MKTG 3342 Final Exam

Avoid Double-Barreled Questions

"How satisfied were you with the price and quality of service that you received?" •Price and quality of service are different topics for assessment

Ethnography Quote

"What people say what people do and what people say they do are entirely different things" 1901-1978 Margaret Mead anthropologist

(Likert) Scales

(Likert) Scales are Interval scales with 5, 7 or 10 points that typically measure attitudes **Agree or disagree or 1-7

Survey Question Funnel

(Top part of funnel, Wide) Broad - the category Usage - (frequency, occasions, consideration sets) Attributes that are important Narrow - specific brands Attitudes, perceptions New concepts Future intentions (Bottom of funnel, narrow)

Ethnography (Ellen Isaacs at TEDxBroadway)

- Ethnography grew out of anthropology, then later was applied to industry (and marketing research) - It's about the practice of observing people in their environment

Screener questions

1) Screener questions are used in recruiting for qualitative studies, or at the beginning of a survey. 2) They are structured so that they screen out people who don't fall within your participant qualifications. 3) Each participant qualification should be associated with its own screener question.

Branching

Branching - directing respondents to alternative portions of the questionnaire based on their response to the filter question

Concrete attributes

Concrete attributes: Tangible product features, e.g. taste, brand, appearance

Data

Data - the raw facts, recorded measures of certain phenomena

5) Intentions

Intentions - Anticipated or planned future behavior, like purchase Intent

The differences between Methods of Obtaining Primary Data

Observation vs. Communication

Interval

Scale - Interval Basic Comparison - Comparison of Intervals Examples - Customer Satisfaction Brand Attitudes Average - Mean, Median AND Mode

How do you get participants that meet your qualifications?

With screener questions.

Physiological needs

breathing, food, water, sex, sleep, homeostasis, excretion

Means-End Chains

•Researchers Olson and Reynolds applied the theory of Means-End Chains to the consumer end-state values •Means-end chains are knowledge structures by which consumers represent the connections between products and brands and their own personal needs, goals and values - their self concepts.

Output of Factor Analysis

•Super variables •Groups of variables/attributes that consumer responses cluster around (thus producing segments)

Test Markets (Causal Research in Consumer Marketing - Test Markets)

•Test Markets involve the use of a controlled experiment done in a limited, but carefully selected, section of the marketplace •McDonald's used test markets to determine that a market existed for its own higher-end coffee drinks before beginning large-scale distribution

Principles of Segmentation

•The end goal is to hone in on the most productive segments, so you can create the advertising message that speaks to them (and use ad dollars more effectively. •Identifying unmet needs of a segment can help clearly outline your innovation pipeline and help increase share in your category. •People tend to segment on attitudes, needs and occasions, not demographics

Examples of 5 Key Areas of Insights that Make up Foundational Insights for a Brand

- Are my products/services optimized for our target audience? Do they have the right features and benefits? - How do consumers perceive our brand compared to others in the category? - Who is our best target audience? - What is our differentiated positioning and how should we communicate it? - Who are our competitors and how are they positioning themselves?

Focus groups are useful for...

- Characterizing social and cultural norms - Sharing and comparing (Morgan) - Revealing how people talk about an issue (This is why groups are often done as pre-work to a large, foundational study such as a segmentation study or positioning work) - Exploring potentially sensitive topics

The Iceberg Principle

- The decision maker is standing aboard a ship looking out at an approaching iceberg. - The ship represents the decision problem definition. - The decision maker sees the following obvious measurable symptoms in the iceberg: unhappy customers, decreased market share, loss of sales, and low traffic. - At the same time, the researcher is exploring the iceberg underneath the water and observes real business / decision problems, such as: marginal performance of sales force, inappropriate delivery systems, unethical treatment of customers, poor image, and low-quality products.

Simple regression investigates a straight-line relationship of the type: Y = α + βX

- Where Y is a continuous dependent variable and X is an independent variable that is usually continuous (although a dichotomous nominal or ordinal variables can be included in the form of a dummy variable) - Alpha (α) and beta (β) are two parameters that must be estimated so that the equation best represents a given set of data - These two parameters determine the height of the regression line and the angle of the line relative to horizontal - When these parameters change, the line changes

r2 (r squared)

- r2 describes the variation in the dependent variable associated with the variation in the independent variable. It tells you what percentage of the total variation you can explain. - It varies between 0.00 and 1.00, and is calculated by dividing the explained variation by the total variation in the dependent variable.

