Meta Marketing Analytics Professional Certificate Answers - Coursera

Meta Marketing Analytics Professional Certificate Answers - Coursera

Language: English

Developed by marketing analytics experts at Aptly together with Meta marketers, the industry-relevant curriculum is designed to prepare you for jobs that include Marketing Analyst, Marketing Researcher, and more.

You’ll learn basic marketing principles, how data informs marketing decisions, and how you can apply the OSEMN data analysis framework to approach common analytics questions. You’ll learn how to use essential tools like Python and SQL to gather, connect, and analyze relevant data. Plus, common statistical methods used to segment audiences, evaluate campaign results, optimize the marketing mix, and evaluate sales funnels.

Along the way, you'll learn to visualize data using Tableau and how to use Meta Ads Manager to create campaigns, evaluate results, and run experiments to optimize your campaigns. You'll also get to practice your new skills through hands-on, industry-relevant projects.

This certification is part of Meta Career Programmes

Upon successful completion of the program, you’ll:

• Get exclusive access to the Meta Career Programs Job Board—a job search platform that connects you with 200+ employers who have committed to sourcing talent through Meta’s certificate programs, as well as career support resources to help you with your job search.

• Earn both a Professional Certificate and the Meta Digital Marketing Associate Certification, showcasing your skills in social media marketing and the use of Meta Ads Manager to potential employers.

Connect with 200+ hiring partners in Meta’s Career Programs Job Board

Redeem your voucher for the Meta Certified Marketing Science Professional Exam

Learners who pass all 5 courses will receive a one-time voucher to take the 200-101: Meta Certified Marketing Science Professional exam at no cost. You are required to take this exam in order to complete the Meta Marketing Analyst Certificate Program and earn your Coursera certificate.

This course prepare for and Take the Meta Marketing Science Certification Exam

Language: English

Certification URLs:

facebook.com/business/learn/marketing-analytics-certificate-coursera

coursera.org/professional-certificates/facebook-marketing-analytics

Questions:

Course 1 – Marketing Analytics Foundation

Week 1: The Importance of Analytics in Marketing

Jordan is calculating the return on ad spend for an existing marketing campaign. Of the five main use cases for marketing analytics, this is…

• Evaluating effectiveness
• Optimizing sales funnel
• Optimizing marketing strategy
• Finding your audience
• Planning and forecasting

Jordan is testing a new version of some of their advertising material - more images versus more text. Of the five main use cases for marketing analytics, this is…

• Evaluating effectiveness
• Optimizing sales funnel
• Optimizing marketing strategy
• Finding your audience
• Planning and forecasting

Jordan is reworking the checkout flow on their website to reduce friction. Of the five main use cases for marketing analytics, this is…

• Evaluating effectiveness
• Optimizing sales funnel
• Optimizing marketing strategy
• Finding your audience
• Planning and forecasting

PRACTICE QUIZ: BASIC PRINCIPLES OF MARKETING

1. The marketing department or person at a company promotes and sells the products a company makes.

• False
• True

2. Next, a marketer needs to build a message, determine delivery methods, and plan out a campaign for a product.

• False
• True

3. Once a campaign has launched, a marketer needs to optimize and evaluate its effectiveness

• True
• False

4. Next, a marketer needs to… (choose all that apply)

• Find new potential customers
• Plan out the appropriate next steps for their marketing campaign
• Generate a message and story about the product they want to sell
• Determine where and how this message should be delivered

PRACTICE QUIZ: USES OF ANALYTICS IN MARKETING

1. When defining a target audience, it’s too early to incorporate analytics.

• True
• False

2. True or false: The purchase funnel is visualized as a funnel because the assumption is that some people will drop out of the funnel before completing a purchase.

• True
• False

3. The first opportunity a marketer has to use data analytics comes when they are…

• Building out their team
• Identifying their target audience
• Sorting through product reviews
• Creating new products

4. Choose all that apply: Marketing analytics can be used to

• Design the visuals for a marketing campaign.
• Find agencies to help with a marketing campaign.
• Evaluate the effectiveness of a campaign.
• Plan and forecast a campaign.

5. The purchase funnel describes the steps users go through when purchasing a product. Which of the following represents the steps as they follow each other in the funnel?

