Download Ch - Pearson Canada

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

History of statistics wikipedia , lookup

Operations research wikipedia , lookup

Human subject research wikipedia , lookup

Misuse of statistics wikipedia , lookup

Transcript
Ch#
1
Term
Marketing Research
Definition
Deals with the collection, processing, analysis, and
communication of information regarding people's attitudes,
feelings, intentions, and behaviour toward products, services,
and those organizations and people involved in any aspect of
marketing.
1
Marketing
The set of activities involved in initiating, enhancing, and
supporting the exchange of goods, services, and money
between providers and customers.
1
Exchange
Occurs when one person provides something of value to
another person who in turn gives something back of equal value.
1
Distribution Channel
The process through which a product passes on its way from the
manufacturer to the end-use customer.
1
Primary Research
A marketing research study that is designed and executed to
address a current need for additional information on which to
base a marketing decision.
1
Secondary Research
Involves the use of information that was not collected specifically
for the purpose at hand.
1
1
Scope of Marketing
Pertains to the range of activities and the depth of those
Research
activities.
Market Research
The description of markets is the range of market research (in
contrast to the development of information for making better
marketing decisions, which is the realm of marketing research).
1
Industry Associations
Organizations comprised of companies from within a specific
business sector or industry for the purpose of association and
sharing of information.
1
Professional Marketing
A person who has been educated in marketing research, has
Researcher
substantial experience in all or almost all phases of marketing
research, and is actively involved in providing marketing
research services for most or all of their work week. The
Professional Marketing Research Society is authorized to
designate members as Certified Marketing Research
Professionals (CMRP).
1
Subcontract
An organization will typically contract a consulting firm to
conduct their marketing research. If this is a full-service
marketing research firm, the entire project is likely conducted by
Sound File
that company. A firm that is not “full service” will subcontract
other firms to conduct parts of the marketing research project on
behalf of the original contractor.
1
PMRS, CSRC, and
These are the three principal marketing research associations in
CAMRO
Canada. PMRS is comprised of individual members whereas
CSRC and CAMRO are comprised of member companies or
organizations. At the time of writing this book, the three
associations have decided to merge.
1
Custom Research
When a marketing research project is specifically designed and
executed to provide information to support marketing decisions
within the organization.
1
Standardized Studies
Marketing research projects that are always conducted in the
same way, regardless of the client.
1
Syndicated Studies
These are designed and executed by marketing research firms
to fill a need among several marketing organizations. The study
is completed and then the report is sold to those needing the
information.
1
Omnibus Services
Shared-cost marketing research projects, i.e., several noncompeting clients contribute questions, share study costs, and
get answers back to their own questions and to the common
demographic questions.
1
Gap
Exists between what the organization knows and what it thinks it
needs to know to effectively compete in the marketplace. A gap
motivates the need for obtaining information based on marketing
research.
2
Marketing Problem
Marketing managers look in tactical and strategic market
management for answers to the problems they face. When a
marketing manager defines a marketing problem, it will typically
include a need for marketing and market information that can be
provided by marketing research.
2
Research Design
One of the first steps in a marketing research project is to design
the overall project as well as each step. Research design
involves specifying the activities at each step of the project so
that the objectives are met within the project scope.
2
Market Segmentation
Divides the brand's market or category market into groups. Each
of the market groups or segments should be different from other
segments on some key dimension(s) that help better understand
customers and more effectively serve their needs.
2
Customer Satisfaction
This type of research focuses on measuring the satisfaction
level of brand customers and understanding which aspects of
the brand and the brand-buying experience significantly affect
that satisfaction.
2
Marketing Objectives
Key challenges of the marketing problem that must be achieved