Avoid Ambiguous Words and Questions...

-Avoid "problem" words like occasionally, often, rarely, sometimes, usually as they can be imprecise and/or ambiguous

Avoid Leading Questions

-Avoid basically telling respondents how to answer, or even a clue as to how to answer

Observation

-Does not involve questioning respondents -Involves recording respondent's actions -Advantages: objective, accurate Observational research is collecting behavior data with no interaction.

Laboratory Experiment (Experiments as Causal Research)

-Includes a situation with exact conditions •Like a chemistry lab -Control of variables other than X or Y is maximized •Labs are sterile -X variables are manipulated **Lab more like science, can control variables

Field Experiment (Experiments as Causal Research)

-Includes a situation with fluid conditions •Like a retail store -Control of variables other than X or Y is challenging •Store conditions vary -X variables are manipulated **Field like a test market, can NOT control variables

Communication

-Involves questioning respondents -Involves respondents completing a questionnaire -Advantages: versatility, speed, cost Home Interviews with Ethnography is observation plus communication of some type E.g. a Shop a long - observing the shopper, recording, plus questions and discussion, video testimonies, etc. **Traditional ethnography just watching them Shop a long is communication Definitely know where shop along is

** 8 Types of Primary Data

1) Demographic/Socioeconomic 2) Personality/Lifestyle 3) Attitudes 4) Awareness/Knowledge 4A) Usage 5) Intentions 6) Motivation 7) Behavior

Emerging Trends in Marketing Research Five major trends are emerging:

1. Increased emphasis on secondary data collection methods. (CRM, Shopper Marketing) 2. Movement toward technology-related data management. (CRM, Data Warehouses) 3. Expanded use of digital technology. (Mobile surveys) 4. A broader international client base. 5. Movement beyond data analysis toward a data interpretation / information management environment. (AI, as with IBM Watson and Tableau) **Use of AI is most important

4 Key Sample Size Elements

1. Population Size 2. Margin of Error (Confidence Interval) 3. Confidence Level 4. Standard of Deviation

Nonsampling errors have these characteristics.

1. They create "systematic variation" or bias in the data. 2. They are controllable. 3. They cannot be measured directly. 4. They can create other nonsampling errors (e.g. a badly worded question can lead to bad answers).

5 Key Areas of Insights that Make up Foundational Insights for a Brand

1.Product 2.Brand 3.Consumer Segmentation 4.Positioning and Communication 5.Competitive Landscape

Security Screen Example

2A. Are you or is anyone in the household employed in any of the following industries? •Oil and gas industry (for example Shell, Mobil, BP, Chevron, Sunoco etc.) [TERMINATE] •A market research or consumer research company [TERMINATE] •A clothing store or company that makes or sells clothing •A company that manufactures, distributes or sells health care products •None of the above

Survey vs. Questionnaire

A Survey is the tool or method you're using for research, and the Questionnaire is the written out form of your survey questions

histogram

A histogram is a graphical way of showing a frequency distribution in which the height of a bar corresponds to the frequency of a category

Benefit of a histogram

A key benefit of producing a histogram or frequency distribution is to identify outliers in your data - an observation so different from the rest of the observations that the analyst chooses to treat it as a special case (or just delete it, in most cases)

What are participant qualifications?

A list of parameters that define who you want to have in your study. They can include demographics, brand or category usage, geography and more.

A sample survey....

A sample survey...is a more formal term for a survey emphasizing that respondents' opinions presumably represent a sample of the larger target population's opinion

Regression Analysis - What is it?

A statistical technique which analyzes the linear relationship between a dependent variable and multiple independent variables by estimating coefficients for the equation for a straight line.

A survey represents....

A survey represents....a way of describing public opinion by collecting primary data through communicating directly with individual sampling units

**Open-ended vs fixed alternative questions

ADD

1) Demographic/Socioeconomic

ADD

Lays Example

ADD

Abstract attributes

Abstract attributes: Implementation of a concrete attribute, e.g. tasty, easy to prepare

Action, or implications

Action, or implications are how it impacts what you're doing and/or how it should influence your strategy

An advantage of journaling and written responses over focus group discussion is...

An advantage of journaling and written responses over focus group discussion.... is that you get thoughtful, contextual responses to questions or topics, and then you can follow up and chat either individually or as a group to probe further and have people build off of each others' ideas.

