MKT RESEARCH EXAM 2 MAIN

Qualitative Research:

collection of data in the form of text or images using open-ended questions, observation, or 'found' data (OPEN ENDED) understanding- "the why"

When would you choose qualitative research?

when you need to explore complex, ill-defined problems, answer "how" or "why" questions, and understand human experiences, context, or motivations in deep detail

Pros/ Cons of qualitative research:

Pros: Deep context, High flexibility, Early-stage utility

Cons: Small sample sizes, Subjective bias, Time-intensive:

Quantitative Research:

uses formal standard questions and predetermined response options in surveys of large samples (the validation) -typically a longer time frame

Pros/ Cons of quantitative research:

Pros: Statistical confidence, High objectivity, Fast analysis

Cons: Lacks depth, Rigid design, Misses the "why"

The Qualitative Research process:

1) Data Reduction

2) Data Display

3) Conclusions

4) Peer Review

Data reduction is basically what?

Content Analysis

Data reduction is the process of what?

Process of taking transcripts and reducing it to a neat table (to the most important ones)

Content Analysis consists of what?

Interrelated processes (starting with transcript):

• Categorization and coding

• Comparison

• Theory building

• Iteration & negative case analysis

• The role of tabulation (keeps the researcher honest)

Data Display examples:

- A table that explains central themes in the study

- A diagram that suggests variable relationships (i.e., conceptual model)

- A matrix including quotes (verbatims) for various themes from representative informants

Data Display does what?

-Works with data reduction

-Visuals help summarize

-It is easier to digest

Conclusion (Drawing/ Verification):

- checking for common biases

- credibility in qualitative research

-Emic validity

-Cross- researcher reliability

-Triangulation

-Peer review

Credibility:

The degree of rigor, believability, and trustworthiness established by qualitative research

Emic validity:

Affirms that key members within a culture or subculture agree with the findings of a research report (member checking)

Internal Validity:

The extent to which the research design accurately identifies causal relationships.

EX: Laboratory experiments

External validity:

The extent to which a causal relationship found in a study can be expected to be true for the entire target population.

EX: Field experiments

What is the last step of the research report?

Conclusions and recommendations/ suggestions

Cross- researcher reliability:

The degree of similarity in the coding of the same data by different researchers (interrater reliability)

Triangulation:

Looking at data from different perspectives to establish credibility- Addressing the analysis from multiple perspectives

• Using:

- Data collection and analysis

- Multiple data sets

- Multiple researchers

- Multiple time periods

- Different kinds of relevant research informants

EX of triangulation:

yelp, trip advisor and google reviews

Peer review:

-One of many ways to increase credibility in a qualitative report

A process in which external qualitative methodology or topic area specialists are asked to review the research analysis

Methodology

lays out how you do the research (who participated)

Sampling errors in research:

-The difference between the findings based on the sample and the true values for a population

sampling errors in research can be caused by what?

Caused by the method of sampling used and the size of the sample (non sufficient sample sizes)

How can sampling errors in research be reduced?

• Increasing sample size

• Using the appropriate sampling method

Types of nonsampling errors:

Respondent errors

nonresponse errror

response error

Bad questions are a source of.....

nonsampling error

Respondent Errors:

Consist of both nonresponse error and response error

Nonresponse error:

A systematic bias that occurs when the final sample differs from the planned sample (b/c a sufficient number of sample respondents refuse to participate or cannot be reached) (ANY KIND OF ERROR)

EX of Nonresponse error:

doing a study of consumers you want diversity (senior citizens) not going to send the survey out on tiktok because they are never going to see that link. Not going to respond to that

Key characteristics of nonsampling errors:

1. They create "systematic variation" (bias) in data

2. They are controllable

3. Cannot be directly measured (unlike random sampling error)

4. One nonsampling error can create others

Response error:

When respondents have impaired memory or do not respond accurately

Topic sensitivity:

The degree to which a survey question leads a respondent to give a socially acceptable response.

Exploratory research:

A design classification focused on discovering initial insights (part of market research designs)

exploratory research is considered....

qualitative research

Descriptive research:

Quantitative research that uses numbers and statistics (mean, median, standard deviation) to summarize demographics, attitudes, and behaviors. Divided into cross-sectional and longitudinal designs. (WHO, WHAT, WHERE & HOW)

Casual (PREDICTIVE) research:

Studies that enable researchers to assess "cause-effect" relationships between two or more variables

-what do customers think of our service quality?

Lab experiments:

Conducted in an artificial setting; more likely to be internally valid.

Field experiments:

Manipulate independent variables in natural or real settings to measure dependent variables; more likely to be externally valid (e.g., Test Marketing).

Validity:

The extent to which the conclusions drawn from an experiment are true

Qualitative counterparts:

-Credibility

-Emic validity

-Cross researcher reliability

-Triangulation & peer review

Probability sampling:

Each sampling unit in the defined target population has a known probability of being selected for the sample

What is probability sampling necessary to do?

It is necessary for making inferences about the population

Nonprobability sampling:

Sampling designs in which the probability of selection of each sampling unit is not known

EX of probability sampling methods:

-Simple random sampling

-Systematic random sampling

-Stratified random sampling

-Cluster sampling

EX of nonprobability sampling methods:

-Convenience sampling

-Judgment sampling

-Quota sampling

-Snowball sampling

Simple random sampling:

Every sampling unit has a known and equal chance of being selected

(e.g., all names in a hat)

-Produces unbiased estimates of population variables

Systematic random sampling:

Target population is ordered and selected systematically using a skip interval.