• Awareness, Interest, Decide, Action
• Interest, Awareness, Decide, Action
• Social, Website, Cart, Checkout
• Browse, Find, Purchase, Review

6. Choose all that apply: Marketing analytics can be used to

• Find agencies to help with a marketing campaign.
• Design the visuals for a marketing campaign.
• Plan and forecast a campaign.
• Evaluate the effectiveness of a campaign.

META MARKETING ANLYTICS COURSERA ANSWERS AND STUDY GUIDE

GRADED QUIZ: USE CASES FOR DATA IN MARKETING

1.When segmenting data collected about people, it’s best…

• To put similar people together into groups and pay attention to the biggest of these groups.
• To start with random groupings and brainstorm on potential campaigns that might appeal to them.
• To single out people who are least similar and gather more information from them.

2. Most advertising platforms provide…

• Design teams that make updates to your ads as needed.
• A money back guarantee.
• Detailed reports to calculate and track the effectiveness of ads.

3. If an ad isn’t performing as well as expected, it’s a good idea to let it run as long as initially planned to gather that data.

• True
• False

4. Jordan is evaluating how many purchases resulted from previous campaigns on different social media platforms to determine what to expect from the money they plan to spend on a new campaign on these platforms. Of the five main use cases for marketing analytics, this is…

• Optimizing marketing strategy
• Finding your audience
• Optimizing sales funnel
• Evaluating effectiveness
• Planning and forecasting

5.When optimizing a marketing campaign, it’s a good idea to…

• Post an ad on a competitor’s social media presence.
• Test different versions of an ad and run them together.

6. Jordan is putting together a survey to learn more about their customers. Of the five main use cases for marketing analytics, this is…

• Finding your audience
• Optimizing marketing strategy
• Optimizing sales funnel
• Planning and forecasting
• Evaluating effectiveness

7. It’s better to have a higher ROAS than a lower one.

• True
• False

8. It’s possible to make educated forecasts of potential success on specific platforms based on historical data.

• False
• True

9. In which of the following marketing functions can marketing analytics help?

• Consumer and market analysis
• Marketing planning
• Advertising effectiveness evaluation
• All of these

10. How did segmentation help James define his target audience?

• Segmentation helped to identify the number of interested people
• Segmentation helped to group the people interested in Snackwall and describe their common characteristics
• Segmentation helped to find the companies with the most employees

11. How can historical data help in the marketing planning phase?

• Historical data for similar events in the past can help predict events in the future and can thus guide the planning process
• Historical data provides you with the number of sales that happened in the past and does give you information about how much budget you have for your marketing.
• Historical data is not very helpful for planning since you cannot predict what will happen in the future.

12. If I spend $1 on advertising and as a result of my ads I have $2 revenue, what would my ROAS be?

• 1
• 2
• 0.5

13. Which of the following are examples of friction in the purchase process?

• When a websites pages load very slowly during the checkout process
• When a website is not loading correctly on your mobile device.
• When the shipping costs are not made clear in the checkout process
• All of the above

Week 2: Marketing Data Sources

PRACTICE QUIZ: UNDERSTANDING DATA MARKETERS USE

1. Offline data is…

• Data that you, the marketer keep in physical notebooks
• Data that is too sensitive to go on the internet
• Data that is gathered from an offline source

2. Online data can be gathered from (Choose all that apply)

• POS data
• Internal, website sales data
• Social media platforms
• Analytics dashboards

3. If your data is sampled, that means…

• It’s a placeholder version of the data you hope to eventually get.
• It’s a small part of the larger set, meant to represent the whole group.
• It’s been pre-checked to ensure that it’s of good quality.

4. First and second party data is…

• Information that a customer knowingly offered to a company or one of their partners
• Information that a customer doesn’t know they’ve given
• Made up data about a potential customer
• Information that is gathered about browsing habits

5. Third party data is just as good as first party data.

• True
• False

6. True Online data can only be gathered from your own website.

• False
• True

7. Random sampling helps to…

• Protect the privacy of the people in the dataset.
• Keep stakeholders informed and engaged by showing them the unexpected.
• Make sure the sampled data is accurately representing the entire dataset.

PRACTICE QUIZ: DATA SOURCES

1. A content management system or CMS allows a content publisher to…

• Pick which ads are going to be shown to specific users.
• Update and edit the content on a website easily.
• Design and code a new website.

2. A web server log generally includes what? (Choose all that apply)

• First name and last name
• Home address
• Unique identifier
• IP address
• Time and date

3. A browser cookie is…

• A small transparent image that tracks behavior on a webpage.
• A text identifier that lives on a server.
• A website-specific piece of formatted text stored in the browser.