according to the marketing team in order to improve marketing
of the product.
2
Marketing Research
Define the challenges for marketing information that must be
Objectives
achieved by the marketing research project. The marketing
research objectives are a subset of the marketing objectives.
2
Latent Behaviour
Those customer activities that are not directly observable and
Patterns
are important for better understanding how to serve customer
needs.
2
Scope of the Study
Helps to define the parameters of the marketing research project
pertaining to its breadth and depth. These can include the
definition of the relevant population of customers, the depth of
statistical data analysis, and other relevant aspects encountered
during the execution of the project.
2
Manifest Variables
Those aspects of the customer that can be directly observed or
proven. Age, income, education, and the number of boxes of
cereal bought last month are all observable and provable.
2
Latent Variables
Those aspects of behaviour that cannot be directly observed
such as respondents' attitudes.
2
Hypothetical Construct
Pertains to something that we think exists but can never prove.
For example, customer satisfaction and corporate reputation are
hypothetical constructs.
2
Reliability
In research projects, this means that those projects can be
repeated with the same questions on similar subjects with
similar findings obtained.
2
Validity
In research projects, this means that the projects measure what
they intended to measure.
2
Types of Marketing
There are several of these, such as usage and attitude studies,
Research Projects
pricing research, and market segmentation studies. These have
very similar components regardless of where they are
conducted.
2
Information
On a research project, these relate to the objectives and needs
Requirements
of the marketing research and marketing problems; these are
typically listed as exploratory, descriptive, and causal.
2
Exploratory Study
When little is known on a topic, the research is called
exploratory. It is often acknowledged that the initial exploratory
study will help to refine research methodology for future
projects. These studies often have a significant qualitative
component.
2
Descriptive Studies
These explain the current state of the market and marketing to a
sector.
2
Causal Studies
These attempt to explain cause-and-effect relationships using
some of the most sophisticated design and analysis techniques.
2
Qualitative Research
Focused on obtaining respondents' in-depth comments on topics
through their verbatim discussion of marketing issues.
2
Focus Groups
Discussions organized with six to twelve people to fully explore
a specific topic through oral discussion.
2
In-depth
Discussions that one moderator has with one respondent to
Personal Interviews
qualitatively explore a specific topic in the words of the
respondent.
2
Quantitative Research
Mainly involves obtaining respondents' selection of one or
several answers to specific questions in a survey, the
quantification of those answers over several respondents, and
the measurement of the accuracy of those answers.
2
Moderators
Lead respondents through the research topics of qualitative
studies and encourage deep consideration and discussion of the
topics.
2
Personal Interviews
In a quantitative marketing research study methodology,
personal interviews occur when one person at a time is led
through the quantitative questionnaire to elicit his or her
answers. These can be conducted in a respondent's home,
office, or in a central location.
2
2
Central Location
Respondents are recruited in a location such as a shopping mall
Personal Interviewing
to be interviewed for a quantitative study.
Telephone Interviews
The most common form of quantitative fieldwork is the
telephone interviews where the interviewer asks respondents
questions during a telephone conversation.
2
CATI
Telephone interviews often use Computer Assisted Telephone
Interviewing (CATI) where the questionnaire is programmed into
the computer so that the interviewer reads questions off the
computer screen and enters answers directly into the computer.
2
Self-Completion
Relies on the respondent to read the questions and respond
Technique
manually. These are typically administered using paper-andpencil questionnaires, computer administration, and the internet.
2
Skip Patterns
Directions for moving from one question to another in a
questionnaire where some questions might be skipped,
depending on answers to previous questions.
2
Field Supervisor
Manages the fieldwork operations of marketing research, often
by organizing and supervising the operations of field
interviewers to maintain high quality requirements.
2
Perceptual Methods
Involve observing and measuring some aspect of human
behaviour.
2
2
Eye-Movement
