies

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 competitive intelligence
 customer service tactics

Why we buy - supermarkets

 layout of the supermarket – Cafes and fresh food dining available
before doing grocery shopping

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Supermarkets want us to stay

 Mellow music in supermarkets - slow down the space
 Lighting relaxes customers – cutting down how many times you
blink
 Produce mazes making it harder for customers to get to the
items they need
 2/3 items are impulsive purchases
 Featured displays
 Expiration dates on food items
 integrating merchandising
 Samples - impulse buying – 90% of pupil purchase an item if
they try a sample
 Coloured packages – red and orange, blue and green

External secondary data

Sources include:
 published data in periodicals, directories or indexes
 data compiled by an outside (syndicated or commercial) agency
that can be acquired on an as-needed basis for a nominal fee
 data contained in online databases or available through
computer-facilitating agencies or vendors
The major challenge associated with external data sources lies in
finding and securing the appropriate source for extracting the data

Sources of external secondary data

 Government documents
o ABS reports and census data, CIA factbook

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Australian and New Zealand Standard Industrial Classification

(ANZSIC) codes for compilation and analysis of industry statistics
 Single source data
o A large secondary data base which is collected from a
single source, i.e. a single respondent.
o The Roy Morgan Research Centre interviews 50 000+
people annually on issues such as demographics, media
habits, finance, tourism.
 Syndicated sources
o Companies that collect and sell common pools of data (i.e.
market share, ad effectiveness, sales tracking) of known
commercial value designed to serve a number of clients
 Neilson Reports and Studies
 IBISWorld Industry Research Reports

Planning for external secondary data

 The problem is not finding out whether information exists; it is
finding out where the information resides
o Most secondary information is not categorised in any
particular form.
 The GO-CART approach
o Establish goals
o Develop objectives
o Define specific information characteristics
o Outline specific research activities
o Establish reliability
o Document using tabulation mechanisms

Secondary data - Reasons for a literature review

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Clarify and define the research problem and research questions

 Suggest research hypotheses to investigate
 Identification of scales and constructs required for the study
 Identification of well-established and successful research
methodologies to study the problem at hand

Electronic search sources

Electronic searches
 Popular articles and newspapers
 ABI/INFORM
 LexisNexis
 Search engines
 Online blogs
Scholarly research
 Peer-reviewed scholarly articles
 Google Scholar
o Easy access
o Number of citations

Advantages of secondary data

Secondary data
 High availability of data with advances in internet and related
search technologies and existing published and accessible
sources

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Costs associated with many secondary data sources are minimal

Primary data
 Primary data acquisition may take months due to designing and
testing questionnaires, data collection and analysis
 Primary data acquisition requires moderate to substantial
investment depending on the scope and magnitude of the
research
Secondary information is becoming more widely available and technology
is enabling greater refinement and categorization for electronic searches.

Limitations of secondary data

• Prior data manipulation
 Render data unfit for present purpose
• Data relevancy
 The time period of the collection
 The categories of definitions
 The unit of measures
• Data accuracy (trustworthiness)
 Consistency across sources
 Source credibility, appropriateness of methodology and source
bias

Lecture 3 - INTERVIEWS and FOCUS

Marketing research data

 Management is quite often faced with problem situations where
important questions cannot be adequately addressed or resolved
merely with secondary data

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Meaningful insights need to be gained through the collection of

primary data
 Primary data is typically collected using a set of formal
procedures in which researchers question or observe individuals
and record their findings

Quantitative research
 Research that places heavy emphasis on using formalised,
standard questions and pre-determined response options in
questionnaires administered to large numbers of respondents
o Applicable for descriptive and causal designs
o Researchers trained in questionnaire design, construct
development, scale measurement, sampling and statistical
data analysis

Goals of quantitative research

 Make accurate predictions about relationships between market
factors and behaviours
 Gain meaningful insights into those relationships
 Validate the existing relationships
 Test various types of hypotheses

Qualitative research
 Gain preliminary insights to decision problems and opportunities
o Methods include probing, interviews, open-ended or
unstructured questions, observation, feedback
o Preliminary insights are sometimes followed up with
quantitative research to verify the qualitative findings
o Applicable for Exploratory Exploratory research designs
o When objectives focus on gaining background information,
defining terms and establishing research priorities