Another key advantage of online qualitative....

Another key advantage of online qualitative.... is the ability to recruit people from many different places without the expense of travel and focus group facilities. So it's perfect for any brand or product with national distribution.

Articulation questions

Articulation questions are used in recruiting for focus groups or other types of qualitative studies. They help ensure that your participants are willing to participate with articulate and creative discussion.

3) Attitudes

Attitudes - An individual's overall evaluation of something, such as perceptions about brands, attributes and features that are important to them.

Product factors

Attributes

4) Awareness/Knowledge

Awareness/Knowledge - Insight into, or understanding of facts about something -Unaided recall vs. Aided recall vs. Recognition -Awareness vs familiarity

The Types of Information Gathered Using Surveys

Basically, all the different types of primary data •Questions about product use, desirable features, and Web habits help with product development and advertising messages •Surveys gather information to assess consumer knowledge and awareness of products, brands, or issues and to measure consumer attitudes, feelings and behaviors •The term survey is most often associated with quant research, but certain aspects of surveys may be qualitative (such as open ended survey questions)

7) Behavior

Behavior data - What individuals have done (Purchasing, shopping, visiting, spending) Observing or measuring behaviors vs. asking respondents to remember and report behaviors (Scanner data and Web analytics are both observed behavior)

Leading Questions

Book example - Do you feel that limiting taxes by law is an effective way to stop the government from picking your pocket? Yes No

Breakoff (or drop-off)

Breakoff (or drop-off) - term referring to a respondent who stops answering questions before reaching the end of the survey

Participant qualifications examples

CHEVRON EXAMPLE Overall Participant Objectives/Qualifications •N = 60 •Men and women •Own or lease their own vehicle •Age 21-55 - balanced by US Census age distribution •Mix of different regions nationally •Brand accepters (purchased and/or consider purchasing in the future) •All must be primarily buyers/users of synthetic motor oils •70% Past 12 month purchasers of Chevron Havoline Motor oil, Half have purchased at Walmart •70% are DIY oil changers •Not employed in a sensitive industry

Screener questions examples

CHEVRON EXAMPLE Overall Participant Objectives/Qualifications •N = 60 •Men and women •Own or lease their own vehicle (Q3) •Age 21-55 - balanced by US Census age distribution (Q1) •Mix of different regions nationally (Q2) •Brand accepters (purchased and/or consider purchasing in the future) (Q8) •All must be primarily buyers/users of synthetic motor oils (Q5) •70% Past 12 month purchasers of Chevron Havoline Motor oil (Q6) Half have purchased at Walmart (Q7) •70% are DIY oil changers (Q4) •Not employed in a sensitive industry (Q2a)

Coding open ended responses

Coding open ended responses - the process of transforming raw textual data into categories or classes. The goal is to reduce the great number of individual responses into a much smaller set of general categories.

Confidence Interval is between _____ and ______

Confidence Interval - the actual is somewhere between 85% - 95%

3. Confidence Level

Confidence Level — Your OVERALL CONFIDENCE LEVEL. How confident do you want to be that the actual mean falls within your confidence interval? The most common confidence intervals are 90% confident, 95% confident, and 99% confident.

Confidence level

Confidence level - we're 95% confident that the actual is somewhere between 85% - 95%

Conjoint analysis

Conjoint analysis is the optimal market research approach for measuring the value that consumers place on features of a product or service. This commonly used approach combines real-life scenarios and statistical techniques with the modeling of actual market decisions.

Constant-Sum or Allocation Scale

Constant-Sum or Allocation Scale - is a Ratio Scale that asks the respondent to allocate points among different measures. **Has to equal 100

Convenience Sample:

Convenience Sample: Population elements are sampled simply because they are in the right place at the right time Example - In-store intercepts, or interviewing people in your restaurant

Covariation

Covariation is the amount of change in one variable that is consistently related to the change in another variable of interest. • It is the degree of association between two variables.

What is the first thing you do in the Research Process?

Defining research objectives is the first thing you do. Defining Research Objectives--> Research Design --> Sampling --> Data Collection --> Data Analysis --> Conclusions and Reporting -->

Descriptive analysis

Descriptive analysis is the elementary transformation of data to describe basic characteristics such as central tendency, distribution, and variability - Averages, medians, modes, variance, range and standard deviation typify descriptive statistics - Can summarize responses from large numbers of respondents in a few simple statistics - Sample descriptive statistics are used to make inferences about characteristics of the entire population of interest - Simple but powerful and are used very widely - The level of scale measurement influences the choice of descriptive statistics

Descriptive/Quant and Test Markets happen when?