Track the movement of respondents' pupils as they look at a
Cameras
document, picture, or advertisement.
Omnibus Study
Often called a shared-cost study, this is a survey that includes
questions supplied by several noncompeting clients.
2
2
Cross-Sectional
Conducted at one time, measuring the attitudes, behaviour, and
Studies
characteristics of a cross-section of relevant respondents.
Longitudinal Panels
Measure the characteristics, attitudes, and behaviour of a group
of respondents at regular intervals over a period of time, often
months or years.
2
Consumer Panels
Marketing research firms recruit people to be part of consumer
panels where they will be asked questions periodically. The
questions might or might not include components that
longitudinally track these measures.
2
Panel Profile
Panels are recruited to represent certain characteristics of the
Maintenance
relevant population. The composition of a panel can vary over
time due to members opting out of the panel. New members
must be recruited to the panel to maintain its
representativeness.
2
Retail Audits
Survey the movement of products through retail outlets and
other retail activities.
2
Hybrid Field
Sometimes two or more field methodologies are combined to
Methodology
form a hybrid field methodology such as recruiting by telephone
and asking respondents to complete the survey over the
internet.
2
Research Proposal
The research firm details the way in which it plans to design,
execute, and report on a study through its research proposal.
2
Request for Proposal
Companies needing marketing research services invite one or
(RFP)
more marketing research firms through a request for proposal
(RFP) to submit their designs, plans, budgets, and timelines for
the project.
2
Terms of Agreement
A formal document developed and signed by the research firm
and the client organization to specify the steps and conditions of
the marketing research project.
3
Secondary Research
Any information obtained through marketing research for a
project other than the purpose at hand.
3
Primary Research
A marketing research study designed and executed to address a
current need for additional information on which a marketing
decision will be based.
3
Intranet
“A network operating like the World Wide Web but having
access restricted to a limited group of authorized users (as
employees of a company).” (Merriam-Webster On-Line
Dictionary)
3
Information Warehouse
Some organizations store company, customer, and market
information in organized data files that comprise the firm's data
or information warehouse.
3
Feasibility Studies
Intended to identify whether a specific course of action will
provide the needed value to the firm.
3
3
Store Location
Marketing research, or geo-demographic research, that is
Research
intended to identify the best geographic location for a store.
Internal Secondary
Information that was collected and stored at some time in the
Information
past within the organization, either in hard form or in electronic
form.
3
External Secondary
Information that was collected and stored at some time in the
Information
past outside of the organization, either in hard form or in
electronic form.
3
Customer Relationship
Intended to provide greater service to customers by integrating
Management (CRM)
customer-focused information from all points in the firm and all
points of contact with customers.
3
Competitive Intelligence
The brand of marketing research that provides information about
the market position of competing brands and companies and
their marketing actions.
3
Industry Associations
Associations of companies within an industry or business sector
that provide a source for sharing information and promoting the
industry.
3
3
Internet Search
Internet-based computer programs that assist internet users to
Engines
locate information electronically.
Standardized Studies
Marketing research projects that are always conducted in the
same way, regardless of the client.
3
Syndicated Studies
Designed and executed by marketing research firms to fill a
need among several marketing organizations. The study is
completed and then the report is sold to those needing the
information.
3
Data Mining
The activity of gleaning important information from large
databases using sophisticated and powerful data analysis
techniques.
3
Geo-demographic
Typically directed to provide information for optimally locating
Analysis
physical operations. This is accomplished by analyzing
information about customer location and movement, and
demographic information such as family size, education, and
income.
4
Sample Survey
The collection of information from some members of the target
audience.
4
Sample
A subset of the population from whom we collect information.
4
Census
Collects information on everyone in the universe. Reasons why
a census is often not feasible:

