MARKETING RESEARCH 3613 USF

Curbstoning or Rocking Chair Interviewing
A practice of data falsification when the researchers complete the interviews themselves or make up “observed” respondent behaviors.
Deception
experimental designs- placebo, debriefing
Phantom Response
A practice of data falsification where researcher duplicates an actual respondents data to represent a second set of responses
Marketing Research
the function that links an organization to its market through the gathering of information
Marketing Dashboard
An interactive computer terminal or screen that displays the Key Performance Indicators (KPIs) in a way that is easy for executives to read and understand.
What is Importance-Performance Analysis (IPA)?
A research approach for evaluating competitors’ strategies, strengths, limitations, and future plans
What are the two predominant, scientific approaches to research?
Inductive and Deductive Research
What are three structural elements of Observation Research?
Direct vs. Indirect
Disguised vs. Undisguised
Structured vs. Unstructured
Projective Methods
An indirect method of questioning that enables a subject to project beliefs and feelings onto a third party, into a task situation, or onto an inanimate object.
Netnography
A qualitative research technique that draws upon data from virtual communities e.g. Harley Davison Brand Community.
Content Analysis
A systematic procedure of taking individual responses from transcripts, and grouping them into larger themes or categories.
Probe Questions
Specific questions that result when an interviewer takes the subject’s initial response to a question and uses that response as the framework for the next question in order to gain more detailed responses.
What are the possible research question types answered by descriptive research designs?
Who, what, when, where and how
How do Longitudinal Study Designs work?
This descriptive research method tracks the same sample through repeated measurements, such as panels.
An unobservable, intangible and abstract concept measured indirectly by several related variables.
Construct
What is the incidence rate of the target sample in the entire population?
The percentage of the general population that is the subject of the marketing research. For example pilots and shooters.
null hypothesis
A statement of the perceived existing relationship between two constructs/ variables as being NOT significantly different.
Difference between correlation and causation
Relationship between two variables vs. one variable producing an effect on another variable.
Three factors necessary for causation
(1) Functional Correlation
(2) Temporal Order or Precedence
(3) Control Extraneous Variables
External Validity
The extent to which a causal relationship found in a study can be expected to be true for the entire target population.
complete randomization
The procedure whereby many subjects are assigned to different experimental treatment conditions, resulting in each group averaging out any systematic effect on the investigated functional relationship between the IVs and the DVs.
different types of consumer data online
Web traffic, real-time, click-stream, biometrics and smart cards
A logical aggregation of information stored in a single data location.
Data Warehouse
4Vs of Big Data
Volume, Velocity, Variety and Veracity
customer lifetime model?
A database model developed on historical data, using actual purchase behavior, not probability estimates, to predict future actions.
How is Neural Networking defined as a data mining technique?
This is a non-linear predictive model that learns how to detect patterns that match a particular profile. The name comes from the fact that the process resembles that of the human brain. For example, How likely is a consumer to upgrade his cell phone given a number of data from his purchase patterns and other individual specific data?
Importance of Marketing Research
Identifying opportunities/ problems
Developing marketing actions
Evaluating marketing performance
Forge Long term relationship
Information sharing
Integrated Marketing Communications
Role of Marketing Research
1. Opportunity identification
2. Marketing planning
3. Evaluation and control
Managerial Functions Served by Marketing Research
Descriptive function: what is the sales trend in the industry/ identifying consumers with similar preferences or needs
Diagnostic function: what was the impact on sales when say a package design was changed/ or when cycle time was reduced
Predictive function: what can we change in future based on what we know now/ demand analyses
Product
Concept/ Product Testing
Test marketing
Product sampling
Customer satisfaction studies S
ervice quality studies Product portfolio
Price
Demand analysis
Sales forecasting
Product analysis
Retailing research Environmental research
Place
Retailing research
Logistics assessment
Cycle time research
Sales tracking studies
MDSS
EDI
Promotion
Benefits and lifestyle studies
Perceptual mapping
Brand preferences
Consumer psychographics
Product usage
Consumer decision process
Retail preferences
Market Research Industry
Classified – Intellectual property, patents
Internal – GM, P&G (functional consistencies, information sharing)
External – outsourced (cost advantage)
Custom – specific research e.g. brand-name testing, NPD
Standardized – general services e.g. AC Nielsen Brokers – data entry, tabulation, statistical analyses Facilitators – ad agencies (supplementary research)
Marketing Ethics
The application of morals to behavior related to the exchange environment
Sources of Ethical Dilemmas
respondents, research provider, research info user
Sugging/Frugging
Selling or fundraising under the guise of conducting research
Soft Costs
Unethical pricing
Respondent Bill of Rights
1. Your privacy and the privacy of your answers will be
respected and maintained
2. Your name, address, phone number, personal
information, or individual responses won’t be disclosed to anyone outside the research industry without your consent (confidentiality)
3. You will always be told the name of the person contacting you, the research company’s name, and nature of the
survey (full disclosure)
4. You will not be sold anything, or asked for money, under
the guise of research
5. You will be contacted at reasonable times, but if the time is inconvenient, you can ask to be re-contacted at a more
convenient time
6. Your decision to participate in a study, answer specific questions, or discontinue your participation will be respected without question (voluntarism)
7. You will be informed in advance if an interview is to be recorded and of the intended use of the recording
8. You are assured that the highest standards of professional conduct will be upheld in the collection and reporting of information you provide
Human Subjects Review Committee/ IRB
Children participation (under the age of 18)
– Parental consent is required
– Obtaining and documenting assent from children Protection:
1) Ensure confidentiality and anonymity
2) Provide access to or information about resources for
coping with psychosocial stress caused by the
research procedures
3) Voluntary participation and informed consent
Marketing Research Process
It is a systematic approach to collecting, analyzing, interpreting, and transforming data into decision-making information.
