Marketing Research Chapter 5 & 6

Front 1

Research Design

Back 1

The framework or plan for a study that guides the collection and analysis of the data

Front 2

Once research problem(s) are formalized, the next question to ask is

Back 2

“Exactly what information is needed to solve the research problem?”

Front 3

The research design:

Back 3

(1) is driven by the research problem
(2) depends upon how much is known about the problem

Front 4

Types of Research Design

Back 4

Qualitative research

Quantitative research

Front 5

Qualitative research

Back 5

Exploratory
Goal: Explore

Front 6

Quantitative research

Back 6

Descriptive Research
Goal: Describe
Causal Research
Goal: Establish Cause and Effect

Front 7

Qualitative (Exploratory)

Back 7

For example: if you want to know more about Venezuelan culture ask a Venezuelan
But the Venezuelan you ask will not perfectly represent ALL Venezuelan people
That’s why you need Quantitative research

Front 8

Quantitative

Back 8

Appropriate for seeing if your understanding is correct for the entire group that you want to study
Uses statistics to make guesses about an entire group from asking only a small part of the group
For example:
Your interview with Joey from the University of Texas has shown that he loves driving his truck in the mud.
You want to see whether the majority of people from UT also tend to love driving in the mud.
It takes too long to ask everyone attending UT!
So you just ask a few people and make an educated guess about everyone else—using statistics

Front 9

Types of Research Design

Back 9

Exploratory
Descriptive
Causal

Front 10

Exploratory Research Design

Back 10

What might be important to consider?

Front 11

Descriptive Research Design

Back 11

What are the characteristics of…?

Front 12

Causal Research Design

Back 12

If we do this, what will
be the impact?

Front 13

Why conduct exploratory research?

Back 13

Better formulate the manager’s decision problem
Increase researcher’s familiarity with the problem
Clarify concepts
Develop hypotheses
Exploratory research works to develop a “theory” regarding the research problem at hand

Front 14

Literature Search

Back 14

A search of statistics, trade journal articles, other articles, magazines, newspapers, and books for data or insight into the problem at hand (i.e., qualitative secondary data)

One common—but time intensive—methodology: content analysis
Ex: Collaboration in business

Front 15

Depth Interviews

Back 15

Open-ended interviews with people knowledgeable about the general subject being investigated

Some possibilities:
those who work with it (e.g., employees, consultants)
those who study it (e.g., researchers, analysts)
those who live it (e.g., consumers)

We will talk more about this next lecture

Front 16

Focus Group

Back 16

Group interview facilitated by a moderator
Participants playing off each other Typically 8 – 12 people
Homogeneous within group
1.5 to 2 hours in length
Sessions recorded and transcribed

Front 17

Case Analyses

Back 17

Intensive study of selected examples of the phenomenon of interest
Can include observation
Used for benchmarking, reality checks

Ethnographic study in stores video (RV1)
Especially effective with cases reflecting...
...recent change
...extremes of behavior
...the “best” and “worst” situations

Front 18

Projective Methods

Back 18

Indirect method of getting someone’s opinion
Useful when respondents do not want to talk about a subject
For example:
When respondents do not fully trust the researcher
For studying illegal or unethical behavior
For studying taboo or embarrassing topics

Content analysis or a similar technique is then used to find underlying meaning

Front 19

Projective techniques

Back 19

Role playing

Word association
What words best describe how you feel about each logo?

Sentence completion
People who ride bikes are ________.

Front 20

Why bother with quantitative research?

Back 20

To make guesses about a larger population
Cheaper and easier than conducting a census
Provides evidence

Front 21

Exploratory research is very flexible; descriptive research is MUCH more rigid

Back 21

Descriptive research requires the clear specification of…
WHO, WHAT, WHEN, WHERE, WHY, and HOW
-- before data collection can begin.

Front 22

Longitudinal Analysis

Back 22

Continuous Panels
Discontinuous Panels

Front 23

Continuous Panels

Back 23

Measurements taken on same items from same people over time.