target audience too large

target audience too dispersed

too time-consuming

too expensive

difficult to assure quality
4
Sample Design
Defines the characteristics of the sample.
4
Population or Universe
The target audience under study.
4
Sampling Unit
The smallest unit of a sample that will constitute one unit in
analysis.
4
4
4
4
4
4
Sample Frame
The listing of the entire universe. It should be:

comprehensive

precise

practical
Probability or Random
Means that each unit in the population has an equal chance of
Sampling
being included in the sample.
Probability Sampling
Based on statistical theory that enables us to specify the
Methods
accuracy of our estimates.
Simple Random
A procedure in which every member of the population has an
Sampling
equal chance of being selected and included in the sample.
Random Number
Computer programs that produce numbers in a random
Generators
sequence.
Random Number
Tables containing preselected random numbers.
Tables
4
Systematic Random
The first sampling unit is chosen at random. The remaining
Sample
sampling units are chosen at given intervals (e.g., every 100th
person on the list).
4
Sample Interval
The number of units in the sample frame divided by the sample
size.
4
4
Stratified Random
We first divide our universe into a few homogeneous subgroups
Sample
and then draw random samples from each subgroup separately.
PPS Samples
We keep the size of each stratum in a sample that reflects the
population proportion.
4
Disproportionate
The samples in each stratum are deliberately chosen to not
Sampling
reflect the population proportion. Weighting procedures are
applied to the data to correct for disproportionate sampling.
4
Oversampling
Initial sampling is done using the PPS method. We then
increase the sample sizes of group(s) that do not have an
adequate number of respondents.
4
Multistage Sampling
The drawing of random samples at different levels, with each
sample level becoming the population for the next level.
4
Primary Sampling Unit
The sampling unit selected at the first stage of sampling.
(PSU)
4
Cluster Sampling
Refers to randomly choosing subsets (clusters) of the population
and then randomly choosing respondents within each cluster.
4
Design Factor
An adjustment applied to the data to correct for the clustering
effect.
4
Replicated Samples
Independent samples of the universe in the same study.
4
Probability Samples
Often modified to suit the specific requirements of different data
collection methods.
4
In-home (Door-to-door)
Interviews that use cluster sampling.
Interviews
4
White Pages Dialling
Uses telephone listings from the phone book.
Method
4
4
Random Digit Dialling
Uses randomly generated telephone numbers. Some numbers
(RDD) Method
generated this way may not exist.
Seed Sampling
Uses a set of telephone numbers that are known to exist with a
constant added to each number.
4
Grid Method
Selects a respondent within a household by first listing every
eligible person in the household and then randomly choosing
one.
4
Last Birthday Method
Selects the person who celebrated his or her birthday last from
among those who are eligible to participate in the survey within
a household.
4
Nonprobability
Everyone in the population does not need to have an equal
Sampling
chance of being chosen. It is assumed that if many people have
the same opinion, then that opinion will be prevalent throughout
the population.
4
Purposive Samples
Respondents are chosen based on the researcher's judgment of
who is and who is not a typical representative of the population.
4
Accidental Samples
Respondents who can be conveniently reached are interviewed.
4
Quota Sampling
The researcher specifies the number of interviews to be
conducted in each subgroup of the population.
4
Snowball Sampling
An eligible respondent identifies other eligible respondents.
4
Adaptive Sampling
We interview the person adjacent to an eligible respondent.
4
Estimate
A value we obtain using a survey.
4
Parameters
The values we would have obtained if we could accurately
measure everyone in the population. Two factors affect the
accuracy of our estimates:

the way sample is chosen

4
Nonsampling Errors
the size of the sample
Errors in our estimates that are not the result of the sample size.
They are the result of factors such as low nonresponse rates.
Some possible solutions are increased number of callbacks,
statistical adjustment of the results, and nonresponder surveys.
4
Callbacks
Attempts to recontact respondents who were not available when
first called.
4
Nonresponder Survey
A survey of respondents who did not participate in the initial
survey, generally with a view to assessing whether they are in
any way different from the participants.
4
Sampling Errors
Result from interviewing only a small portion of the population
rather than everyone in the population. This can be estimated
from statistical formulas.
4
Validity
Properly measuring what we are trying to measure.
4
Reliability
Consistently measuring whatever it is that we are measuring.
4
Confidence Interval and
To choose the sample size according to statistical criteria, we
Confidence Level
need to specify two parameters: the confidence interval (margin
of error acceptable to us); and the confidence level (degree of
certainty required).
4
Sample Size
Determined by dividing the number in the sample by the square
of the result of the division of the confidence coefficient for the
level of confidence needed by the required margin of error.
4
Confidence Coefficients
90% = 1.65
95% = 1.96
99% = 2.56
4
Calculating Sample
To calculate the sample size at a 95 percent level of confidence,
Size
divide 100 by the acceptable margin of error and square the
result.
4
Finite Population
When the sample is large in relation to the population (i.e., when
Correction (fpc)
the sample is about 10% of the population or higher), we can
apply finite population correction (fpc) to the sample size. This
will result in a lower sample size for the same margin of error.
4
Valid
A properly selected sample of 100 respondents is as valid as a
similarly selected sample of 1000 but not quite as reliable.
5
Qualitative Research
Elicits information using semi-structured or even unstructured
probing of the opinions of respondents. It also includes indirect
methods such as projective techniques.
5
Focus Group
Involves an extended discussion between a moderator and a
group of respondents, typically eight to ten in number. The
discussion generally focuses on a single theme (e.g., health
foods or insurance).
5
Mini-group
A junior version of the full-sized focus group with about two to
six participants.
5
Discussion Guide
An outline of the topic areas to be covered in the focus group.
Moderators generally use written discussion guides.
5
Respondent Selection
Criteria are normally specified by the client, working in
collaboration with the moderator.
5
Random Method
Respondents are chosen using mechanical statistical
procedures.
5
Referral Method
Respondents are recruited on the basis of being referred by
others. The referral method is more commonly used than the
random method.
5
Video Conferencing
The focus group discussion is transmitted live to another
location across the city or country.
5
Internet Viewing
The interview is made available live over the internet, enabling
the client to watch the focus group from anywhere.
5
Writing exercises
Used when the moderator would like to know the uninfluenced
opinions of each member of the group on a pivotal point.
5
Framing
Putting an idea or a situation in the context chosen by the
moderator.
5
Reframing
Removing an idea or a situation from the current context and
putting it in the context chosen by the moderator.
5
Hypothetical Scenarios
These put the participants in particular situations that can make
the discussion more realistic and shed light on how different
products are perceived under different usage circumstances.
5
Regression
Refers to mentally placing the respondents in an earlier period in
time (such as childhood).
5
5
Negative
These deal with contrary scenarios and focus thinking on the
Questions
specific reasons for a given behaviour.
Online Focus Groups
Conducted at one of the websites set up to facilitate the conduct
of group discussions through personal computers.
5
Individual Depth
The moderator talks to one respondent at a time rather than to a
5
Interview
group of people.
Projective Techniques
An indirect way of gleaning insights into human behaviour. They
are based on the idea that people will subconsciously attribute
to others what they find unacceptable in themselves.
5
Personification
A technique in which respondents are asked to assume that a
product or service is a person and to attribute human
characteristics to that person.
5
5
5
5
Transposed Vocabulary
Respondents are asked to assume that a given product or
Technique
service under consideration is actually a different product.
Transference
A projective technique that deliberately asks the respondent for
Technique
opinions that might be held by others.
Sentence Completion
The respondent is given an incomplete sentence with regard to
Technique
the product or service and is asked to complete it.
Half-Questions
A technique in which the interviewer deliberately stops in the
Technique
middle of a question or a statement expecting the respondent to
complete it.
5
Cartoon Test
One of the characters is depicted as saying something about the
product or service. The balloon for the other character is empty
and the respondent is asked to fill it in.
5
Photosort Technique
A deck containing a number of photographs of people is given to
respondents and they are asked to sort these as users of
different products or different brands of a product.
5
Semiotics
The study of signs, symbols, and communication based on the
concept that all human communication is made to texts that