Descriptive/Quant and Test Markets happen as products are being developed and launched

Ordinal/Ranking Example Interval versus Ordinal (Likert vs Ranking)

EXAMPLE •Rank the mascara brands Clinique Cover Girl Estee Lauder Maybelline Cover Girl ranks #1, and Maybelline #2 and Clinique #4, but you don't know how far apart they are

Interval Scale Example Interval versus Ordinal (Likert vs Ranking)

EXAMPLE •What is your feeling toward each of the following mascara brands (1=Negative, 5=Positive)? Clinique 1 2 3 4 5 Cover Girl 1 2 3 4 5 Estee Lauder 1 2 3 4 5 Maybelline 1 2 3 4 5 -Cover Girl gets an average 4.7 rating -Maybelline gets an average 4.5 rating -Clinique gets a 2.3

Quota Sample Example:

Example - Research Problem: Investigate 100 undergraduate student attitudes toward a controversial new technology fee Known Population Parameters: Class (30% Freshman, 20% Sophomores, 30% Juniors, 20% Seniors) and Gender (50% Female, 50% Male) Approach: 10 students will interview 10 friends each for a total of 100 responses

3 Types of Research Design

Exploratory Descriptive Causal

Exploratory is located where in the process?

Exploratory is at the beginning, during the innovation process

Syndicated studies are considered what type of data?

External data (outside the firm)

Factor analysis

Factor analysis is a way to condense the data in many variables into a just a few variables. For this reason, it is also sometimes called "dimension reduction." You can reduce the "dimensions" of your data into one or more "super-variables."

Factor analysis is useful in:

Factor analysis is useful in: •Condensing variables •Uncovering clusters of responses

**Filter question

Filter question - a question that screens out respondents who are not qualified to answer a second question

Frequency distribution

Frequency distribution - A count of the number of cases that fall into each category when the categories are based on one variable.

Types of Conjoint

Full-Profile Conjoint Analysis Choice-Based Conjoint (Discrete-choice)

Full-Profile Conjoint Analysis

Full-profile conjoint analysis takes the approach of displaying a large number of full product descriptions to the respondent. The evaluation of these packages yields large amounts of information for each customer/respondent. Full-profile conjoint analysis has been a popular approach to measure attribute utilities. By controlling the attribute pairings, the researcher can correlate attributes with profile preferences and estimate the respondent's utility for each level of each attribute tested....and then over all of the respondents. In the rating task, the respondent gives their preference or likelihood of purchase to the total concept.

Functional

Functional: Immediate benefits achieved from experiences with the product e.g. more energy, improve strength

**Funnel technique

Funnel technique - asking general questions before specific questions in order to obtain unbiased responses.

Articulation Question Example

Here's a question to put your imagination to work for a minute. If you were given a million dollars to write a book what would you write about and why would you write about that particular subject? What would the title of your book be?

Histogram is a ...

Histogram is a picture of a frequency distribution Histogram with a normal distribution line

Example of Ambiguous Words

How often do you buy your milk from Walmart? - Never - Sometimes - Occasionally - All the time - Every week - 1-2 times/month - Once a month - 2-3 times/year - Less than 2 times/year - I never buy milk at Walmart Do not say: Never, Sometimes, Occasionally, All the time

How to do Segmentation using Cluster Analysis?

How to do it? •Again, implant the key components into your survey and gather the data •Use cluster analysis to cluster people based on their "like" answers

In-Home Interviews

In home interviews can be a combination of ethnography (just watching and observing how a consumer uses a product in their home) plus in-depth interviews, where the moderator can ask structured questions or exploratory questions based on what they've observed.

Information

Information - transformed and organized facts

** Secondary Data

Information NOT gathered for the immediate study at hand but for some other purpose Often gives good background information and fills in some gaps in the researcher's understanding

** Primary Data

Information collected specifically for the investigation at hand

Insights

Insights - what you learn from the information - key learning/key findings, etc. Insights and Strategic implications Communicating local is key, because it insinuates (or ladders up to) many other important attributes, including pure, clean, taste and quality

Social media, data mining and reviews are considered what type of data?

