New User Special Price Expires in

Let's log you in.

Sign in with Facebook


Don't have a StudySoup account? Create one here!


Create a StudySoup account

Be part of our community, it's free to join!

Sign up with Facebook


Create your account
By creating an account you agree to StudySoup's terms and conditions and privacy policy

Already have a StudySoup account? Login here

Exam 1 Study Guide

by: Rebecca Leifer

Exam 1 Study Guide MKTG 4110

Marketplace > Tulane University > Business > MKTG 4110 > Exam 1 Study Guide
Rebecca Leifer
GPA 3.4

Preview These Notes for FREE

Get a free preview of these Notes, just enter your email below.

Unlock Preview
Unlock Preview

Preview these materials now for free

Why put in your email? Get access to more of this material and other relevant free materials for your school

View Preview

About this Document

Exam 1 Study Guide!
Research Analytics
Janet Schwartz
Study Guide
50 ?




Popular in Research Analytics

Popular in Business

This 12 page Study Guide was uploaded by Rebecca Leifer on Wednesday December 9, 2015. The Study Guide belongs to MKTG 4110 at Tulane University taught by Janet Schwartz in Summer 2015. Since its upload, it has received 31 views. For similar materials see Research Analytics in Business at Tulane University.

Similar to MKTG 4110 at Tulane


Reviews for Exam 1 Study Guide


Report this Material


What is Karma?


Karma is the currency of StudySoup.

You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!