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Interviews in qualitative research

 Formalized process in which a well-trained interviewer asks a
subject a set of semi-structured questions in a face-to-face
setting
o At home, office, centralised interviewing centre, product
location, purchase location, random locations etc.
o Also referred to as ‘in-depth’ or ‘one-on-one’

 Hybrid interviews
o Combination of internet and phone interviewing
o Internet enables consumers to be exposed to visual and
audio stimuli

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

In-depth interviewing objectives

 To discover preliminary insights of what the subject thinks or
believes about the topic of concern or why the subject exhibits
certain behaviours.
 To obtain unrestricted and detailed comments that include
feelings, beliefs or opinions that can help better understand the
different elements of the subject’s thoughts and the reasons why
they exist.
 To have the respondent communicate as much detail as possible
about his or her knowledge and behaviour towards a given topic
or object
 Collection of attitudinal and Behavioural dialogue through
probing questions
o When an interviewer takes the subject’s initial response to
a question and uses that response as the framework for
the next question (the probing question) in order to gain
more detailed responses
 Interpretations of the dialogue to create theme categories and
insights

In-dept Interviewing
Advantages
 Flexibility to collect data on activities and behaviour patterns,
and attitudes, motivations and feelings.
 Large amount of detailed data possible
 The possibility to probe the respondent further
Disadvantages
 Lack of generalizability.
 Lack of reliability and validity.
 Inability to distinguish small differences.
 Potential interviewer errors.
 Costs and time

In-depth interviewing steps

 1. Understand the decision problem and research objective
 2. Create a set of appropriate questions
 3. Decide on the best interview environment
 4. Screen and select suitable prospective subjects

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 5. Contact subjects, provide guidelines, create comfort zone,

begin interview
o Conduct the in-depth interview
o Analysis the subjects' narrative responses
o Write summary report

Types of interviews
 Experience interviews
 Protocol interviews
 Articulative interviews
 Projective interviews
o Word association tests
o Sentence completion tests
o Picture tests
o Thematic appreciation test (TAT)
o Cartoon or balloon tests– Role-playing activities
o Zaltman Metaphor Elicitation Technique (ZMET)

Experience interviews
 Interviews that refer to informal gatherings of individuals
thought to be knowledgeable on the issues
 Quickly gather information that can be used to develop future
research topics
 Example: If a company like Procter & Gamble has a research
problem that deals with estimating future demands for its newly
created website, the company could begin by contacting several
website ‘experts’ and asking their opinions on the issues

Protocol interviews
 Process where subject is placed in a decision- making situation
and is asked to express the process and activities undertaken to
make a decision
 Provides insights and understanding of motivational or
procedural activities or both within the overall decision process
 Example: Asking Dell customers to talk through the steps and
activities they went through in the PC purchase decision

Articulative interviews

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Interviews that focus on listening for and identifying key conflicts

in a person’s orientation values toward goods and services
 Structured to elicit narratives as opposed to gaining factual
truths
 Example – Researchers can identify different meanings and
interpretations of words, products and advertisements based on
feedback from various groups of respondents

Projective interviews
 Indirect method of questioning that enables a subject to project
beliefs and feelings onto a third party, into the task situation or
an inanimate object.
 To learn more about the respondents in situations where they
might not reveal their true thoughts in a direct questioning
process
 The researcher uses the findings to look for hidden meanings and
associations

Focus groups in qualitative research

 A formalised process of bringing a small group of people together
for an interactive, spontaneous discussion on one particular topic
or concept
o Usually 6-12 people are guided by a moderator through an
unstructured discussion that may typically occupy one to
three hours.
 The main purpose is to gain insight into the topic of interest.
Value of technique lies in the unexpected findings often obtained
from a free-flowing group discussion.

