marketing research exam
the problem that decision maker faces and typically involves what needs to be done.
Decision problem
first and most important step in the marketing research process is
formulating the problem, covers the managers and researchers perspective
a subset of all the members of a population of interest.
sample
in the 4th step of the marketing research process, we are designing the sample and collecting data through
sampling
the difference between the parameter and statistic
sampling error
A list of all the units in the population from which a sample will be selected.
sampling frame
a listing of the population elements from which the actual sample will be drawn
sampling frame
example of interval scales
x-itemized rating scales pictorial rating scale likert scale (stronglydisafreeoragree) semantic differential scale
Why use secondary data?
• Better problem definition • Suggest further data (provide guidance for next steps of research) • Suggest better research methods • Substitute for primary data
Advantages of Probability Samples
•Allows quantification of sampling error •Generally more representative
Common criteria for target population
•Demographics •Geographic area •Time period
Exploratory Research methods
•Literature reviews •Case studies •Interviews(Street-intercept interviews and 1-1 in-depth) •Focus Groups •Projective techniques •Observation (Ethnography)
When Not to Conduct Research
•The research costs exceed the expected benefits •Insufficient time/budget •The product is new and it represents a radical innovation •Outcome "decided" in advance
What is the flaw in the following question: What was your total annual income last year from all sources? (Above $60k, $50k to $60k, $40k to $50k, $30k to $40k, Below $30,000)
The choices are not mutually exclusive.
databases have 4 components
markets, products, facts, and periods
The choice of probability vs. non-probability sampling is closely tied to the
research problems
the research problem is the
researchers perspective
•Randomly select a population element •Then select every kth element following that element
systematic sample
descriptive research does not answer the question....
"why"
Cross sectional studies
-describe population at one point in time (snapshot) -Multiple snapshots from different samples
Longitudinal studies
-same sample is measured repeatedly -panel studies -same set of ppl are surveyed after a promotion
common types of projective techniques for sensitive topics
-word association -third person techniques -sentence completion -cartoon test -picture interpretation ZMET
6 steps in marketing research process
1. Formulate the problem 2. Determine the Research Design 3. Design the data collection method and forms 4. Design the sample and collect data 5. Analyze and interpret the data 6. prepare the research report
Consider the following two statements. The third-person technique may yield more honest survey responses for sensitive questions. Income can be measured on an ordinal scale instead of a ratio scale to make it more likely that respondents answer truthfully. Which statement(s) is(are) true?
Both are true
Test for cause and effect Choose between alternatives (experiments)
Causal Research
Randomly select subgroups, then select samples within subgroups •One-stage: include all elements within selected subgroups •Two-stage: take random sample of elements within selected subgroups •Area cluster sample: subgroups are geographical areas
Cluster Sample
A researcher does a street intercept poll. What type of sample is this?
Convenience
Methods of Descriptive Research
Cross sectional studies and longitudinal studies
Describe characteristics, behavior preplanned, structured, CONCLUSIVE (surveys, panels, scanner data)
Descriptive Research
sources of a sampling frame
Directories and public records Aggregators (e.g. infoUSA, AccuData) Internal databases
____________ is a general term for preliminary research conducted to increase the understanding of a concept, to clarify the exact nature of the problem to be solved, or to identify important variables to be studied
Exploratory research
Consider the following question taken from a questionnaire: "When seeking a new car, price is not a concern for me." Strongly disagree (1) Disagree (2) Uncertain (3) Agree (4) Strongly Agree (5) This is an example of a:
Likert scale item
Which is the biggest marketing research company?
Nielsen
the two biggest providers of scanner data and panel data :
Nielsen and IRI services
Population elements are selected in a non-random manner
Non-Probability
the actual value (mu)
Parameter
the entire group of people about whom information is needed.
Population
Every element has a known, non-zero probability of inclusion in the sample
Probability
What type of scale is involved if adult women are asked to place five brands of eye shadow in sequence so that "1" is assigned to the eye shadow with the highest-quality applicator, and "5" is assigned to the eye shadow with the lowest-quality applicator
Rank-order scale
The degree to which repeated measurements yield consistent results
Reliability(same point)
Characteristics of good measurement scales
Reliability, Validity, and Sensitivity
A restatement of the decision problem into what information is required by the decision problem. Usually there are multiple research problems corresponding to a decision problem.