Date Created: 12/09/15
Research Analytics Exam 1 Study Guide Intro to Research Analytics • Being customer led - listen to customers, but understand the limitations of what you are getting in some environments • Research Analysis: 3 Skills (1) Backward Market Research • Substantial uncertainty characterizes many important business decisions • Data can help but you have to know where to get it & how to use it • Distinguishing signal from noise • Imagine the end of the process first • What will the final report look like? • What decision alternatives might be implemented? • What information do we need to make a choice among alternatives? • Where to get the data for analysis? • Do they already exist? If not - need to collect data • Design the study • NEED to know vs. NICE to know • Analyze data and make recommendation 1. Formulate the Problem 2. Determine Research Design 3. Design Data Collection Method and Forms 4. Design the Sample and Collect Data 5. Analyze and Interpret the Data 6. Prepare the Research Report (2) Getting Data & Judging Its Quality • Secondary Data • Associations in Data • Descriptive & Survey Data • Exploratory research & Sampling (3) Tools (analysis frameworks) for classic marketing problems • Course Positioning • Research and analytics are necessary for consulting, finance, marketing management, entrepreneurship • Production and evaluation of research is often an analysis’s main job function • Research consumption is necessary for all managers • Respondents’/ Consumers’ Rights • Informed Consent • Privacy • Safety • Be informed of research purpose • Learn of research results • Client’s Responsibilities • To respondents: • Avoid using respondent list for sales leads • avoid deception • To suppliers • Avoid dishonesty 1 • Provide accurate inputs to research • To business partners, investors, colleagues • Decision research, not advocacy research • Non-zero value of information • Supplier’s Responsibilities • Client confidentiality • Freedom from conflict of interest • Proper execution of research • Technically sound • Meet time & budget agreed upon • Limitations disclosed • Typical Analyst Responsibilities • Respondent privacy and confidentiality • Keeping data protected • Reporting any problems/breeches • Company/client use only • Client confidentiality • Cannot share proprietary information • Stick to timelines and budgets • Making Decisions with Imperfect Data • Limited Time —> Have to use the information that’s out there • Difficult to judge the quality • Limited Budget —> Need to know vs. Nice to know • Limited Information —> Data was collected for another purpose •Primary Data: new data collected for current purposes •Secondary: data exists already, was collected for some other purpose •Is data consistent with other independent sources? •What are the classifications? Do they fit needs? •When were numbers collected? Obsolete? •Who collected the numbers? •How were the numbers generated? •No causation from correlation? •PROS •inexpensive •quick •often sufficient •CONS •there is a lot of data out there •numbers sometimes conflict •categories may not fit your needs •data constraints New Product Development •What is the perceived market or business need? •High level view •What does your product do to meet this demand? •Product design •Product implementation •Commercialization •Research & Analytics (Early Stage) 2 •Identifying Market Opportunities & Needs •Qualitative & Quantitative Research •Initial Vetting •Weeding out unfeasible opportunities •Who is your target market? •Who is your competition? •Making some assumptions, when will you become profitable? •Development & Testing •Assessing production costs, identifying desirable features, product positioning, customer input on price, usage and frequency •Analytics •Refine selling price, estimate sales, market size •Predict break even and profitability •Research & Analytics (Late Stage) •Market (Beta) Testing •Produce a prototype or mock up •Testing in typical usage situations •Consider a test market/refine distribution •A/B testing to assess ideal version, pricing •Post-Launch •Advertising, promotion •Impact of sales on existing products •Forecast competition’s movements •CLV, Segmentation •Refine production costs, revenues and profits Secondary Data, Measure Types, Hypothesis Testing •Correlation is a very common analysis —> measures the strength of a relationship between two variables •r statistic •Values range from -1.0 to 1.0 •0 implies no relationship •Measure Types •Nominal: unordered categories •Ex. What is your favorite type of candy? Chocolate, Gummies, Sugar etc. •Ordinal: ordered categories, intervals cant be assumed to be equal •Ex. Rate in order your favorite type of candy? 1st: Chocolate, 2nd: Gummies, 3rd: Sugar •Interval: Equally spaced categories, 0 is arbitrary and units arbitrary •Ex. On a scale 1-10, rate how much you love chocolate •Ratio: Equally spaced categories, 0 on scale means 0 of underlying quantity •Ex. How many times a day do you eat candy? 0, 1, 2, 3+ Elaboration Model, Exploratory Research, Unmet Customer Needs •Statistics / Hypothesis Testing: Step 1 •You should always have a question in mind when doing market research •In most cases your question is a hypothesis about the state of the world •Is the sample representative of the population? •Assurance is more important than tangibles? 3 •State a null hypothesis and an alternative such that they are mutually exclusive •H0 (null): the sample matches the population •Ha (alt): the sample does not match the population •Statistics / Hypothesis Testing: Step 2 •Pick a significance level at which you will reject the null H: •The p-value is then probability of finding the particular observed data assuming the null hypothesis is true •The critical p-value is set to balance two errors: •Type 1: rejecting the null when it is true - more likely with higher values of p (p<.10) (false alarm) •Type 2: failing to reject the null when it is false - more likely with smaller values of p (p < .001) miss •The p-value tells us the probability that we got a result due to chance •Standard cutoffs for significant p-values is frequently cited as the following: •significance: p <= .05 •For simplification, please use this p-value for evaluating hypotheses in this class •No data is perfect, no market research is perfect Real World 1 0 Tinder Hot Not Hit False Alarm Swipe Miss Correct Rejection 4 •Statistics / Hypothesis Testing: Step 3 •Observe your data, calculate your statistic and compare it to the critical value of that statistic •Accept or reject •If the observed p-value is lower than the critical significance level, we reject the null hypothesis •Hypothesis testing