4. Cookies are helpful for a marketing analyst, but they aren’t perfect. Some challenges include:

• Cookies can be manually deleted or blocked.
• People don’t use only one browser
• All of the above
• Cookies do not work in mobile apps

5. A tag or a pixel is a…

• A text string that is stored in a browser to make a browsing experience more convenient
• Small piece of code that loads when a visitor lands on a site and can track some actions taken on that page.
• A personalized logo that can be attached to your username
• A hash key used to decrypt PII

6. True or false: an SDK is a piece of code that can be installed in an application to make certain functions easier.

• False
• True

7. An API or Application Programming Interface allows a piece of software to…

• Talk to another piece of software.
• Take control of another piece of software.
• Borrow code from another piece of software.

GRADED QUIZ: DATA SOURCES

1. Taylor runs a website that includes a forum. Taylor is interested in seeing what time of day most people are visiting the forum. To do this, they can…

• Check the SDK
• Check the browser cookies
• Check the server logs

2. Taylor is thinking of including a browser cookie on their website, but they know it will have certain limitations, such as: (Choose all that apply)

• The cookie will need to be updated often
• The cookie will not work in apps on mobile devices
• The cookie will not work across different browsers and devices
• The cookie can be manually deleted by a user

3. Taylor is thinking of including a pixel or tag on their website, some of the most common available options are: (Choose all that apply)

• The Universal Understanding and Gathering tag
• The Google Ads Remarketing tag
• The Google Analytics tag
• The Facebook Pixel

4. Taylor would like to incorporate another company’s cart and checkout flow into the mobile app they are working on. To do this, they can…

• Add another tag or pixel
• Add a SDK with the company’s code
• Store information about checkout in browser cookies

5. Taylor is thinking of using an API to add more features to their website, some good uses for APIs include: (Choose all that apply)

• Tracking a user’s behaviors across multiple sites
• Connecting email address to an email marketing platform
• Syncing in-store availability with online availability
• Sharing purchase information from both in-store and website customers

6. Taylor wants to make it simpler for people to complete a process on their website when they return a second time. To do this, they can…

• Change the server logs
• Use a browser cookie
• Implement a pixel

7. Taylor is trying to find a way for people to post content from their website onto social media without leaving their site. To do this, they can…

• Encourage users to log in with their social media accounts
• Mirror the server logs and send them out
• Incorporate an Application Programming Interface

8. What’s an example of offline data? (Choose all that apply.)

• Name, address, and email collected through a form on the website
• Products purchased tracked through an ecommerce site
• Products purchased tracked through the store’s POS system
• Name, address, and email collected through a sign-up form at the store counter

9. What’s an example of online data? (Choose all that apply.)

• Feedback collected through a focus group
• Number of visitors to the physical store
• Feedback collected through an online survey
• Number of visitors to the website purchase page

10. What is NOT an example of sampled data?

• An Excel with one million raw data entries for each of the one million visitors to a website
• Seeing a pop-up that says “You’ve been randomly chosen to take a survey.”
• Generating a stratified report based on 100,000 data points
• Inviting 10 people from a 100 person pilot to give feedback in a focus group

11. What’s an example of first-party data? (Choose all that apply.)

• A list of emails from another store’s newsletter sign-up
• A list of addresses a business paid for
• A list of emails from your newsletter sign-up
• Customer purchase data from your website store

12. How are Ad Servers and CMS’s different?

• The CMS always delivers the same content and the Ad server adjusts the ads based on the person that accesses the web site
• The CMS picks the ads that the ad server delivers
• The CMS delivers the publisher’s content to a webpage and the ad server fills in the advertising spaces on the page with ads.

13. Which of the following is made possible through the use of cookies?

• Keep you signed in on a website
• All of the above
• Give you locally relevant content
• Adjust the content you see on a site based on your preferences

14. Which of the following is an example of a third-party cookie?

• A cookie from an advertisers network that the publisher uses to deliver ads
• A cookie Facebook stores in the browser when I am visiting my Facebook page.
• A cookie from the publisher of the site you are visiting

15. How does a pixel differ from a cookie?

• A pixel collects data about user behavior on a website and a cookie doesn’t
• A cookie lives in the browser, a pixel is code that is added to a website by the publisher of that website
• A cookie is stored in your browser by the website you are visiting and the pixel is added to a site by a third party

16. Which of the following might you use an API for?

• To connect sales data and email addresses of your customers with an email marketing platform
• To provide information on users who abandoned their checkout cart on your website to an advertising platform
• To send information about the products in your store catalogue to an online shopping platform
• All of the above

17. Which of the following is an example of the way in which an API could be used?

• All of these examples describe uses of an API
• An API can help make it possible to let users use their Google profile to log in to your website.
• An API can be used to send data on online conversions (like online sales) to a platform like Facebook.
• An API can help to integrate a payment mechanism like PayPal into your website.