Research problems/Questions
Ability to discriminate between meaningful differences in attitudes
Sensitivity
the value in a sample, used as an estimate of the actual value x-(bar)
Statistic (or "estimate")
Suppose Porsche managers want to know how people view the Porsche brand, he/she asked: Why do you think your neighbor would buy a Porsche? This is a projective technique called:
Third-Person Technique
What type of question is the following: Should Macy's department stores continue its excellent return policy for its customers?
This is a leading question.
longitudinal data can be used to answer questions about brand loyalty and switching but
cross-sectional data cannot
Are we measuring what we think we are measuring?
Validity(center)
Ex of decision problem: Where should we locate a new store? Possible research problems:
Who are our targeting consumers? where are the prospective locations? What are the nearby demographics for each location? who are our competitors? cost of rent?
probe attitudes and feelings through the use of metaphors and visual images
ZMET (zaltman metaphor elicitation technique)
a written outline of topics to be covered during a focus group discussion.
a discussion guide the moderator uses
Which of the following scales is a type of closed-ended question? a. All of the above b. Semantic differential scale c. Likert scale d. Dichotomous scale
a. all of the above
Which of the following is an incorrect statement concerning questionnaire layout? a. ask general questions last b. allow plenty of space for open-ended questions c. position questions that require the most effort in the middle d. position threatening or sensitive questions last
a. ask general questions last
Exploratory research can involve each of the following except a. experimentation b. it can involve all of the other c. in-depth interviews d. focus groups
a. experimentation
Which of the following is the primary reason or underlying rationale for conducting focus groups? a. interaction among group members b. able to provide more precision than quantitative studies c. ambiance of the focus group promotes direct questioning d. allow for individualized analysis
a. interaction among group members
things to avoid in questionnaires
ambiguous words leading questions generalization and estimates double-barreld questions implicit alternatives and assumptions
what do we ask for last in questionnaires
ask for classification
use the funnel approach in questionnaires which is
asking broad questions first
Which of the following is not a characteristic of descriptive research? a. It is used to describe characteristics of a market b. It can demonstrate causality in some cases c. It assists in decision making d. All of the others are characteristics of descriptive research e. It requires some understanding of the nature of the problem
b. It can demonstrate causality in some cases
Which of the following is not a reason that marketing research is beneficial to managers? a. Marketing research reduces the uncertainty the manager faces in the decision b. Marketing research is always worth the cost, regardless of the problem c. Marketing research assists the manager in understanding the link between marketing mix variables and firm performance d. All of the other are reasons that marketing research is valuable to managers
b. Marketing research is always worth the cost, regardless of the problem
Which of the following statement is true? a. None of them is true b. Open-ended (qualitative) questions in a questionnaire are hard to analyze but more flexible than closed-ended questions. c. It is always necessary to include screening questions at the beginning of the survey d. Researchers need to disguise the brand/ firm they worked for at the beginning of the survey
b. Open-ended (qualitative) questions in a questionnaire are hard to analyze but more flexible than closed-ended questions.
Which of the following is NOT a step in the marketing research process? a. Sampling and data collection b. Determine the research design c. Prepare the exploratory method d. All of the other are steps in the marketing research process e. Design the collection method
c. Prepare the exploratory method
For which of the following are focus groups least useful? a. To investigate needs for a new product b. To aid in clarifying the nature of a problem c. To draw conclusions about the characteristics of the target market d. Focus groups are equally useful for all of the others e. To discover new ideas
c. To draw conclusions about the characteristics of the target market
Which of the following is a primary disadvantage of observation research? a. observation data is always distorted by social pressure b. actual behavior is not reliable c. motives, attitudes and intentions cannot be evaluated d. observation data requires a skilled interviewer
c. motives, attitudes and intentions cannot be evaluated
collecting data from or about every member of the population of interest.