Internal data (inside the firm)

Interval Scale

Interval Scale -Measurement in which the assigned numbers legitimately allow the comparison of the size of the differences among and between numbers. You can measure the spectrum. -Can Also take on the properties of nominal (identification) and ordinal (rank order) scales

Interval Scale Examples

Interval Scale EXAMPLES: •Brand Attitude: What is your feeling toward each of the following mascara brands (1=Negative, 5=Positive)? Clinique 1 2 3 4 5 Cover Girl 1 2 3 4 5 Estee Lauder 1 2 3 4 5 Maybelline 1 2 3 4 5

Exploratory (What it is good for)

Inventing, Innovation, News

What is the right flow of survey questions or discussion guide topics in a research study?

It's best to start broad, and then move to specifics.

Judgment Sample:

Judgment Sample: Population elements are handpicked because they are expected to serve the research purpose Example - Hire panelists who are knowledgeable about the issue being researched rather than selecting them at random

Question Logic and Skipping

Kick someone out of your survey because they didn't answer the screener question

Knowledge gaps

Knowledge gaps - are important insights about your brand that you haven't acquired yet Plan based on the rigor you need, or based on what you need to add to your overall insights.

Marketing Research is a .....?

Link Consumer <--> Marketer

MEANS END CHAINS

MEANS END CHAINS - The idea of this "construct" is to link (in a consumer's mind) a product's attributes to functional and emotional benefits, and ultimately to instrumental and terminal (core) values that are important to them in their life.

2. Margin of Error (Confidence Interval)

Margin of Error (Confidence Interval) — No sample will be perfect, so you must decide how much error to allow. The confidence interval determines how much higher or lower than the population mean you are willing to let your sample mean fall. If you've ever seen a political poll on the news, you've seen a confidence interval. For example, it will look something like this: "68% of voters said yes to Proposition Z, with a margin of error of +/- 5%."

**Marketing or business objectives

Marketing or business objectives address what you need to know to move the business. They're related to a business or marketing question, such as a digital advertising strategy, what new products to launch, etc.

Marketing research supports.....

Marketing research supports..... all facets of the marketing function. Through marketing research, the organization gathers and interprets data from the environment for use in developing, implementing, and monitoring the firm's marketing plans

Marketing research

Marketing research.....is the function that links the consumer to the marketer through information. The information is used to: - identify and define marketing problems; - generate, refine, and evaluate marketing actions; - monitor marketing performance; - and improve understanding of marketing as a process.

How Maslow described the pattern through which human motivations generally move.....

Maslow used the terms "physiological", "safety", "belonging and love", "social needs" or "esteem", and "self-actualization" to describe the pattern through which human motivations generally move. This means that in order for motivation to arise at the next stage, each stage must be satisfied within the individual themselves.

Relationships between the types of primary data

Motivations + occasions = need states Core values in motivations are linked to lifestyle (Lifestyle + core values influence motivations)

6) Motivation

Motivations - why people behave as they do. Links to drivers, need states and core values

Multicollinearity

Multicollinearity - the fact that some independent variables are so closely related that you can't really measure their impact separately

Natural Language Processing

Natural Language Processing - Natural language processing is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human languages, in particular how to program computers to process and analyze large amounts of natural language data

Nominal Scale

Nominal Scale - Measurement in which numbers are assigned to objects or classes of objects solely for the purpose of identification. It's about classification.

Nominal Scale Examples

Nominal Scale EXAMPLES: •Gender: 1=Female, 2=Males •Brand Purchase: Did you purchase Cover Girl mascara? 1=Yes, 2=No

Nonprobability Sample:

Nonprobability Sample: A sample that relies on personal judgment in the element selection process -Used when you don't know the exact # of your total target population. Most common in marketing research Convenience Judgment Snowball Quota

Nonresponse error

Nonresponse error occurs then a sufficient number of preselected respondents do not participate.

Nonsampling Error

Nonsampling error: error that arises in research that is not due to sampling

Cheetos Example

Occasion (after school snack) + Motivation (want something craveable) = Need state (Mindless Nibbling)

Scatter diagram

One way of visually describing the covariation between two variables is with the use of a scatter diagram. --> A scatter diagram plots the relative position of two variables using horizontal and vertical axes to represent the variable values.

Online qualitative

Online qualitative is a great way to gather both in-depth exploratory insights and structured data.