Focus group objectives

 1.Provide data for defining and redefining marketing problem
 2. Identify specific hidden information requirements
 3. Provide data for better understanding the results from other
quantitative survey studies
 4. Reveal consumers’ hidden needs, wants, attitudes, feelings,
behaviours, perceptions and motives regarding services,
products or practices

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 5. Generate new ideas about products, services or delivery

methods
 6. Discover new constructs and measurement methods
 7. To help explain changing consumer preferences

Phase 1: Planning the study

• The most critical phase
• Researchers must have an understanding of:
 – purpose of the study
 – a precise definition of the problem
 – specific data requirements
• Key decisions on selecting the appropriate participants, selection
and recruitment of members, focus group size and session details

Focus group participants

 Central factors in the selection process

o Strong consideration of the study’s purpose and think
about who can best provide the requisite information
o Potential group dynamics
o Willingness of members to engage in dialogue
o Individuals’ knowledge of the topic
o Group should be homogeneous enough to encourage
comfort and discourage socially acceptable responses,
while allowing enough variation to allow for contrasting
opinions

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Phase 2: Conducting discussions

 The success of the actual focus group session depends heavily on
the moderator and his or her communication, interpersonal,
probing, observation and interpretive skills.
 The moderator must be able not only to ask the right questions
but also to stimulate and control the direction of the participants’
discussions over a variety of predetermined topics.
- a good understanding of the background of
the research and the requirements of the
group
- must know how and when to bring closure
to one topic and move the discussion to the
next
Moderator traits
 Good interpersonal, communications and interpretive skills
 Display professionalism and create positive group dynamics
 Good understanding of the topics and questions
 Skilled in asking follow-up probing questions

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Communicate clearly and precisely both in writing and verbally

 Exhibit a friendly, courteous and adaptive personality
 The person should be experienced in focus group research
 Quick mind capable of noting and probing new ideas
 Know how and when to bring closure to one topic and move the
discussion to the next

Moderators guide
• Development of a moderator’s guide
 A detailed outline of the topics, questions and sub-questions that
will serve as the basis for generating the spontaneous interactive
dialogue among the group participants.
 The moderator’s guide uses a structured outline format that
establishes an order for asking a series of opening, introductory,
transition, critical and ending questions
 Review ‘A closer look − Business insights: Moderator’s guide’

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Phase 3: Analysing and reporting results

Debriefing analysis
 – Summary analysis of the comments and ideas
 – Researcher and moderator discuss the subject responses and
feedback
 – Need to check interpretive bias, faulty recall, lack of critical
reflection, etc.
Content analysis
 – Systematic procedure of taking individual responses and
grouping them into larger theme categories/patterns
 Software tools : NVivo, Xsight
A report to communicate the findings

Analysing focus outcomes

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Focus groups: advantages

 Stimulates new ideas, thoughts and feelings about a topic
 Can uncover underlying reasons
 Fosters an understanding of why people act or behave
 Client participation
 Elicits wide-ranging customer responses
 Brings together hard-to-reach groups
 Inability to generalise results Questionable reliability of results
Subjectivity of interpretation High cost per participant

Technology and focus groups

 High-tech versions of focus group interviewing, promoted as
online focus groups is gaining popularity
 Subjects are gathered in a centralized location and the session is
carried in real time across the internet to clients and researchers
at various locations
 Advancements in interactive marketing technologies (IMTs) is
opening new avenues for conducting telephone, video and
internet focus group interviews

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Lecture 4 - MAKING SENSE OF QUALITATIVE

DATA & SAMPLING

Qualitative data analysis

 Data is textual and occasionally visual and the goal is
‘understanding’
 Qualitative data analysis tends to be ongoing and iterative
 Qualitative data analysis is largely inductive
o categories, themes, patterns emerge from the data; rather
than defined prior to data collection
 Popular methods used– observation, focus groups, interviews,
ethnographic research
 Qualitative data needs to be collected & transcribed
 ‘Too much’ detailed data!
– Transcription of audio/video tapes
– Researcher observation recordings and notes
– Field notes by ethnographers

Managing the data collection

 Qualitative data must be transcribed for analysis
o Text from online focus groups and netnography is
produced automatically and is immediately available for
analysis
o Audiotape or videotape recordings have to be transcribed
o Notes from the field, during observation, debriefs need
integrated
o Corrections and adjustments need to be made to the
transcription
 All qualitative data material should be indexed and related
material should be cross-indexed.