census
Non-Probability sampling procedures
convenience judgement quota snowball
Which of the following expressions about exploratory research is not true? Exploratory research... a. is often used for developing hypotheses b. is less structured c. help in questionnaire development d. All of the others are true
d. all of the others are true
Which of the following is not an advantage of in-depth interviews (IDIs) over focus groups? In depth interviews.... a. may uncover deeper insights about feelings and emotions b. suffer less from biases in the responses from social (peer) pressure c. All are advantages of IDIs over focus groups d. can be conducted in a much shorter amount of time e. allow for the responses to be attributed to one person
d. can be conducted in a much shorter amount of time
If the marketing research problem was defined as "what features do buyers prefer in our product?" the most appropriate type of research would be
descriptive bc it's describing characteristics
exploratory research IS NOT WHAT
drawing conclusions
Which of the following is not an example of a projective technique? (Please see slides for information for this question) a. sentence completion b. third - person technique c. cartoon test d. word association e. all of the others are examples of projective tests
e. all of the others are examples of projective tests
One of the advantages of focus group interviews is a. All of the above are advantages b. the moderator effect c. quantitative interpretation d. generalizability of findings e. group dynamics
e. group dynamics
dichotomous scale example
e.g. Did you see any movie in the past six months? yes or no
multichotomous scale example
e.g. What factor(s) did you consider in purchasing a Sony color TV?A. Price B. Quality C. Service D. Warranty E. Other (please specify)____ Lots of issues with multichotomous scale
the study of human behavior in its natural context
ethnography for observational research (researchers disguised as customers)
the second step of the marketing research process is determining the research design, the research design could be:
exploratory for insights descriptive for generalizability causal for identification of causality
clarify problem discover ideas, Gain insights Formulate hypotheses less structured, flexible (case studies, focus groups, qualitative research)
exploratory research
3 types of research
exploratory, descriptive, causal
A scale is reliable when it measures what it intends to measure.
false
An auto analyst is conducting a satisfaction survey, sampling from a list of 10,000 new car buyers. The list includes 2,500 Ford buyers, 2,500 Honda buyers, 2,500 GM buyers, and 2,500 Toyota buyers. The analyst selects a sample of 400 car buyers, by randomly sampling 100 buyers of each brand. This an example of cluster sampling.
false
An ordinal scale always assumes that the "distance" between the ranks is equal along the scale.
false
Exploratory research studies provide conclusive evidence to determine a particular course of action.
false
For the service provider example we discussed, we can infer that Verizon promotion is effective at gaining market share from cross-sectional data (look at ur notes)
false
It is best to spend as little time as possible on the problem definition stage of a research project, in order to reach the data collection stage quickly
false
It is typical in observation studies for the observer to ask the person who is being observed questions.
false
Marketing research should be conducted even if the managers will not be able to afford implementing a study's recommendations.
false
Personal interviews are the best way to conduct a survey because respondents are less likely to terminate the survey.
false
Primary data is data that is already collected for purposes other than the study at hand.
false
Secondary data can never be used as the only source of data for a marketing research study
false
To ensure the research objective is achieved, focus groups should follow a highly structured format.
false
Usually there is only one applicable research design for a given marketing research project
false
Discussion with loose structure •Generate ideas •Understand consumer vocabulary •Reveal needs, motives, perceptions, attitudes
focus groups
types of secondary data
internal and external (published and syndicated)
in the 6th step of the marketing research process, we are preparing the research report by
interpreting our findings and tailoring to our audience
classification, order, and distance a scale of measurement in which the intervals between numbers on the scale are all equal in size has no "true zero," "not at all satisfied" "very satisfied"
interval
•Please indicate your degree of liking on each of the following pizza places by checking the appropriate position on the 5-item rating scale. dislike a lot, dislike, neutral, like, like a lot
interval
which scales are continuous
interval and ratio
questionnaire design is an ________ process
iterative (repetitive)
most well known scale in psychology and marketing research
likert scale
please rate the extent to which you agree or disagree with the following statements
likert scale
the decision problem is the
managers perspective
a questionnaire should not take .....
more than 5-10 minutes to complete
When participants in a research study are coded as either "male" or "female," what type of measurement scale is being used?
nominal
classification only a scale in which objects or individuals are assigned to categories that have no numerical properties yes vs no questions
nominal
•Which of the following pizza places do you like to order your pizza from? Check all that apply .•Blaze Pizza •Papa John's Pizza •Donatos Pizza •Sicilia Pizza •Tommy's Pizza
nominal
which scales are discrete (categorical)
nominal and ordinal
In a survey about bicycling habits, each respondent is asked to provide his or her zip code. This is an example of which primary measurement scale? Group of answer choices
nominal scale
Types of scales
nominal, ordinal, interval, ratio
Please rank order the following pizza places according to your preference: 1=most preferred and 5= least preferred _Blaze Pizza _Papa John's Pizza _Domino's Pizza _Sicilia Pizza _Tommy's Pizza
ordinal
classification and order a scale of measurement in which the measurement categories form a rank order along a continuum "3-5 times", "18-24"
ordinal
rank order scale is what type of scale
ordinal rank order scale is when you rank a brand from say 1-10
Consider the following question: How many vacation trips do you take per year (on average) ___0 trips ___1-2 trips ___3-4 trips ___5 or more trips What measurement scale is being used here?