summary •You are mostly testing questions •Are Tulane students more likely to be Saints fans? •Answering correctly helps makes decisions •Identifying unmet needs, offering promotions, etc. •Errors can happen, may impact the bottom line •Elaboration Model: elaborating on relationships between variables in order to interpret that relationship •Relationships can be testing by simultaneously adding variables •Gender •Income •SES •Location •Introducing the concept of ‘control’ •Does the relationship between Ivy education and success ‘hold’ when controlling for SES •Causation vs. correlation •Defining control variables is tricky •Easing our way into regression •Market research is about making predictions •Zero order association: simple relationship between two variables (the relationship between two variables without controlling for any other variables) •Partial association: relationship between two variables while controlling for a third Focus Groups & Exploratory Research •Elaboration Model Summary •Understanding the relationships between the variables helps us identify the casual chain •The original relationship between 2 variables (zero order) might be explained by another variable (partial association) •Moderator’s Performance •Building rapport and trust •Facilitating spontaneous discussion •Controlling flow of topic discussion •Balancing participation •Probing and intentional ignorance •Diverging from moderator’s guide •PROS •Interactions can stimulate new ideas •Group pressure can keep thinking realistic •Observe consumers •Data is engaging and easy for clients to understand •CONS 5 •Small slice can lead to a false sense of understanding •Representative sampling issues •Social desirability and moderator influence •Respondent introversion Survey Research, Measurement, Multi-Attribute Attitude Model •Generally interested in obtaining information not already obtainable or directly observable that describe some aspects of the study population •Generally, information is collected only from a fraction of the population •Surveys usually used for descriptive research •Descriptive, not casual (unless experimental) •Nuts & Bolts •process of survey design •problems respondents might have with surveys •scales •ordering of questions •managing respondent willingness to participate •choosing appropriate survey method •Multi-Attribute Attitude Model (MAAM) •consumer attitude toward a product will take into account •how important they rate the attributes •how consumers evaluate individual attributes •Liking for a product as a whole = sum of liking for component parts •Importance •Evaluation of Brand J on attribute I High Areas for improvementKeep up the good work Importance Low Lowest Priority Possible Overkill Poor Strong Performance • MAAM, Quadrant Analysis • Many factors can influence people’s attitudes & preferences •Does preference = purchase? •Do we get the same responses from people over time? Big Data •What is it? •Technology brings new sources of data all the time •Large/complex that traditional applications for analysis and structuring don't apply •Unstructured •Unparsed •Large •Is Bigger, Better? 6 •Not always •Bad data is bad data no matter the size •Incomplete •Cannot distinguish signal from noise •Non-representative •Poor confidence in interpretation •Sentiment analysis •Poor reliability with other measures, limited validity •Privacy and confidentiality issues •Good News •Big, many observations •Timely, can observe changes in attitudes, preferences, sales etc. in real time •Predictive •Inexpensive •The Industry •Requires significant resources •Data storage, management, processing, compression •Tools for analysis and visualization •standard statistical inference approaches don’t apply •Substantial Expertise •Computer scientists, AI experts, statisticians •Web Crawling •Systematic internet browsing •Indexing the internet •Constantly updating web content •Searching for URLs •Downloading the content •Selection criteria •Revisit criteria •Web Scraping •Extracting information from websites •Manually // cut & paste •Automatically // python & pearl •Semantic web vision •Translating web content into usable data •Text processing •Semantic understanding •Artificial Intelligence •Human Computer Interaction Segmentation, Analyzing Competition • Analyzing Competition • How do firms gain advantage in a competitive market? • Positioning: Understanding differentiation and correctly positioning vs. competitive offerings • Recognize that consumers satisfy needs • Which products satisfy those needs and under what conditions? • From consumer perspective • We can map how our product is perceived by consumers relative to the different competing products in the marketplace 7 • Link segmentation and positioning • Customer Defined Competition • How to describe and identify which products are considered substitutes and how close of substitutes they are • Competition can be defined based on individual perceptions and uses • Perceptual Mapping • Physical map of customer perceptions • Visual representation of competition • Observe spatial competition based on which competitors are close to each other as defined by customers • Distance between two brands • Measuring similarity between two brands • Rating of overall similarity • Perceptual attributes • ratings of overall similarity • perceptual attributes: correlation between brands in how they are rated on perceptual attributes • current snapchat of perceptions • reposition by reformulating product or advertising • expense • sustainability • Attribute Based • Give consumers list of brands • Factor Analysis • Output shows • dimensions from factor analysis • attributes most related to dimensions • brand locations • Works best for hard or functional attributes • Mapping Using Similarity Measures • Multi Dimensional Scaling • Advantages • allows mapping products and simultaneously infer attributes • better for softer attributes which we don't verbalize very well • Disadvantages • impractical when the number of products are large • Perceptual Mapping Uses • identify closest competitors • suggest repositioning strategies • suggest advertising themes supporting repositioning • identify brands that should be harvested • identify new product opportunities where some segment not well served by current brands • Validity check: Forecast current market shares • Competition Take Aways • Customer Defined Competition • For customer to chose brand i, brand i must be considered and brand i must be most preferred of brands considered and brand i must be preferred of brands considered • Perceptual Maps 8 • View of how consumers see the market • Forecasting share • Most preferred • More sophisticated