Analysing qualitative data

 There is no one process for analysing qualitative data
o Some researchers prefer impressionistic approach and do
not go through transcripts and other documents

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o Nevertheless, careful and deliberate analysis is crucial to

sound qualitative analysis
o Three-step process is useful
 Step 1: Data reduction
 Step 2: Data display
 Step 3: Conclusion drawing/verification

Data reduction (Step 1)

 The amount of qualitative data can be extensive – Data reduction
processes allow us to read through transcripts and develop
categories to represent the data
 Data reduction can be done through:
o categorisation and coding
o Comparison
o theory building
o iteration
o negative case analysis
o tabulation

Data reduction: Categorisation and coding

 Categorise sections of the transcript and label them with names
or code numbers
 Categories
o may be defined before the analysis
o can be developed inductively in the analysis process
o may be modified and combined as analysis continues
 A code sheet is a document with all the categories and codes on
it
o Codes can be words or numbers
 Popular software used: NVivo and ATLAS

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Data reduction: Comparison

 Process of developing and refining theory and constructs by
analysing the differences and similarities in categories, themes,
participants, etc.
 Each potential new instance of a category or theme is compared
to already coded instances
 Understand the differences and similarities
o between two constructs of interest
o between different kinds of informants

Data reduction: Theory building

 Building theory that is grounded, or based on the data collected
Axial coding
o Process of relating codes (categories and properties) to
each other, via a combination of inductive and deductive
thinking
o Looking for any and all kind of relations and fit things into
a basic frame of generic relationships
 Selective coding
o Process of choosing one category to be the core category,
and relating all other categories to that category
o Develop a single storyline around which everything else is
draped

Data reduction: Iteration

 Iteration means working through the data several times in order
to modify early ideas and to be informed by subsequent analyses
 Results in revising and deepening constructs as well as the larger
theory based on relationships between constructs
 Note taking or memorizing right after an interview or focus group
is an important iterative element

Data reduction: Negative case analysis

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Researchers deliberately look for cases and instances that

contradict the ideas and theories that researchers have been
developing
 Generally ideas and theory generated from the data should be
viewed with skepticism
o We should not be looking for evidence to confirm pre-
existing biases and early preliminary findings

Data reduction: Tabulation

 Frequency of mention, re-occurrence and co- occurrence of key
words, concepts, codes and responses
 Shows exact times of occurrence of specific codes
 Controversial
o Not all questions are asked in the same way
o Not all responses are given in the same way
o Frequency of mention is not a good measure of importance
 Further iterative analysis is required to support or refute the
credibility of tabulation analysis

Data display (Step 2)

 Visual displays to summarise extensive textual data.
 Major ideas, relationships, categories are illustrated in compact
fashion. Creative task.
 Formats will differ in response to the combination of research
problem, methodology (interviews, focus groups, observations,
etc. ) and focus of analysis.
 Data can be visualised using tables, diagrams, models, matrix of
quotes, consensus maps, etc.

Conclusion drawing/verification (Step 3)

 Credibility of qualitative data analysis is based on the rigour of
the actual strategies used for collecting, coding, analysing and
presenting data for theory generation

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

 Need to persuade audiences that the research findings of an

inquiry are:
o reliable (measurement and findings are stable, repeatable
and generalisable)
o valid (the research measures what it was intended to
measure)
 Cross researcher reliability
o Degree of similarity in the coding of the same data (text
and images) by different researchers
 Peer review
o External qualitative methodology or topic area experts are
asked to review the research analysis and findings
 Triangulation– To check and establish validity in their studies by
analysing a research question from multiple perspectives, such
as:
o multiple methods of data collection and analysis
o multiple data sets
o multiple researchers analysing the data
o data collection in multiple time periods
o acknowledging different and relevant perspectives and
informants

Qualitative research reports

 These reports typically contain three sections: 1.Introduction
o Research objectives
o Research questions
o Description of research methods
 Analysis of the data/findings
o Literature review and relevant secondary data

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o Findings displayed in tables or charts

o Interpretation and summary of the findings
 Conclusions and recommendations

Sampling
 The information gathered from the sample (small group) will
allow for judgments to be made about the larger group (target
population).
 Marketers and decision-makers base much of their decision-
making on the assumption that a sample can be representative
of the larger population.