18. True or false: If Taylor is using a browser cookie on their site, they can expect that cookie to follow users regardless of the device or browser they are using.

• False
• True

19. True or false: If Taylor adds a Javascript pixel to their website, it will load on that page every time someone visits it.

• False
• True

20. Taylor is thinking of using a software developer kit in their app, some possibly added functionalities are: (Choose all that apply)

• Free customer service support
• Seamless shopping bag and checkout
• Additional photo or video filters
• Logging in with another company’s credentials

21. True or false: An application programming interface allows a user to block ads and trackers.

• True
• False

22. The server logs for Taylor’s website will include what pieces of information? (Choose all that apply)

• Country of Origin
• Requested Content
• IP Address
• Unique Identifier

23. True or false: If Taylor is looking for the first and last names of people who visit their site they can check the server logs.

• True
• False

Week 3: Marketing Measurement and Analytics

True or false: In a spreadsheet cell, you can only include numbers and letters.

• True
• False

A Global Site Tag is a piece of code provided by what analytics tools?

• Google Analytics
• Adobe Analytics
• Squarespace

True or false: There is only a single web analytics tool available- Google Analytics.

• True
• False

Because Facebook Ads Manager looks at the success of specific ad campaigns, it can be particularly helpful when determining…

• Your customer service needs
• ROAS
• Retention

PRACTICE ACTIVITY: GOOGLE SHEETS SIMULATION

1. Use the following scenario and Google Sheets simulation to answer Questions 1-3. The simulation is for you to practice working with Google Sheets. The questions serve as a tool to further reflect on its components and to give practical experience. Use the simulation and questions however you see fit to build your knowledge of how to use Google Sheets for marketing purposes.

Scenario: Inu + Neko have a physical store and a website where they sell toys and food for pets, and you are their marketing analyst. Your manager sends you a report based on some research she did. She conducted surveys of 350 Inu + Neko customers to better understand who they are and what their needs are. Customers were presented with six features of the Inu+Neko product offerings and asked to indicate which is most important to them.

• Organic dog food options
• Nutrient enriched dog food options
• Dog food delivery
• A variety of dog food options
• Auto delivery of dog food

This information will help you later to market to this audience. Your manager asks whether you can provide her with an easy to understand horizontal bar chart so that she can share her findings with stakeholders. Here is the spreadsheet with the data she provides to you.

Simulation: In this simulation, you will use Google Sheets to create a horizontal bar chart based on the information from the survey responses your manager collected. Clicking the simulation link will open it in a new window.

• True
• False

2. Use the scenario and simulation linked in Question 1 to answer this question.

Which of the following charts accurately represents the results you would like to share with your manager?

• Meta Marketing Analytics Chart 1 – Course 1 – Week 3
  • Meta Marketing Analytics Chart 2 – Course 1 – Week 3
  • Meta Marketing Analytics Chart 3 – Course 1 – Week 3
  • Meta Marketing Analytics Chart 4 – Course 1 – Week 3

PRACTICE QUIZ: ANALYZING AND CATEGORIZING DATA

1. All calculations must be solved with pen and paper then added to a spreadsheet. True or False?

• False

• True

2. Google Sheets and Excel are both valid options for making spreadsheets. True or False?

• False
• True

3. A cell always displays exactly what is inside of it. True or False?

• False

• True

4. Which of the following are visualization software? Select all that apply.

• Tableau

• Qlik

• Power BI

5. Excel is the only spreadsheet software. True or False?

• False

• True

6. =SUM( 2, 2 )

If the above is written in a calculated cell, the cell will display:

• =SUM( 2, 2 )
• 4
• ERR!