models A/B Testing & Casual Research •A/B testing and experimental designs •how to know if something is truly effective •without experiments, you cannot identify the causal chain •companies often don’t experiment, people infer causality from correlation •increases the likelihood of type 1 errors •expensive and preventable mistakes •Disadvantages •expensive •larger sample sizes •many different conditions •logistic and operational challenges •design to supply chain, legal concerns •customer awareness •damage study results, hurt firm reputation •A/B testing mechanics •experimental designs are the best way to test casual hypotheses •random assignment of subjects to conditions •independent variable = hypothesized cause •dependent variable = effect •Elements •R: random assignment of people to one of the groups shown in different rows •EG: experimental/treatment group •CG: control group •X: manipulation •O: measured dependent variable •Control groups bolster internal validity •self selection: people who like your product are likely to sign up for studies with your product •history: an event occurring around same time as treatment that has nothing to do with treatment •maturation: people change pre to post •seasonality: cyclical changes in behavior •testing: pretest causes change in response •Factorial Designs •2 or ore independent variables, each with two or more levels •Managerial Implications of Interactions •If two controllable marketing decision variables interact, implication is that you can’t decouple decisions; must coordinate •can extend framework to tactical segmentation •if A is a controllable decisions variable and B is a potential segmentation variable, interaction means that segments respond differently to some element •Takeaways •Experiments, random assignment to control and experimental groups is key 9 •Factorial designs •main effects and interactions •if two marketing tactics interact, coordinate •when a marketing tactic interacts with customer classification it implies the classification is a potential basis for segmentation •Perhaps sensitivity to some marketing mix variable Conjoint Analysis: Measuring Values and Forecasting Evaluations of Individual Buyers •Limitations •cannot observe true utilities directly, but can reveal overall ratings and calculate utilities that are the same other than a scaling factor •Utilities that we calculate can be used to compare different products •can compare the differences between high and low within an attribute and use that as a measure of attribute importance •CANNOT compare a single level of one attribute to a single level of another attribute meaningfully •Using conjoint analysis to estimate market share of new or modified products •understand tradeoffs, what consumers value and where opportunities are in the market to develop new products and plan product line strategies •estimate market shares for new product introductions and improvements •estimate profitability associated with new product introductions or improvements by integrating price and cost information Multiple Regression in Marketing • Regression • provides a flexible model with wide applicability • approach to regression depends on goals • Promotion analysis: uncover the marginal effects of marketing action on customer response • Conjoint analysis: regression with dummy variable • also want to uncover the marginal effect of each different level of each attribute • Database Marketing: forecast customer response • not particularly interested in the marginal effects of any action but very interested in having an overall model that can predict Y very well • Partial effects: in multiple regression, we technically speak of the coefficients as partial effects because it is the change in Y from a change in X holding everything else in the regression constant • Conjoint Analysis via Multiple Regression • Start with a regression with no collinearity • We had control over the conjoint experiment and set it up with uncorrelated X’s and have measures for all the X’s that respondents were supposed to consider • Dummy Variable Coding • Interpreting coefficients • regression coding can vary, which affects coefficients you get but not the overall implications • What to consider when running regressions • Overloaded Models - multicollinearity 10 • Problem is that the regression includes X variables that are highly correlated with each other • Affects precision of the coefficient estimates • Omitted Variables • regression excludes relevant variables that are correlated with Y and correlated with X’s we include • Affects the coefficient estimate - biased estimate that may not be a good estimate of the relationship in the population Simulated Test Markets and CLV • Simulated Test Market • Research and analysis are an ongoing process • BMR • Data has been collected, analyzed and segments have been identified • Don’t always predict real world market successes • Necessary Steps • Introduce product or service to target audience • Measure response • Project response to full launch • Advantages • Simulated test markets provide additional intelligence • Can save millions by gauging market success • reduce risk • increases efficiency • identifies which direction to move in • increase security • anticipate responses • Testing Pre-Launch v. Post-Launch • New brand/product vs. brand extension • High vs. low competition • High vs. low production costs • Customer Lifetime Value • About • Important metric for firms • Net profit attributed to future relationship with the firm • Shift in focus from quarterly earnings to longterm time horizons • Model and derivatives make several assumptions • Better the data, shorter the model • Calculations • Calculated for a given period • CLV ($) = margin ($)*Retention Rate (%) / ([1+Discount Rate (%)] * Retention Rate (%)) • CLV is a multiple of the margin, adjusted for retention and discounted • Advantages of estimating CLV • Intuitively appealing • Helps marketers determine amount to spend recruiting and retaining customers • Customer Equity • Not all customers have equal value to the firm 11 • Reduces customer churn/increases retention • Disadvantages • Dynamic vs static output model • Changes over time = constant updating • Requires accurate inputs • Where most analysts fail • Don’t compute margins accurately & don’t have good measures of segments and behaviors • Key Points • Refining key estimates about costs, demand, expected profits etc. are crucial to launch success • Getting the right data, making sure it is high quality & properly analyzed is key • Smaller market tests help refine inputs • CLV helps determine long-term strategy • Both approaches require good data 12