ordinal scale
on scale of 0 no pain and 10 hurts a lot faces
pictorial rating scale
strategy oriented decision problems are associated with
planned change
A decision problem can arise from:
planned change (proactive) and unanticipated change (reactive)
data collected by you... collected through observation, interview, questionnaire Information collected specifically for the purpose of the investigation at hand
primary data
if there is a readily available sampling frame then
probability sample is plausible
pros and cons of observations
pros: natural environments, real behavior, no interaction with researcher cons: expensive/time consuming, may be intrusive, bias
pros and cons of literature reviews (see what experts think)
pros: •Cheap•Easily accessible•Can be done quickly cons: •Biases•Not specific for problem of interest•Limited
pros and cons of focus groups
pros: •Fast•Interactive•Cost effective•Reveal feelings, attitudes, motives, needs•Unexpected insights cons: •Small sample•Group/social pressure•Biases•Moderator effect•Observer influence
pros and cons of 1-1 Depth interviews
pros: •No influence from others •Good for sensitive topics•Can get in-depth cons: •Expensive/time consuming•Small sample•Interviewer effect
Which of the following sampling methods is the least statistically efficient? systematic quota simple random cluster
quota
notes on pepsi coke example
random,,There are 4 levels of measurement, which can be ranked from low to high: Nominal: the data can only be categorized. Ordinal: the data can be categorized and ranked. Interval: the data can be categorized and ranked, and evenly spaced. Ratio: the data can be categorized, ranked, evenly spaced and has a natural zero.
classification, order, distance, and natural origin Any scale of measurement possessing magnitude, equal intervals, and an absolute zero "what is your current weight in pounds"
ratio
•Please divide 100 points among each of the following pizza places according to your degree of liking for each. _Blaze Pizza _Papa John's Pizza _Domino's Pizza _Sicilia Pizza _Tommy's Pizza
ratio
Consider the following question: What do you think a fair price for this product would be (in dollars) __________ Which measurement scale is being used here?
ratio scale
constant sum scale is what type of scale
ratio scale constant sum is when you allocate a total of 100 points to what is important
The framework or plan for a study, used as a guide in collecting and analyzing data.
research design
Helps to winnow the respondents to the most appropriate people
screening question
data collected by other people, published online data Information not gathered for the immediate study at hand but for some other purposes
secondary data
In desigining the data collection method (3rd step of marketing research process),,, we are collecting possibly two types of data
secondary data and primary data (used for descriptive research)
Consider the following scale: Happy --:--:--:--:--:--:-- Sad Young --:--:--:--:--:--:-- Old Ugly --:--:--:--:--:--:-- Pretty This is an example of a:
semantic differential scale
a five-point scale in which the opposite ends have one- or two-word adjectives that have opposite meanings, lines of showing high quality or low quality or useful or useless, etc.
semantic differential scale
Probability sampling procedures
simple random systematic stratified cluster
When each element has a known and equal chance of being selected in a population, this is referred to as taking a:
simple random sample
•Each element has a known and equal chance of being selected •Elements are selected by an objective process (e.g. coin toss, random number generator) •Requires a numbered list of population elements Each element of the population has the same known nonzero probability of inclusion.
simple random sample
•Divide target population into mutually exclusive and exhaustive subgroups ("strata") •Select a simple random sample from each stratum •Proportionate vs. disproportionate
stratified sample
secondary data that can be purchased from firms that collect it, store level scanner data, household level panel data
syndicated data
All of the following are non-probability sampling techniques, except: None of the other Convenience sampling. Systematic sampling. Quota sampling. Snowball sampling.
systematic sampling.
Delta Air Lines wants to assess the current level of satisfaction with its frequent flyer program. •What is the target population? •What sampling frame would you suggest?
target population is frequent flyer members sampling frame we'd suggest is internal database on frequent flyer members
phrase the question in terms of others
third-person technique
Marketing research can potentially address all four elements of the marketing mix.
true
discovery oriented decision problems are associated with
unplanned change
basic measures and facts of scanner data
volume price distribution merchandising
When to use descriptive research?
when the decision and research questions are clearly formulated.
rank from 1 being poor to 7 being excellent
x-itemized rating scales