need decoding.
5
Laddering
Holds that the attributes of a product or a service can be viewed
as means to an end. The aim of the technique is to identify the
underlying or the “end” motives of consumers.
5
ZMET
Designed to elicit the mental models that drive consumer
thoughts and behaviour. The objective of ZMET is to explicate
these models in actionable contexts using consumers'
metaphors.
5
Study-Related Biases
These arise out of incorrect problem definition, improper
recruitment, poor display material, restrictions on proper rotation
of display material, an inappropriate research location,
excessive subject matter, and unrealistic timing provisions.
5
Moderator-Related
These arise out of factors such as the moderator's inability to
Biases
remain dispassionate, moderator incompetence, or inability to
control and insensitivity to cross-currents and subtleties.
5
Client-Related Biases
These arise when the moderator is inadequately or incorrectly
briefed by the client or when the client introduces his or her
expectations and biases into the briefing.
6
Questionnaire
A standard set of questions that are asked of all those who
participate in a survey.
6
Screening questions
Determine whether a consumer is eligible to take part in a
survey. These questions are always placed first.
6
Funnelling Technique
Starts with generalized questions and proceeds to more and
more specific questions.
6
Inverted Funnel
Where a general question may distort the response to specific
Approach
questions, an inverted funnel approach is used, specific
questions are asked before the general question.
6
Classification
Generally refers to demographic information and can include
Information
items such as the respondent's age, gender, income, education,
and place of residence.
6
Double-Barrelled
Questions that have two parts but ask for only one answer.
Questions
6
Leading Question
A question that leads a respondent to an answer by the way the
question is phrased.
6
Loaded Question
Similar to a leading question, only stronger. Loaded questions
imply that certain answers are socially and emotionally more
desirable.
6
Layout of a
Refers to the physical way in which questions are laid out.
Questionnaire
6
Closed-Ended
These have predefined answers. They can take many forms.
Questions
6
6
Simple Dichotomous
These have only two possible predetermined answers, yes or
Precoded Questions
no.
Multichotomous
These have many predetermined possible answers.
Precoded Questions
6
Multichotomous
These have many predetermined possible answers and
Precoded Questions—
respondents are told what they are.
Prompted Multiple
Answers
6
6
Aided Recall or
Prompted responses are also known as aided recall or
Recognition
recognition.
Multichotomous
These have many predetermined possible answers and
Precoded Questions—
respondents can choose more than one response.
Unprompted Multiple
Answers
6
Unaided Recall or Top-
Spontaneous and unprompted response.
of-Mind
6
Multichotomous
These have many predetermined possible answers and
Precoded Questions—
respondents can choose only one response.
Single Answer
(Prompted or
Unprompted)
6
Multichotomous
Contain codes only for the most popular alternatives.
Partially Precoded
Questions
6
6
Multichotomous Non-
These can have many possible answers, none of them
coded Questions
precoded.
Open-Ended questions
These let the respondent decide the scope of the answer. The
answers given by the respondent are recorded verbatim by the
interviewer. Answers are grouped into logical categories at the
coding stage.
6
Probe
To ensure we receive the full picture, the interviewers are asked
to probe the respondents. This is usually done by a simple
question such as, “What else?” after the respondent gives her or
his initial answer to an open-ended question.
6
Skip Patterns
Rules that decide which question a respondent should answer
depending on what answer he or she gives to the current
question. For skip patterns, use a vertical format.
6
Response Piping
Refers to incorporating the answers of earlier questions into
later questions.
6
Response Rotation
Refers to programming the prompted list so that it appears in a
different order to different respondents.
6
Informal Pre-testing
Refers to testing the questionnaire with co-workers or friends.
6
Formal Pre-testing
A small sample of respondents (e.g., 20 to 50, depending on the
size of the study) is surveyed in exactly the same way as they
would be in the main study.
7
Warm-Up Questions
Designed to establish rapport between the interviewer and the
respondent. They should be short, easy to answer, and not of a
personal nature.
7
Attitudes
Deal with consumer perceptions and judgments. They exist in
the mind of consumers and cannot be directly observed.
Attitudes are assumed to be relatively enduring (i.e., attitudes
change slowly).
7
Dichotomous Scales
Assess the existence of an attitude. This type of scale usually
leads to a “Yes” or “No” response.
7
Ranking Scales
These ask the respondents to state their order of preference but
not necessarily their intensity.
7
Rating Scales
Provide information on distance between scale points.
7
Bipolar
Use negative numbers to indicate negative opinion and positive
(Positive/Negative)
numbers to indicate positive opinion.
Rating Scales
7
Constant Sum Method
A technique in which the respondent is asked to divide a given
number of points among all alternatives.
7
Semantic Rating Scales
Use words instead of numbers to measure the strength of an
attitude.
7
Likert Scale Technique
Presents a set of attitude statements. Respondents are asked to
express agreement or disagreement with each statement,
usually on a five-point scale.
7
Semantic Differential
The respondent is presented with a word such as a brand name