Sampling Objectives
 Making the right decisions in the selections of items (peoples,
products or services)
o Making inductive and predictive judgments or decisions
about the total target population on the basis of limited
information or in the absence of perfect knowledge
 Feeling confident that the data generated by the sample can be
transformed into accurate information about the target
population

Sampling terminology
 Census: a research procedure that includes every element in the
defined target population
 Population: the identifiable total set of elements of interest
 Defined target population: a subset of the population singled out
specifically for investigation
 Sampling unit: a particular element from the defined target
population from which data and information are sought
 Sampling frame
o The list of all eligible sampling units; the master list of the
defined target population, e.g. telephone books, list of
customers
 Sampling frame error– An error that occurs when the sampling
frame includes

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o elements from the population that: do not fit the sample

unit profile or complete requirements of the defined target
population are complete segments of the defined target
population that are not included in the sampling frame

Sampling theory
 Confidence interval
o The statistical range of values within which the true value
of the target population parameter is expected to lie.
 The wider the confidence interval you are willing to
accept, the more certain you can be that the whole
population answers would be within that range
 Confidence level
o Expressed as a percentage and represents how often the
true percentage of the population who would pick an
answer lies within the confidence interval
 The 95% confidence level means you can be 95%
certain; the 99% confidence level means you can be
99% certain. Most researchers use the 95%
confidence level
 Sampling error
o Refers to any type of bias or error because a sample was
used
 Nonsampling error
o Refers to any type of bias or error in the survey that is not
attributable to mistakes in either drawing a sample or
determining the sample size
o Population frame error
o Response error
o Measurement error
o Errors from gathering information

Probability sampling methods

 Simple random sampling
o A sample is drawn by a random procedure from a sampling
frame

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o Researchers use a table of random numbers, random-digit

dialling, or another random selection procedure
o This ensures that each sampling unit in the defined target
population has a known, equal, non-zero chance of being
selected into the sample
 Systematic random sampling
o Sample is chosen by selecting a random starting point and
then picking every ‘nth member’ from the random starting
point until the necessary sample is drawn
o A constant ‘skip interval’ is determined to ensure
representativeness, and the skip interval is applied to
select every nth member
o This sampling design is used in such a way that the entire
list is covered, no matter what the starting point
o This design accomplishes the same end goal of the SRS
method, and is more efficient
o Review exhibit 10.7 for the steps in drawing a systematic
random sample
 Stratified random sampling
o Population split into sub-populations or strata based on
distinguishing characteristics such as age, income, product
ownership, university faculties, etc.
o After the strata are segmented, a simple random sample is
drawn for each stratum, AND then samples from each
stratum are combined into a single sample of the target
population
o Useful when the defined target population is believed to
have a non-normal (or skewed) distribution
o Review exhibit 10.8 for the steps in drawing a stratified
random sample
 Cluster sampling
o This method requires that the defined target population be
segmented into geographic areas, each of which is
considered to be very similar to the others.  Each cluster is
representative of the target population
o Researchers randomly select a few areas, then either
conduct a census of the elements in each area

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o This sampling method is appealing when researchers can

easily identify similar geographic areas
o Review exhibit 10.9 for the steps in drawing a cluster
sample

Non-probability sampling methods

 Convenience sampling
o Samples are drawn at the convenience of the researcher
o Assumption is that the defined target population is
homogeneous and the samples are similar to the overall
target population
o Examples include:
 shopping-centre/mall-intercept interviewing
 interviews in other high-traffic areas
 Judgment sampling
o Participants are selected according to the researcher’s or
some other experienced individual’s belief that they will
meet the requirements of the study
o Assumption is the researcher’s subjective belief that the
opinions of a group of perceived experts on the topic of
interest are representative of the entire defined target
population
o Examples include: satisfaction survey only on heavy users 
interviews with key people only
 Quota sampling
o This method involves the selection of prospective
participants according to pre-specified quotas such as:
 demographic characteristics (e.g. age, race, sex,
income),
 specific attitudes (e.g. satisfied/dissatisfied,
liking/disliking),
 specific behaviours (e.g. regular/occasional,
user/non-user)
o Sample elements are then selected based on convenience
or researcher judgment