Determine Need for Marketing Research
Benefits outweigh costs
Goal for Marketing Research
Gather raw data – Relevant
Create data structure – Meaningful Information
Provide interpretation – Decision Making
Major Steps in Marketing Research DSEC
Determine the Research Problem
Select the Research Design
Execute the Research Design
Communicate the Research Results
Symptom vs. Problem
discrepancy between actual and expected result
what went wrong with what
Decision vs. Research Problem
develop new package design-evaluate effectiveness of alternative
increase amount of repeat service-asses current repeat purchase amount
increase store traffic-measure current store image
introduce new product-develop a test market to assess
acceptance of new product
Research Designs
Exploratory Research – understanding consumer attitudes, motivations and behaviors
Descriptive Research – answering who, what, when, where and how
Causal Research – cause and effect relationship between two or more variables
Secondary Data
Data that have already been collected by and are readily available from other sources
Primary Data
◦ Data collected for the specific research needs ◦ Internal collection or outsourcing?
Secondary vs Primary
Gathered directly from consumers
Can be expensive
Is often time consuming
More representative of the population
Primary data methods
Surveys
Focus groups
Interviews
Observation Studies
Market Testing
Experiments
Types of Secondary Research
Internal Data
◦ Data that is collected and stored in-house
◦ CRM, MDSS, EDIs, Data warehouses
External Data
◦ Data that is collected by outside agencies
◦ Fed data, trade associations, periodicals, e.g. wsj, Fortune 500
Literature Review
is a comprehensive examination of available information relating to a topic of interest.
Consumer Panels
Benefits
Lower cost than other methods
Rapid availability and timeliness
Accurate reporting of sensitive purchases
High level of specificity
Risks
Sampling error (low minority representation)
Turnover of panel members
Response bias (SDR)
Syndicated Data
Data that has been compiled according to some standardized procedure; customized for a company such as for market share, ad effectiveness, and sales tracking.
Methods of Syndicated Data
1) Consumer Panels: large samples of households that provide specific, detailed data for an extended period
of time
2) Store Audit: examination and verification of how
much of a particular product or brand has been sold at the retail level
Sources of Secondary Data
Internal
Sales Invoices
Accounts Receivables
SEC
Filings Annual Reports
Sales Activity Reports
Online Registration
Customer Comments
Mail-order Forms
Credit Applications
Warranty Cards
Sales Person
Expense Forms
Past Studies
External- government public files, electronic searches, compile data
Store Audits
Examination of how much of a particular product or brand has sold at retail level
◦ Product sales in relation to competition
◦ SALES= Beginning inventory + Net purchases- Ending Inventory
◦ Effectiveness of shelf space/POP displays (point of purchase: a place where sales are made)
◦ Sales at various price points
◦ Effectiveness of POS coupons (point-of-sale: the place where a retail transaction is completed)
◦ Direct sales by store type, location, etc.
Research Design
Study blueprint: How the research problem will be addressed?
Involves
◦ Research orientation
◦ Data collection and analysis
Ensures
◦ Managerial Relevance
◦ Economic use of resources
Quantitative research
Uses formal questions and predetermined response options in questionnaires administered to large number of respondents.
Qualitative research
Seeks to understand research participants rather than to fit their answers into predetermined categories.
When to use Exploratory Research
To gain background information
Problem formulation
Identify alternative courses of action
Develop hypotheses
Isolating key variables
Defining terms
Establishing priorities for future
research
Help interpret conclusive research
Observation Research advantages/disavantages
Advantages:
– Natural environments – No recall error – Sometimes it’s the only way
Disadvantages
– May not be representative – Subjective interpretation – Inability to learn why
Depth Interviews
One-on-one interviews
Collect both attitudinal and behavioral data from the respondent
Unique characteristic of this method: Uses probing questions to get more data on the topic.