of a car and presented with a variety of adjectives to describe it.
7
Graphic Rating Scales
Use pictures as scale points.
7
Lifestyle or
Refers to a person’s self-reported behaviour, personality traits,
“Psychographics”
and related attitudes.
Screening Question
Identifies whether the person contacted is eligible to answer the
7
questions.
8
Briefing
A presentation to familiarize the supervisors and the
interviewers with the general and special requirements of the
study.
8
Pre-testing
The conducting of a few interviews before going ahead with fullscale interviewing.
8
Pilot Test
A pre-test in which the pre-test is nearly identical to the main
study in terms of questionnaires, respondents, interviewer mix,
etc.
8
Monitoring
The actual listening in by a supervisor to make certain that an
interview was actually conducted.
8
Verification
Entails a supervisor calling a respondent back to make certain
that an interview was actually conducted.
9
9
Numeracy (or Number
The ability to understand and communicate the meaning of
Sense)
numbers.
Variable
Any numerical information pertaining to a respondent. It can
vary from respondent to respondent. An example of a variable is
age.
9
Attribute
A word variable that indicates the presence of a certain
characteristic. An example of an attribute is gender (male or
female).
9
Dependent Variable
A variable whose value is influenced by some other variable. For
example, if income is influenced by education, then income
depends on education and is a dependent variable.
9
Independent Variable
A variable whose value influences some other variable. For
example, if education influences income, then education is the
independent variable.
9
Banners
Column headings in a cross-tabulation that are usually the
independent variables.
9
Stubs
Row headings in a cross-tabulation that are usually the
dependent variables.
9
Counted Variables
Answer the question, “How many?” They are also called
<i>nonmetric</i> variables.
9
9
Measures of Central
Summary measures such as the mean, the median, and the
Tendency
mode.
Arithmetic Mean or
The same as average as it is used in everyday language. It is
Mean
obtained by adding all the values and dividing that sum by the
total number of observations.
9
Variable
Any numerical information pertaining to a respondent. It can
vary from respondent to respondent. An example of a variable is
age.
9
Median
The middle observation when the observations are arranged in
order of magnitude and the number of observations is odd.
When the number of observations is even, the median is the
average of the middle two observations.
9
Median
The median is the score attached to respondent (n + 1)/2 when
the scores are ordered. <i>If the result of (n + 1)/2 ends in 0.5
such as 4.5, average the scores above and below (e.g., if the
median is 4.5, average the score of the 4th and 5th
respondents).</i>
9
Mode
The most frequently occurring value in a data set.
9
Measures of Dispersion
Statistical measures that describe how the actual scores are
spread out. They include the range, the mean absolute
deviation, the variance, and the standard deviation.
9
Range
The difference between the largest and the smallest score in a
set of data.
9
Mean Absolute
The average deviation from the mean, ignoring the sign.
Deviation
9
Variance
The average of the squared deviations from the mean. When
samples are used, the average is computed on the basis of (n –
1) rather than n.
9
Standard Deviation
The square root of the variance.
(<i>s</i>)
9
Coefficient of Variation
Expresses the standard deviation as a percentage of the mean.
9
Standard Scores or Z-
Measurements expressed in standard deviation units.
scores
9
Normal Curve
A symmetrical, bell-shaped mathematical curve. Many physical
variables in nature and measured variables approximate this
distribution.
9
9
Measured Variables (or
These Measure some attribute. The attribute may be a quantity
Metric Variables)
or a quality.
Descriptive Statistics
Refer to statistical measures that are concerned with describing
the data in terms of summary and dispersion measures.
9
Inferential Statistics
Refer to statistical measures that are concerned with
generalizing the observed data to the population.
9
Nonsampling Errors
Include any error that is not attributable to sampling.
Nonresponse, language problems, and interviewer errors are
some examples of this type of error.
9
Sampling Errors
The result of the fact that a sample, rather than a population, is
used to obtain data.
9
Margin of Error
Refers to the range within which the “true result” (the value that
would have been obtained if everyone in the population had
been sampled) is likely to fall. Such ranges can be specified to
any given level of probability.
9
Parameter
The <i>true</i> value. It is the value that would have been
obtained if everyone in the population had been sampled without
error.
9
Estimate
The value obtained using a sample survey.
9
Standard Error
The standard deviation divided by the square root of the sample
size.
9
Standard Error of
The pooled standard error.
Difference
9
T-test
A test to determine if two percentages or means are significantly
different from each other.
9
Hypothesis Testing
A procedure used to statistically evaluate the difference between
different groups.
9
Null Hypothesis
The hypothesis of no difference. It states that the differences
between different groups is the result of sampling error.
9
Alternative Hypothesis
Any hypothesis that is not the null hypothesis. It states that there
is a difference among different groups.
9
9
Type 1 or Alpha (α)
Error that occurs when a null hypothesis is rejected when, in
Error
fact, it is true.
Type 2 or Beta (β) Error