PRACTICE ACTIVITY: GOOGLE ANALYTICS SIMULATION 1

1. Use the following scenario and Google Analytics simulation to answer Questions 1-3. The simulation is for you to practice working with Google Analytics. The questions serve as a tool to further reflect on its components and to give practical experience. Use the simulation and questions however you see fit to build your knowledge of how to use Google Analytics for marketing purposes.

Scenario: You are the marketing analyst on the Inu + Neko marketing team. You have a brainstorming session with your manager about a plan to offer a curated selection of dog food products for subscribers of your dog food subscription service. Your manager believes it would be best to go with the top four online bestsellers, and she asks you to come up with the list. You decide that you can use Google Analytics to help you.

Simulation: In this simulation, you will use Google Analytics to determine the popularity of Inu + Neko’s products with your current customers. Clicking the simulation link will open it in a new window.

True or False: Instinctive_dog, Wellmost_dog, Ziggies_dog, and Royal Pups_dog are the top 4 selling products for the past 28 days.

• True
• False

2. Use the scenario and simulation linked in Question 1 to answer this question.

What are the best selling products online for the past 28 days? Which four do you list on the memo you are drafting for your manager? (select all that apply)

• Royal Pups_dog
• Nuvio_dog
• Ziggies_dog
• Taste of the wilderness_dog
• Instinctive_dog
• Blue Plate_dog

3. Use the scenario and simulation linked in Question 1 to answer this question.

Which of the following product groupings list the four top sellers?

• Ziggies_dog, Royal_Pups_dog, Blue Plate_dog, Nuvio_dog
• Instinctive_dog, Natures Best_dog, Ziggies_dog, Organix Plus_dog
• Taste of the wilderness_dog, Instinctive_dog, Blue Plate_dog, Ziggies_dog
• Nuvio_dog, Stan_and_Chester_dog, Nature Best_dog, Wellmost_dog

PRACTICE ACTIVITY: GOOGLE ANALYTICS SIMULATION 2

1. The following simulation is for you to practice working with Google Analytics. The question serves as a tool to further reflect on its components and to give practical experience. Use the simulation and question however you see fit to build your knowledge of how to use Google Analytics for marketing purposes.

Scenario: Inu + Neko have a physical store and a website where they sell toys and food for pets, and you are the marketing analyst on their team. Your manager is curious about the technology your returning users use to navigate the website, because it will help inform how to target people for the subscription product. The product is a dog food subscription service.

Once again you can use Google Analytics to understand your customer’s behavior.

Simulation: In this simulation, you will use Google Analytics to determine what technology your returning customers use to make purchases. Clicking the simulation link will open it in a new window.

Click here to go to the Google Analytics simulation

Based on the information you gathered from Google Analytics, should we target our returning customers through mobile devices or via desktop?

• Mobile Devices

• Desktop

PRACTICE QUIZ: GOOGLE ANALYTICS AND WEB MEASUREMENT

1. I would like to learn more about what content on my site is visited most by my users. Which section of the Google Analytics report could help me with that?

• The ‘users’ section
• The ‘engagement’ reports under the ‘life cycle’ section
• The event report in the ‘events’ section
• The ‘retention’ reports under the ‘life cycle’ section

2. Which of the following statements correctly describe the data shown in this Google Analytics dashboard (Choose all that apply):

• Most users in the past 7 days were new to the site, and over the past 60 days, the largest number of users from outside the US came from Canada.
• The percentage of new users that found the Merchandise store through referrals is higher than the percentage that found the store based on a cost per click (CPC) campaign. In the last 30 mins, the site saw more users from Canada than from any other country outside of the US.
• Over the past 7 days, the total revenue for the Google Merchandise store was $65K. Most new users found the site through organic (non-paid) search. Most people who visited the site were from the US.

3. What is the default time frame used for reports in the Google Analytics dashboard?

• Past month
• The data are real-time and cover the past 30 mins
• 7 days
• Past 2 weeks

PRACTICE ACTIVITY: FACEBOOK ADS MANAGER SIMULATION

1. Use the following scenario and Facebook Ads Manager simulation to answer Questions 1-4. The simulation is for you to practice working with Facebook Ads Manager. The questions serve as a tool to further reflect on its components and to give practical experience. Use the simulation and questions however you see fit to build your knowledge of how to use Facebook Ads Manager for marketing purposes.