Front 24

Discontinuous Panels

Back 24

Measurements taken on different items from same people over time.
Essentially it is the same group of respondents over a variety of projects.

Front 25

Sample Survey

(Cross-Sectional Analysis)

Back 25

Study in which the sample is selected to be representative of the target population and in which the emphasis is on the generation of summary statistics such as averages and percentages.

Front 26

Causal Research

Back 26

The purpose of causal research is to test cause and effect relationships:
X --> Y
condition X causes event Y

Front 27

Casual: Why questions (does x cause Y)

Back 27

Do people who are in love buy more candy?
More love More candy
Does using fear tactics in commercials actually reduce smoking?
More fear Less smoking
Do younger people prefer sweeter food?
Lower age More preference for sweet food
Do people with bad credit refinance their homes more often?
Worse credit More refinancing

Front 28

Hypotheses

Back 28

Hypothesis: A statement that specifies how two or more measurable variables are related.
(Look at slide for example.)

Front 29

Consistent variation

Back 29

evidence of the extent to which X and Y occur together or vary together in the way predicted by the hypothesis

Front 30

Time order

Back 30

evidence that shows X occurs before Y

Front 31

Elimination of other explanations

Back 31

evidence that allows the elimination of factors other than X as the cause of Y

X—the cause (independent variable)
Y—the effect (dependent variable)

Front 32

Experimental design is the “correct” way of testing causality

Back 32

It is often not practical to actually conduct in business
Therefore, we often use surveys instead

Front 33

Experiment:

Back 33

A test under controlled conditions that is made to examine the validity of a hypothesis

Front 34

Experiments

Back 34

Assign people into groups
Condition group vs. Control group

Front 35

Internal validity:

Back 35

Internal validity: extent to which observed effect can be attributed to experimental variable and not to other factors. Lab experiments tend to have higher levels of internal validity.

Front 36

External validity:

Back 36

External validity: extent to which observed effect can be generalized to particular populations and situations. Field experiments tend to have higher levels of external validity.

Front 37

Secondary Data

Back 37

Information not gathered for the immediate study at hand but for some other purpose.

Front 38

Primary Data

Back 38

Information collected specifically for the investigation at hand.

Front 39

The Balancing Act with Secondary Data

Back 39

POTENTIAL
ADVANTAGES
Time
Cost

POTENTIAL
DISADVANTAGES
Fit
Accuracy

Front 40

Assessing the Accuracy of Secondary Data

Back 40

Primacy of Source
Primary Source
Secondary Source
Purpose of Publication
Who sponsored the research?
General Evidence of Quality
Ability of researchers
Process of data collection

Front 41

Types of Secondary Data

Back 41

Internal Data
External Data

Front 42

Internal Data

Back 42

Data that originate within the organization for which the research is being done.

Most studies should begin with a search for internal secondary data.

Front 43

External Data

Back 43

Data that originate outside the organization for which the research is being done.

Front 44

Types of Data Collection

Back 44

Secondary Data
and
Primary Data

Front 45

Internal Secondary Data Sources

Back 45

Cash register receipts
Sales invoices
Financial records
Credit memos
Salespersons’ call reports
Salespersons’ customer/prospect records
Warranty cards
Salespersons’ expense accounts
Previous marketing research reports

Front 46

Analyzing “thick” data

Back 46

If the data consists of numbers, you can analyze it using statistics
If the data consists of words, you should:
“Convert” it to numbers
Try to draw conclusions directly
But your conclusions will be biased

Front 47

Coding

Back 47

Initial coding
and
Focused coding

Front 48

Initial coding

Back 48

the first stage in classifying and assigning meaning to pieces of information for data analysis.
Numerous codes are generated while reading through responses without concern for the variety of categories.

Front 49

Focused coding

Back 49

the second stage of classifying and assigning meaning to pieces of information for data analysis.
Coding categories are eliminated, combined, or subdivided, and the researcher identifies repeating ideas and larger underlying themes that connect codes.