Error that occurs when a null hypothesis is accepted when, in
fact, it is not true.
9
Chi-squared Tests
Nonmetric tests when more than two groups are involved. They
test the hypothesis that three or more groups do not differ from
one another.
9
Analysis of Variance
Used when we want to compare more than two groups.
9
Correlation Coefficient
A number that summarizes the relationship between two
variables. The value of the correlation coefficient can range from
–1.0 to +1.0.
10
Multiple Exposure
The communication of an idea to a person in more than one way
and uses more than one medium. For example, the
communication can be through print in text, graphs, or tables, or
through the use of the spoken word.
10
Chunking
Means to break information down into smaller parcels that can
be used in a better way or can be better understood.
10
Topline Report
A succinct report of marketing research findings focused on the
key objectives only.
10
Stub-and-Banner
Tables of research findings where the stub is a dependent
Tables
variable such as the customer's intention to buy the brand. The
banners are demographic characteristics such as age,
education, marital status, etc.
11
Product Research
Research to identify how subjects respond to using physical
products or how subjects respond to product concepts.
11
Brand Map
A diagram that graphs category brands in an attempt to spatially
represent consumers' perceptions of similarities and
dissimilarities among the brands or their relative preferences for
the brands.
11
Correspondence
A mathematical procedure for developing brand maps.
Analysis
11
Product Testing
Research to identify how subjects respond to using physical
products.
11
Central Location
Occurs when product tests are conducted in central locations
Testing
such as shopping malls or large meeting rooms in schools,
churches, and government buildings.
11
In-home Testing
Occurs when product tests are conducted in respondents'
homes.
11
Pure Monadic Test
Occurs when each respondent tries only one product and then
evaluates that product.
11
11
Sequential Monadic
Occurs when the respondent tries one product and evaluates it
Test
and then tries a second product and evaluates it.
Paired Comparison
Occurs when the respondent tries one product, then tries a
second product, and comparatively evaluates the two products.
11
Proto-monadic Paired
Occur when respondents try one product and evaluate it, then
Comparisons
try a second product and evaluate it, and then comparatively
evaluate the pair of products.
11
Triangle Test
Occurs when the respondent is presented with two units of one
product and one unit of a second product, tries all three
products, and is asked to comparatively evaluate the “three”
products.
11
Experimental Design
A process for attempting to understand whether a stimulus
causes a defined effect, where respondents are organized in
very specific groups and exposed to stimuli and observed or
measured.
11
New Product Research
Occurs when respondents are asked to evaluate ideas,
concepts, or actual renderings of new products.
11
Simulated Test Market
Occurs when finished new products are tested on samples of
Study (STM)
respondents. The respondents have an opportunity to buy the
new products, take them home, use them, and then evaluate
them.
11
Trial
Occurs when a consumer buys and uses a product for the first
time.
11
Repeat
Occurs when a consumer buys and uses a product for the
second time and thereafter.
11
Hierarchy-of-Effects
Usually descriptions of the stages that a consumer is
Models
hypothesized to pass through during the purchasing cycle.
These stages include being unaware of the product through to
purchase and then through to post-purchase feedback.
11
Cognition
The stage of attitude formation in which a person recognizes an
object and learns about it.
11
Affect
The stage of attitude formation in which feelings and emotional
responses toward an object or action are developed.
11
Conation
The stage of attitude formation in which motivations for action
are developed.
11
Experimental Group
A group of subjects in the experiment that is exposed to a
stimulus and then measured, observed, or evaluated in some
way.
11
Control Group
A group of subjects in the experiment that is not exposed to the
stimulus and are then measured, observed, or evaluated in
some way.
11
Analysis of Covariance
A statistical data analysis procedure designed to measure
whether the means for three or more groups are different while
controlling for other factors.
11
Animatics
A primitive rendering of a television commercial in which
drawings and photographs are used instead of moving pictures
of actual people.
11
Econometric Models
Models of regression adapted to the needs of economic
analysis, frequently containing variables for past time periods,
for example, monthly advertising and prices for the past two
years.
11
Monadic Price Testing
Occurs when respondents are asked to consider whether or not
they would buy a product for a specific price.
11
Conjoint Analysis
A set of statistical techniques in which information is obtained
from respondents conjointly for several attributes of a product.
The information is then analyzed to determine the importance of
those attributes in the driving of the purchase decision and the
relative attractiveness of the levels of each attribute.
12
PIPEDA
Personal Information Protection and Electronics Document Act.
Legislation enacted by the Government of Canada to protect
Canadians from invasion of their privacy and unapproved use of
their personal information.
12
Privacy
According to the Merriam-Webster OnLine dictionary: 1a: the
quality or state of being apart from company or observation:
SECLUSION b: freedom from unauthorized intrusion <one’s
right to privacy>.