Buy Material

Are you sure you want to buy this material for

50 Karma

Buy Material

BOOM! Enjoy Your Free Notes!

We've added these Notes to your profile, click here to view them now.


You're already Subscribed!

Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'

Why people love StudySoup

Jim McGreen Ohio University

"Knowing I can count on the Elite Notetaker in my class allows me to focus on what the professor is saying instead of just scribbling notes the whole time and falling behind."

Janice Dongeun University of Washington

"I used the money I made selling my notes & study guides to pay for spring break in Olympia, Washington...which was Sweet!"

Jim McGreen Ohio University

"Knowing I can count on the Elite Notetaker in my class allows me to focus on what the professor is saying instead of just scribbling notes the whole time and falling behind."

Parker Thompson 500 Startups

"It's a great way for students to improve their educational experience and it seemed like a product that everybody wants, so all the people participating are winning."

Become an Elite Notetaker and start selling your notes online!

Refund Policy


All subscriptions to StudySoup are paid in full at the time of subscribing. To change your credit card information or to cancel your subscription, go to "Edit Settings". All credit card information will be available there. If you should decide to cancel your subscription, it will continue to be valid until the next payment period, as all payments for the current period were made in advance. For special circumstances, please email


StudySoup has more than 1 million course-specific study resources to help students study smarter. If you’re having trouble finding what you’re looking for, our customer support team can help you find what you need! Feel free to contact them here:

Recurring Subscriptions: If you have canceled your recurring subscription on the day of renewal and have not downloaded any documents, you may request a refund by submitting an email to

Satisfaction Guarantee: If you’re not satisfied with your subscription, you can contact us for further help. Contact must be made within 3 business days of your subscription purchase and your refund request will be subject for review.

Please Note: Refunds can never be provided more than 30 days after the initial purchase date regardless of your activity on the site.