**Order bias

Order bias - results when a particular sequencing of questions affects the way a person responds or when the choices provided as answers favor one response over another.

Ordinal Scale

Ordinal Scale - Measurement in which numbers are assigned to data on the basis of some order (e.g., more than, greater than) of objects. Ranking falls here.

Ordinal Scale Examples

Ordinal Scale EXAMPLE: Rank the following mascara brands (1=Most preferred, 4=Least preferred) __ Clinique __ Cover Girl __ Estee Lauder __ Maybelline

Abraham Maslow's Hierarchy of Needs

People started to read and study about Abraham Maslow's Hierarchy of Needs, in his 1954 book Motivation and Personality Self-actualization Esteem Love and belonging Safety needs Physiological needs

2) Personality/Lifestyle

Personality/Lifestyle - A person's core values that can influence their attitudes, perceptions and behaviors.

1. Population Size

Population Size — What groups are you trying to measure? For instance, if you want to know about mothers living in the US, your population size would be the total number of mothers living in the US.

Probability Sample:

Probability Sample: A sample in which each target population element has a known, nonzero chance of being included in the sample Example: The lottery Simple Random Systematic Stratified

Psychosocial

Psychosocial: Emotional benefits achieved from experiences with the product e.g. trust in authority

Qualitative data

Qualitative data •Data that are not characterized by numbers but rather, are textual, visual, or oral •Focus on stories, visual portrayals, meaningful characterizations, interpretations, and other expressive descriptions

Qualitative marketing research

Qualitative marketing research -Addresses marketing objectives through techniques allowing the researcher to provide elaborate interpretations of market phenomena without depending on numerical measurement -Focuses on discovering true inner meanings and new insights

Qualitative research

Qualitative research is interested more in qualities than quantities Chemists sometimes use the term qualitative analysis referring to research that determines the makeup of some compound -The focus is on the inner meaning of specific chemicals—their qualities

Uses of Qualitative Research:

Qualitative research is useful when: 1. The research objective is to develop a detailed and in-depth understanding of some phenomena 2. The research objective is to learn how consumers use a product in its natural setting or to learn how to express some concept in colloquial terms 3. The behavior the researcher is studying is particularly context-dependent 4. A fresh approach to studying the problem is needed E.g. In-home interviews or shop-alongs

Contrasting Qualitative with Quantitative Methods

Qualitative research results are researcher-dependent, or subjective -Different researchers may reach different conclusions based on the same data Qualitative research usually involves smaller samples than the typical quantitative study - Acceptable in discovery-oriented research - Smaller sample sizes do not necessarily equate to cost savings

Quantitative data

Quantitative data Represent phenomena by assigning numbers in an ordered and meaningful way

Quota

Quota - Most common in marketing research studies

Quota Sample:

Quota Sample: Sample chosen so that the proportion of sample elements with certain characteristics is about the same as the proportion of the elements with the characteristics in the target population. This is called balancing the sample

Ratio Scale

Ratio Scale -Measurement that has a natural, or absolute, zero and therefore allows the comparison of absolute magnitudes of the numbers -Can also take on the properties of nominal (identification), ordinal (rank order), and interval (rating) scales

Ratio Scale Example

Ratio Scale EXAMPLE: •Units Sold: How many cases of each of the following mascaras were sold last month? Clinique _____ cases Cover Girl _____ cases Estee Lauder _____ cases Maybelline _____ cases

Causal (What it is good for)

Real World - Predicting

Research Planning

Research Planning - You can plan based on the rigor you need, or based on what you need to add to your overall insights.

Research Program

Research Program - Numerous research studies that come together to address multiple, related research questions.

Research Project

Research Project - a single study addressing one or a small number of research objectives.

**Research problems

Research problems outline the purpose of the research, and/or the situation that's causing you to ask questions and need insights. It's what you'll learn, OR what you don't know.

**Research questions

Research questions relate to actual questions you'll ask the consumer that lead to insights.