Front 50

Content Analysis

Back 50

What is measured?Any or all of the following can be measured:
Frequency
Direction
Intensity
Space

Front 51

Frequency

Back 51

how many times does something occur, eg. a particular word, theme, stereotype?

Front 52

Direction

Back 52

the direction of the messages, e.g. positive or negative; supporting or opposed

Front 53

Intensity

Back 53

the strength or power of the direction, e.g. strongly supporting  strongly opposed

Front 54

Space

Back 54

how much space does a particular message occupy (e.g. paragraphs in an article, duration in a film or advertisement)

Front 55

Content Analysis - quantitative

Back 55

Codes need to be clearly defined so categories are comprehensive and mutually exclusive

Pilot studies are useful to check coding categories

If multiple coders are used, coding must be cross-checked to ensure consistency

Front 56

Setting/Context

Common types of coding categories

Back 56

Setting/Context codes provide background information on the setting, topic, or subjects.

Front 57

Defining the Situation

Common types of coding categories

Back 57

Defining the Situation codes categorize the world view of respondents and how they see themselves in relation to a setting or your topic.

Front 58

Respondent Perspective

Common types of coding categories

Back 58

Respondent Perspective codes capture how respondents define a particular aspect of a setting. These perspectives may be summed up in phrases they use, such as, "Say what you mean, but don't say it mean."

Front 59

Respondents' Ways of Thinking about People and Objects

Common types of coding categories

Back 59

Respondents' Ways of Thinking about People and Objects codes capture how they categorize and view each other, outsiders, and objects. For example, a dean at a private school may categorize students: "There are crackerjack kids and there are junk kids."

Front 60

What to do with the coded data?

Back 60

Try to create hypotheses my connecting the coded data
For example:
You notice a theme about going to parties in your interviews
Marketing majors tend to have a positive attitude towards parties while Finance majors do not
One hypothesis would be:
H1: marketing majors like going to parties more than finance majors.

Front 61

Why Use Observation Research?

Back 61

Observation is often the best method for generating valid data about individuals’ behavior.

Front 62

Structured Observation

Back 62

The problem has been defined precisely enough so that behaviors that will be observed can be specified beforehand, as can the categories that will be used to record and analyze the situation.

Front 63

Unstructured Observation

Back 63

The problem has not been specifically defined, so a great deal of flexibility is allowed the observers in terms of what they note and record.

Front 64

disguised observation

Back 64

With disguised observation, subjects are not aware that they are being observed (e.g., mystery shoppers).
Ethical considerations  Debriefing

Front 65

undisguised observation

Back 65

With undisguised observation, subjects know that they are being observed.

Front 66

Natural Setting

Back 66

Subjects are observed in the environment where the behavior normally takes place

Shopping in a store
Using or consuming a product at home

Front 67

Contrived Setting

Back 67

Subjects are observed in an environment that has been specially designed for recording their behavior

“fake” store
computer simulation

Front 68

human observation

Back 68

With human observation, individuals are trained to systematically observe a phenomenon and to record on the observational form the specific events that take place.

Front 69

mechanical observation

Back 69

With mechanical observation, a mechanical device observes the phenomenon and records the events that take place.

Front 70

Examples of Mechanical Observation

Back 70

Video cameras
Bar code scanners
Response latency
Galvanometer
Voice-pitch analysis
Eye camera

Front 71

Interviewing

Back 71

Purpose of Interviewing: to capture the other person’s perspective
Main concerns:
depth
detail
meaning

Front 72

Advantages of using interviews

Back 72

Enable us to learn about things that cannot be directly observed
Add an inner perspective to outward behaviors
Allows for probing
Respondents can raise concerns
Enable modification to lines of inquiry
Refining questions

Front 73

Disadvantages of using interviews

Back 73

Very time consuming
Expensive
Usually sample size is small
Quality of information obtained is largely dependent upon the interviewer
Subject to interviewer bias
Subject to respondent bias

Front 74

Before the interview

Back 74

Research blueprint:
Sample size
Interview structure
Interview medium
Number of interviews per person
Interview analysis method

Front 75

How big should an interview sample size be?