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

o Provides an assurance that pre-specified subgroups of the

defined target population are represented on pertinent
sampling factors that are determined by the researcher
 Snowball sampling
o Involves subjectively identifying and qualifying a set of
initial prospective respondents who can, in turn, help the
researcher identify additional people to be included in the
study.
o Referrals will have demographic and psychographic
characteristics that are more similar to a person referring
than would be by chance  For example, drivers of ultra
luxury cars worth above $200 000 or more could
recommend others in the sample target market

Exploratory research is defined as a research used to investigate

a problem which is not clearly defined. It is conducted to have a better
understanding of the existing problem, but will not provide conclusive
results
 A study into the role of social networking sites as an effective
marketing communication channel
 An investigation into the ways of improvement of quality of
customer services within hospitality sector in London

Descriptive research is defined as a research method that

describes the characteristics of the population or phenomenon that is
being studied. This methodology focuses more on the “what” of
the research subject rather than the “why” of the research subject.
 The management of a retail store is interested in understanding
who their current customers are.

Causal research, also called explanatory research, is the

investigation of (research into) cause-and-effect relationships. To
determine causality, it is important to observe variation in the variable
assumed to cause the change in the other variable(s), and then measure
the changes in the other variable(s).


Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

Qualitative research
 Gain preliminary insights to decision problems and opportunities
o Methods include probing, interviews, open-ended or
unstructured questions, observation, feedback
o Preliminary insights are sometimes followed up with
quantitative research to verify the qualitative findings
o Applicable for Exploratory Exploratory research designs
o When objectives focus on gaining background information,
defining terms and establishing research priorities

a construct is the abstract idea, underlying theme, or subject

matter that one wishes to measure using survey questions. ... As a
cohesive set, the dimensions of a construct define the construct.
Some constructs are relatively simple and do not have many
dimensions.

Data analysis error

Construct development error
Random sampling error
 Random errors are statistical fluctuations (in either direction)
in the measured data due to the precision limitations of the
measurement device. Random errors can be evaluated
through statistical analysis and can be reduced by averaging
over a large number of observations (see standard error)
Non response error
Survey instrument design error
 Measurement errors are those errors in the survey observations
that may be caused by interviewers, respondents, data
processors, and other survey personnel.[‘; Often, the causes of
measurement errors are poor questions or questionnaire design,
inadequate personal training or supervision, and insufficient
quality control. Measurement errors are often hidden in the data
and are only revealed when the measurement process is
repeated or responses are compared to a gold standard (i.e.,
error-free measurements

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

3 types of Marketing Research Designs – Exploratory, Descriptive and

Casual
Exploratory Research

 Exploratory research is used in obtaining preliminary information

that will help identify the problem and hypothesis. It is done to
understand what is happening and why something is happening.
Some of the most common methods of exploratory research are
focus groups, interviews, literature research (library, newpaper,
magazines, trade publication and online), and case analyses.

Descriptive Research
 Descriptive research is used to identify the marketing problem
and/or the potential for a market. This type of research is used
to identify the characteristics of the target group or the average
user of the product or service.
o Descriptive resesearch will allow us to make specific
predictions and notice a correlation among variables.
There are 2 types of descriptive studies, and they are:
cross-sectional study and a longitudinal study.
 A cross-sectional study involves a sample of the
market population at a certain point in time.
 A longitudinal study involves a panel or fixed sample
of element at a certain point in time.

Casual research
 Is marketing research done to test a hypothesis; the cuase and
effect of a hypothesis. For example, causal research may be used
in a business setting to quantify the effect that a change will
have on its current operations, and what it will have on future
production levels to assist in the business planning process

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

04/20/2020

Downloaded by An Nguyen (annayye_@hotmail.com)

 lOMoARcPSD|480616

04/20/2020

Downloaded by An Nguyen (annayye_@hotmail.com)