Researcher-dependent

Researcher-dependent: Researcher must extract meaning from unstructured responses, e.g., text from a recorded interview or a collage representing the meaning of some experience

Respondent error

Respondent error - Respondent errors occur when respondents cannot be reached, are unwilling to participate, or respond untruthfully. •Nonresponse error •Response error

Full-Profile Conjoint Analysis (Important Facts)

Respondent rates a series of full concepts as a whole Concepts contain different sets of attributes or features Output is a utility score for each attribute

Discrete Choice Conjoint (Important Facts)

Respondent rates a series of full concepts as a whole Sets of concepts are varied to mimic different sets of choices Output is a score for different combinations of concepts, and a diminishing returns score

Respondents

Respondents....are the people who answer questions during a survey

Response error (short definition)

Response error is about human memory, or misunderstanding

Response Error

Response error is about human memory, or misunderstanding •An individual provides a response to an item, but the response is inaccurate for some reason •Possible causes of response error include -Does the respondent understand the question? -Does the respondent know the answer to the question? -Is the respondent willing to provide the true answer to the question? -Is the wording of the question or the situation in which it is asked likely to bias the response?

Descriptive (What it is good for)

SAMPLES - Measure and Assess has Longitudinal, Cross-sectional

Types of Errors

Sampling Error Nonsampling Error

Sampling error:

Sampling error: The difference between results obtained from a sample and results that would have been obtained had information been gathered from about every member of the population

Sampling error:

Sampling error: the difference between results obtained from a sample and results that would have been obtained had information been gathered from or about every member of the population 1. Sampling error is decreased by increasing sample size 2. Can be estimated (assuming probability sample) 3. Usually less troublesome than other kinds of error

Nominal

Scale - Nominal Basic Comparison - Identity Examples - Gender Brand Purchase (Yes/No) Average - Mode

Ordinal

Scale - Ordinal Basic Comparison - Order Examples - Rankings Average - Median AND Mode

Ratio

Scale - Ratio Basic Comparison - Comparison of Absolute Magnitudes Examples - Units Sold Income Average - Geometric & Harmonic Means, Mean, Median, Mode

Secondary research is what type of research when looking at trends?

Secondary research is exploratory research when looking at trends

Security questions

Security questions screen out participants that are employed in the same industry that you're studying, or in the marketing research industry. They are used in both qualitative and quantitative studies.

Segmentation using Cluster Analysis

Segmentation is about segmenting your audience into different groups, to be able to tailor messages and optimize ad dollars spent.

Semantic-Differential Scales

Semantic-Differential Scales - are Interval Scales that include endpoints that are opposites. **Opposite

Sentiment analysis

Sentiment analysis - the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer's attitude towards a particular topic, product, etc. is positive, negative, or neutral.

Simple Random Sample:

Simple Random Sample: Randomized drawing Example - Sample is drawn by a computer or from a physical list using a random number table

Snowball Sample:

Snowball Sample: Initial sample chosen by a probability technique (e.g., systematic sampling) then the population elements are asked for referrals of others they know who might be interested in participation Example - Find 10 moms in Sacramento with kids under 18, then ask them for referrals of others (then screen for all of the participant requirements)

Sources of nonsampling error -

Sources of nonsampling error - •Respondent error. •Study design errors. •Questionnaire design error. •Project administration errors.

4. Standard of Deviation

Standard of Deviation — How much variance do you expect in your responses? Since we haven't actually administered our survey yet, the safe decision is to use .5 - this is the most forgiving number and ensures that your sample will be large enough.

Survey blocks

Survey blocks - sections of a questionnaire that feed the respondent a set of related items that often deal with one unique condition of an experiment

Systematic Sample:

Systematic Sample: Sample in which every kth element (k = sampling interval) in the population is selected for the sample pool after a random start

Text analytics

Text analytics - Text Analytics is the process of drawing meaning out of written communication. In a customer experience context, text analytics means examining text that was written by, or about, customers.

Discrete Choice Conjoint

The Choice-based conjoint analysis (CBC) (also known as discrete-choice conjoint analysis) is the most common form of conjoint analysis. Choice-based conjoint requires the respondent to choose their most preferred full-profile concept. This choice is made repeatedly from sets of 3-5 full profile concepts. This choice activity is thought to simulate an actual buying situation, thereby mimicking actual shopping behavior. The importance and preference for the attribute features and levels can be mathematically deduced from the trade-offs made when selecting one (or none) of the available choices. The output of a Choice-based conjoint analysis provides excellent estimates of the importance of the features, especially in regards to pricing. Results can estimate the value of each level and the combinations that make up optimal products.

