Schiffman 02
Schiffman 02
Schiffman 02
Quantitative Research
• Descriptive in nature.
• Enables marketers to “predict” consumer
behavior.
• Research methods include experiments,
survey techniques, and observation.
• Findings are descriptive, empirical and
generalizable.
Positivism
Prediction
Predictionof
ofconsumer
consumer Understanding
Understandingconsumption
consumption
actions
actions practices
practices
METHODOLOGY
METHODOLOGY
Positivism
Positivism Interpretivism
Interpretivism
Quantitative
Quantitative Quantitative
Quantitative
Table 2.2 continued
ASSUMPTIONS
Positivism Interpretivism
Develop Objectives
Conduct Research
Collect Primary Data
(Using highly trained
(Usually by field staff)
interviewers) Exploratory
Study
Analyze Data Analyze Data
(Subjective) (Objective)
Observation
Experimentation
Surveys
Observational Research
• Helps marketers gain an in-depth
understanding of the relationship between
people and products by watching them buying
and using products.
• Helps researchers gain a better understanding
of what the product symbolizes.
• Widely used by interpretivist researchers.
Experimentation
• Can be used to test the relative sales appeal
of many types of variables.
• Only one variable is manipulated at a time,
keeping other elements constant.
• Can be conducted in laboratories or in the
field.
Survey Data Collection Methods
Personal Interview
Telephone
Online
Table 2.4 Comparative Advantages
PERSONAL
MAIL TELEPHONE ONLINE
INTERVIEW
Cost Low Moderate High Low
Speed Slow Immediate Slow Fast
Response Self-
Low Moderate High
rate selection
Geographic
Excellent Good Difficult Excellent
flexibility
Interviewer
N/A Moderate Problematic N/A
bias
Interviewer
N/A Easy Difficult N/A
supervision
Quality of
Limited Limited Excellent Excellent
response
The degree to which
a measurement
instrument
Validity
accurately reflects
what it is designed to
measure.
The degree to which a
measurement
Reliability instrument is
consistent in what it
measures.
Attitude Scales
• Likert scales: easy for researchers to prepare
and interpret, and simple for consumers to
answer.
• Semantic differential scales: relatively easy
to construct and administer.
• Rank-order scales: subjects rank items in
order of preference in terms of some criteria.
Figure 2.4 Example of a Likert Scale
Please place the number that best indicates how strongly you
agree or disagree with each of the following statements about
shopping online in the space to the left of the statement.
1 = Agree Strongly
2 = Agree
3 = Neither Agree or Disagree
4 = Disagree
5 = Disagree Strongly
3 DVD
Neutral
Digital
2 Cable
DIVX
1
Availability
Number of
Clarity of
Access
Ease of
Cost
Picture
Excellent
Titles
Figure 2.5 Rank-Order Scales
Depth Focus
Interviews Groups
Projective Metaphor
Techniques Analysis
A qualitative research
method in which eight
to ten persons
participate in an
Focus Group
unstructured group
interview about a
product or service
concept.
Figure 2.5 Selected Portions of a
Discussion Guide
1. Why did you decide to use your current cellular
company? (Probe)
2. How long have you used you current cellular
company? (Probe)
3. Have you ever switched services? When? What
caused the change? (Probe)
4. What do you think of the overall quality of your
current service? (Probe)
5. What are the important criteria in electing a cellular
service? (Probe)
Research procedures
designed to identify
Projective
consumers’
Techniques
subconscious feelings
and motivations.
Metaphor Analysis
• Based on belief that metaphors are the most
basic method of thought and
communication.
• Zaltman Metaphor Elicitation Technique
(ZMET) combines collage research and
metaphor analysis to bring to the surface the
mental models and the major themes or
constructs that drive consumer thinking and
behavior.
Customer Satisfaction Data Collection
Instruments (Table 2.5)
• Customer Satisfaction Surveys
• Gap Analysis of Expectations versus
Experience
• Mystery Shoppers
• Critical Incident Technique
• Customer Complaint Analysis
• Analysis of Customer Defections
Sampling Plan Decisions
Whom to
survey?
How many?
How to
select them?
Table 2.6 Probability Sampling
Designs
Simple random Every member of the population has a known and
sample equal chance of being selected.
Systematic random A member of the population is selected at random
sample and then every “nth” person is selected.
Stratified random The population is divided into mutually exclusive
sample groups (such as age groups), and random samples
are drawn from each group.
Cluster (area) The population is divided into mutually exclusive
sample groups (such as blocks), and the researcher draws
a sample of the groups to interview.
Table 2.6 Nonprobability
Sampling Designs
Convenience The researcher selects the most accessible
sample population members from whom to obtain
information (e.g., students in a classroom)
Judgment sample The researcher uses his or her judgment to select
population members who are good sources for
accurate information (e.g., experts in the relevant
field of study).
Quota sample The researcher interviews a prescribed number of
people in each of several categories (e.g., 50 men
and 5 women).