Depth Interview skills
1. Interpersonal skills
2. Listening skills
3. Interpretive skills
Focus Groups
Most widely used qualitative data collection method in Marketing.
Brings a small group of people together for an interactive and spontaneous discussion on a particular topic or concept.
Typically consists of 8-12 people The success of a focus group heavily depends on group dynamics. The cost of a focus group can vary from $2,000 to $5,000 per session
The role of a moderator?
Ask the right questions
Stimulate and control discussion
Create positive group dynamics
Enthnographies
Record behavior in natural settings, often involves extended experience in a cultural or subcultural context
Popular vs. Scholarly
Popular- mags, newspapers, written by anyone, based on opinion, easier to read
Scholarly- journal articles, books, written by experts, harder to read
When to use Descriptive Research?
To describe group characteristics
◦ mean, median, and mode
To estimate proportion of units with particular characteristics
◦ proportion or percent
To make specific predictions
◦ relational statistics (correlations, phi, betas)
Cross sectional studies
describe population at one point in time
sample surveys
Longitudinal studies
same sample is measured repeatedly
panel studies
Conceptual Model
concept map:
real time data
secondary research
primary data
Formal lit review
Variable
an observable item that is directly measured in a research study – TANGIBLE/CONCRETE
Construct
an unobservable concept measured indirectly by several related variables – INTANGIBLE/ABSTRACT
Model Building Process
When the research questions require investigating relationships between constructs or variables, researchers need to conceptualize these hypothesized relationships.
Hypothesis
A statement of the perceived existing relationship between two constructs/variables.
Non-directional Hypothesis
A hypothesis that does not specify the nature and the direction of the relationship between the two variables.
Positive Hypothesis
An association between two variables in which they increase or decrease together.
Negative Hypothesis
An association between two variables in which one increases while the other decreases
Ho, Ha
H0 = A statement of the perceived existing relationship between two constructs/variables as being NOT significantly different.
Ha = Opposite to a null hypothesis, there is a relationship between two constructs/variables, that is significantly quantified.
Survey Research
is a research method involving the use of standardized questionnaires to collect data about people and their preferences, thoughts, and behaviors in a systematic manner
Systematic Error
Errors that can bias a research study that are not related to sampling issues
Random Sampling Error
Statistically measured difference between the actual sampled results and the estimated true population results
Total Sampling Error
– Total Error = Sampling + Non-Sampling Error
Respondent Errors
Nonresponse Error-Too many people don’t complete survey
-Results may vary upon those who respond vs. those who don’t
Response Error
-Deliberate
-Unconscious
Measurement errors
Construct Development Error
• Construct low on reliability and validity
Scale Measurement Error
• Lack of precision, & discriminatory power
• Ambiguous set up or inappropriate descriptors
Survey Instrument Error
• Improper sequencing and length • Inappropriate instructions
Data Analysis Error
• Incorrect technique •
Predictive bias
Misinterpretation Error
• Interpretive bias • Selective perception
Deciding characters for Survey Methods
Situational Characteristics-
Budget
Time Frame
Quality/ Completeness
Generalizability/ Precision
Task Characteristics-
Task Difficulty
Stimuli Design
Amount of Info
Topic Sensitivity
Respondent Characteristics-
Diversity
Incidence Rate
Degree of Participation
Ability/ Willingness/ Knowledge-levels
Definition Errors
Researchers misinterpret the TRUE nature of the problem situation
Descriptive Design
Type of Problem = describing the situation
Research Questions = Who, what, where, when and how?
Research Objective = identify meaningful relationships
Data = Predominantly Primary and QN with N > 200
Research Tool = Surveys/ Questionnaires
Administrative Error
Data Processing error
Observer error
sample design error
Correlation
Correlation = relationship between two variables
Causation
Causation = one variable producing an effect on another
variable
Factors for Causation
1)Correlation
2) Temporal antecedence
3) No third factor driving both
Experiments
Experiments = causal research designs that can identify cause-and-effect relationships between variables/constructs.
Field Experiment
Natural setting but extraneous variables cannot be controlled
Lab Experiment
Artificial setting where extraneous variables can be controlle
Randomization
random assignment of test units to groups
ensures prior equality of experimental groups
Validity
the extent to which the conclusions drawn from the experiment are true.
External vs internal validity
External validity – the extent to which a causal relationship is true for the defined target population

Internal validity – the extent to which the research design accurately identifies causal
relationships.