Cluster Analysis

The goal of cluster analysis is to group data together K-Means Clustering uses machine learning algorithms to allocate data points to the nearest cluster. In consumer segmentation, answers to the survey serve as the data points that determine how consumers cluster together. In our video example, they used K-means clustering to show how to cluster people around three pizza parlors.

There are Four Scales of Measurement

The higher the scale of measurement, the more you can do with the data

The marketing term for Regression Analysis is what....

The marketing term is Key Driver Analysis

core value pyramid

This made a core value pyramid - Values - Consequences - Attributes

Macrotrends

Trends in consumption, attitudes and lifestyles that cross different industries and categories. Can also be a zeitgeist When you cast a wide net at one point in time to capture trends.

4A) Usage

Usage - How a brand or product is used Occasions and frequency (E.g. for restaurants - dayparts, visit frequency) - Level of use - Loyalty vs switchers

Values

Values State of mind consumers are trying to achieve e.g. independence

Person factors

Values Consequences

Implications

We should go as far as we can on communicating local, whether it's the location of the dairy, how many miles the milk travels, making the dairy name prominent, etc.

When do you use a larger scale vs a smaller scale? (with a (Likert) Scale)

When you expect respondents to have wider, varying opinions

Segmentation Study

Why it's done: - Most popular type of high level analytics used in marketing. It's all about Who to target, How to target and Where to target so that you're using your budget effectively - Also identifies Unmet needs (innovation pathways) - Focusing and prioritizing your resources How it's done: Cluster Analysis

Consumer Journey/aka "Experience" Study

Why it's done: •Identify barriers at different customer touchpoints •Identify triggers to purchase at different touchpoints How it's done: Basic Analytics

Conjoint Study

Why it's done: •Most often used to optimize design. •Assigns weights and utility values to features •Can be used for portfolio or line optimization •Example - A conjoint for a new car, where we want to assign values to different potential features How it's done: Conjoint structures - it's about how you structure the survey

Brand Tracker Study

Why it's done: •Similar to A&U, but measures KPIs over time •Overall brand health •Performance with different groups •Example - an annual brand tracker for Dickies that measures awareness of the brand and purchasing behavior, once a year How it's done: Basic Analytics **Do it over and over again

Attitude & Usage Study

Why it's done: •To gauge your overall brand health •To measure Performance overall and Performance with different groups •Creates a funnel that shows how engaged people are with your brand How it's done: Basic Analytics

Why is it best to go from Broad to Specific for survey questions?

Why? To limit perception bias. If you ask about/discuss brand perceptions first, those perceptions might influence they way they feel about category usage, occasions and needs.

Laying out the key variables -

Y = the dependent variable a = the intercept (point where the straight line intersects the y-axis when X=0) b = the slope (change in Y for every 1 unit change in X) X = the independent variables e1 = the error for the prediction

Laddering

You "populate" the core value pyramid through a qualitative research approach called laddering Laddering is the qualitative interviewing technique used to connect the means-end chains (Researchers Olson and Reynolds)

Interval Scale Interval versus Ordinal (Likert vs Ranking)

You can visualize a spectrum of either behavior or attitudes

You typically make the decision of what type of research to do, based on....

You typically make the decision of what type of research to do, based on.... a) the risk vs reward of either doing research or not doing research, and b) where you are in the product life cycle

Ordinal/Ranking Interval versus Ordinal (Likert vs Ranking)

You're forcing a preference, but not learning how similarly people feel about different brands

Love and belonging

friendship, family, sexual intimacy

Self-actualization

morality, creativity, spontaneity, problem solving, lack of prejudice, acceptance of facts

Safety needs

security of: body, employment, resources, morality, the family, health, property

Esteem

self-esteem, confidence, achievement, respect of others, respect by others

The problem definition process includes the following components:

•Agree on the decision maker's purpose for the research. •Understand the complete problem situation. (A situation analysis uncovers the problem's complexity.) •Identify measurable symptoms and distinguish them from the problem. (Clarify the problem - separate out causes and symptoms.) •Select the unit of analysis. •Determine the relevant variables to evaluate.

Systematic Sample Example:

•Example - Research Problem: Investigate 250 undergraduate student attitudes toward controversial new technology fee •Known Population: 5000 students published in the campus directory •Approach: k = 5000/250 = 20 or 1 out of every 20 students on campus will be surveyed. Randomly select the first name then count down 20 names. Select that person to be surveyed and then count down 20 names again. Select that person and so on until you get 250 names.