Back 75

Remember, interviews are not generalizable to a greater population
Therefore, sample size can be determined either by:
Interviewing until information becomes redundant
Best for looking for generalizable trends
2 interviews per relevant category
Best for looking for differences between groups or exceptions to the norm

Front 76

Mediums for interviewing

Back 76

Face-to-face
Telephone
Written

Front 77

Approaches to Qualitative Interviewing:

Back 77

Informal conversational interview (unstructured)
General interview guide approach
(semi-structured)
Standardized open-ended interview (structured)

Front 78

Unstructured interview:

Back 78

Resembles a conversation
informants may sometimes forget that they are being interviewed
Most of the questions asked will flow from the immediate context
Useful for exploring interesting topics for investigation
Typical of ‘ongoing’ participant observation fieldwork

Front 79

Semi-structured interview (commonly called guided interview)

Back 79

Basic checklist of questions are prepared
To make sure all relevant topics are covered.
The interviewer is still free to explore, probe and ask questions.
Useful for eliciting information about specific topics.
Allows for in-depth probing
WHILE still keeping the interview within the parameters of the study.

Front 80

The standardized open-ended interview

Back 80

A set of open-ended questions
Carefully worded and arranged
For the purpose of minimizing variation in the questions posed to the interviewees.
Useful when two or more researchers are involved in the data collecting process.
Less flexibility
Probing is less possible

Front 81

How many interviews per participant?

Back 81

Participants can be interviewed multiple times
Increase rapport between respondent and interviewer
Prevents boredom when a lot of information is needed
More difficulty securing permission
Different interviews can be different styles based on your needs

Front 82

Analysis

Back 82

Multiple interviewers
Taping interviews
Content analysis

Front 83

During the interview...

Back 83

Encourage a free rein but maintain control
Don’t lose sight of your research interest
Gently guide respondents through probing questions if they get off track
Try not to interrupt

Front 84

During the interview...

Back 84

1. Ask clear questions
easy to understand
short
devoid of jargon
2. Ask single questions
3. Ask truly open-ended questions
Do not pre-determine the answers
Satirical example of predetermining an answer (from the Colbert Report):
“George Bush: Great president or the greatest president?

Front 85

During the interview

Back 85

Ask experience/behavior questions before opinion/feeling questions
Sequence the questions
Using funneling
Ex: All babies cry, of course. Some mothers feel that if you pick up a baby every time it cries, you will spoil it. Others think you should never let a baby cry for very long.
Broad: How do you feel about this?
Specific: How about the middle of the night?
More specific: What about on nights when you have to work the next day?

Front 86

Probe & follow-up questions

Back 86

The purpose of probing is to deepen the response to a question

Front 87

Interpret questions

Back 87

Researchers should clarify interviewee’s statements to avoid misinterpretations.
Ex: “Is it correct that you feel that……?";

Front 88

During the interview

Back 88

Probe & follow-up questions
Interpret questions
Follow up on Non-verbal cues such as laughter
Tolerate silence

Front 89

5 probing techniques

Back 89

Procuring details
Faking puzzling
Encouraging
Interject understanding
Acknowledging

Front 90

Procuring details

Back 90

Procuring details
Asking further questions to see if more information can be obtained.

Front 91

Faking puzzling

Back 91

Faking puzzling
Pretending to be confused, indicating elaboration is needed.

Front 92

Encouraging

Back 92

Encouraging
Giving compliments to encourage the informants to carry on.

Front 93

Interject understanding

Back 93

Interject understanding
Making the informant know that his/her comments are understood and treasured + allowing him/her time for further comments.

Front 94

Acknowledging

Back 94

Acknowledging
Repeating the informant’s answer to show attention.

Front 95

Ethical considerations of interviewing

Back 95

Be careful to ensure sensitive information won’t hurt the respondent
Get permission of guardian when interviewing children
Institutional review board (IRB)
For research that is intended to be published
MUST get IRB approval