Stratified random sampling:

Separation of the target population into different groups, called strata, and the selection of samples from each stratum

• e.g., Heider students by classification (fr/so/jr/sr)

Cluster sampling:

Sampling units are divided into mutually exclusive and collectively exhaustive subpopulations (clusters); includes area sampling based on geographic designations.

Convenience sampling:

Samples are drawn at the convenience of the researcher

-Usually more common at earlier stages of research

Judgment sampling:

Participants selected according to an experienced individual's belief that they meet study requirements.

Quota sampling:

Participants are selected according to pre-specified quotas regarding demographics, attitudes, behaviors, or some other criteria (DIVERSITY IS NEEDED)

Snowball sampling:

A set of respondents is chosen, and they help the researcher identify additional people to be included in the study

- A.K.A. referral sampling

How can you reduce sampling error?

Increasing the sample size

Using an appropriate probability sampling method

Correlation does not equal what?

Causation

Causation requirements:

requires experimentation- which is not easy to do

Questionnaire development:

Step 1: Confirm research objectives.

Step 2: Select appropriate data collection method (usually following a "General-to-Specific" pattern).

Step 3: Develop questions and scaling.

Step 4: Determine layout and evaluate questionnaire.

Step 5: Obtain initial client approval.

Step 6: Pretest, revise, and finalize the questionnaire.

Step 7: Implement the survey.

Construct Development:

The process by which researchers identify characteristics that define the concept being studied (defining your constructs)

What is the first step in creating a scale to measure something?

Construct development

Reliability:

Refers to the extent to which a scale can reproduce the same or similar measurement results in repeated trials (consistency)

face validity:

One of the types of scale validity used to evaluate measurement scales.

Structured questions:

Closed-ended questions that require the respondent to choose from a predetermined set of responses or scale points (response process is faster)

EX of structured questions:

multiple choice, disagree or agree (easy and quick to answer)

Unstructured questions:

Open-ended questions formatted to allow respondents to reply in their own words (no constraints)

EX of unstructured questions:

open ended questions- given in depth information if answered

Bad questions:

Any questions that prevent or distort the fundamental communication between the researcher and the respondents (it is a source of nonsampling error)

EX of bad questions:

- Unanswerable

- Leading

- Loaded (assumptive)

- Double-barreled

- Includes jargon

- Double negatives

- Poor answer scale options

Skip questions:

Used if the next question (or set of questions) should be responded to only by respondents who meet a previous condition

• Online survey software is helpful for these

Screening questions:

Identify qualified prospective respondents

- Prevent unqualified respondents from being included in the study

Nominal scale:

The most basic and least powerful scale where questions require respondents to provide only some type of descriptor as the raw response

EX of nominal scale:

Demographics, marital status

-most basic, least powerful; report counts, mode

Ordinal scale:

A scale that allows a respondent to express relative magnitude between the answers to a question

EX of ordinal scale:

orders, incomes, ages

-reports: mode, median, frequencies and range

Interval scale:

A scale that demonstrates absolute differences between each scale point

EX of interval scale:

Celcius/ Fahrenheit

-report mode, median, mean and standard deviation

Ratio scale:

A scale that allows the researcher not only to identify the absolute differences between each scale point but also to make comparisons between the responses

EX of ratio scale:

Weight, kelvin (temperature), age groups (18-24)

-Has a true zero point

-highest level (most advanced)

Likert scale:

An ordinal scale format that asks respondents to indicate the extent to which they agree or disagree with a series of statements about a subject

• Usually treated as an interval scale

Semantic differential scale:

A unique bipolar ordinal scale format that captures a person's attitudes or feelings about a given object (POLAR OPPOSITES)

Constant-sum scales:

Require the respondent to allocate a given number of points, usually 100, among each separate attribute or feature relative to all the other listed ones

Single item scale:

A scale format that collects data about only one attribute of a construct

Multiple item scale:

A scale format that simultaneously collects data on several

attributes of an object or construct (MOST PREFER)

Person administered survey:

In-home interview: Takes place in the respondent’s home or work environment.

Mall-intercept interview: Shopping patrons are stopped and asked for feedback during a mall visit.

Telephone-Administered Survey

Traditional telephone interview: Conducted over the phone from a central location or interviewer’s home.

Computer-assisted telephone interview (CATI): A computer assists in the telephone interview.

Wireless phone surveys: Data collected via wireless phones (text-based or Web-based)- IMMEDIATE RESPONSE

types of self-Administered surveys:

-mail survey

-online surveys

-mail panel survey

-drop-off survey

Mail survey:

Questionnaires distributed and returned via postal service or overnight delivery (EXPENSIVE)

Online survey:

The Internet is used to ask questions and record responses.

*BENEFITS of online surveys:

Low cost per survey

Easy to share (to virtually anyone)

Minimize bias

Quick

Get lots of responses

Mail panel survey:

Mailed to a representative sample who agreed in advance to participate

Drop-off survey:

Left with the respondent to complete later and picked up or returned by mail.

Construct is considered to be....

Intangible and measured with multiple questions

When we do content analysis we keep track of what?

Common themes (tabulation)

Preconceived notions

Discriminatory power on a scale:

The larger the scale = the more power you have

-Makes it easier to distinguish

Questionnaire:

A formal framework (document) consisting of a set of questions and scales designed to generate primary raw data

Despite _________________ ______________, the principles and process behind questionnaire design remain essentially unchanged

technological advances

EX: Pretest of a questionnaire

bring a questionnaire to class for extra credit to determine if it makes sense or is too long

Census:

population count, true/ false questions

-Less time consuming