Scenario: You are the marketing analyst on the Inu + Neko marketing team. After conducting research on customers’ needs and interests, the team has decided to launch a new product: A monthly subscription with bi-weekly deliveries of organic dog food. They have prepared a Facebook campaign to encourage people to check out the new offering and subscribe. The Facebook campaign ran for 30 days now, and your manager would like for you to evaluate some of the data. She would like to know how many impressions the campaign delivered, costs, CPM over the prior 3-month period and number of new subscriptions.

Simulation: In this simulation, you will use Facebook Ads Manager to access the results of the campaign and provide your manager with the information they requested. Clicking the simulation link will open it in a new window.

Click here to go to the Facebook Ads Manager simulation

How many people subscribed as a result of the entire campaign?

• 224
• 324
• 129
• 214

2. Use the scenario and simulation linked in Question 1 to answer this question.

How many impressions did the campaign deliver in the last 30 days?

• 32,982
• 28,242
• 32,255
• 33,141

3. Use the scenario and simulation linked in Question 1 to answer this question.

What was the CPM over the past 30 days for the campaign?

• $23.89
• $32.39
• $22.39
• $22.41

PRACTICE ACTIVITY: GOOGLE ADS REPORT

1. Use the following scenario and Google Ads Report to answer Questions 1-4. The report is there for you to practice working with Google Ads. The questions serve as a tool to further reflect on its components and to give practical experience. Use the report and questions however you see fit to build your knowledge of how to use Google Ads for marketing purposes.

Scenario: You are the marketing analyst for Inu + Neko, and the company has recently launched a new product: A monthly subscription with bi-weekly deliveries of organic dog food. Ad campaigns were organized to promote the new offering. The marketing team is seeing quite a bit of traffic and conversions coming in from the search ads. Your manager is getting ready to optimize the keywords they use to attract traffic through search ads and she is asking you for insights on current keyword performance. You can use this Google Ads report to find this.

Report: The following is a Google Ads report. Please read through Questions 1-4 so that you can look for the correct responses while viewing the report.

The report can be seen in the image below, but for a closer examination, please download the pdf version of the report.

Which keyword led to the most conversions?

• Puppy food
• Food dog
• Best puppy food
• Healthiest puppy food

2. Use the scenario and report linked in Question 1 to answer this question.

For which keyword was the interaction rate highest?

• Good dog food
• Healthiest dog food
• Good Puppy food
• Puppy dog food

3. Use the scenario and report linked in Question 1 to answer this question.

What was the lowest cost per conversion?

• $18.22
• $18.85
• $18.90
• $17.27

4. Use the scenario and report linked in Question 1 to answer this question.

Which keyword was most cost effective in achieving results, in other words, had the lowest cost per conversion?

• Best dry dog food
• Best puppy food
• Puppy dog food
• Healthiest dog food

PRACTICE QUIZ: FACEBOOK ADS MANAGER AND GOOGLE ADS

1. Which of the following questions can you answer with Facebook Ads Manager reports? (Choose all that apply)

• What was the click through rate for my Facebook Ads and my search ads on Google
• How many of the desired actions did people take as a result of my ads on Facebook? How many impressions did my advertising campaign on Facebook and Instagram have?
• How much did I spend on ads on Facebook over the past month?

2. Imra at Calla & Ivy wants to understand the results of the advertising campaign she ran on Instagram to promote her flower subscription service. More specifically, she would like to know how much money she had to spend on ads on Facebook to get one subscription. What should Imra do?

• Imra can look at Google Analytics and see how many people who came to her site ended up there by clicking on a Facebook Ad
• Imra can use Facebook Ads Manager and look at the ‘budget’ data.
• Imra can use Facebook Ads Manager and look at the ‘click through rate’ data.
• Imra can use Facebook Ads Manager and look at the ‘cost per result’ data.

3. Google Ads reports can be used to understand the results of advertising campaigns on Google. Which of the following is a specific report you can get in Google Ads that you won’t find in Facebook Ads Manager?

• The Keyword Results Report

• Campaign overview report showing the number of impressions and clicks for your campaigns.
• Website visitor report

GRADED QUIZ: MARKETING MEASUREMENT AND ANALYTICS TOOLS

1. Web analytics tools can help an analyst learn: (Choose all that apply)

• The name and address of visitors to a site
• How they arrived at a site
• Information about visitors to a site
• How many visitors went to a site

2. When labeling your data, it’s important to…

• Color code each column
• Alphabetize your columns
• Be as descriptive as possible

3. Visualizations are a critical tool of the marketing analyst because…

• They make data gathering more simple.
• They automate marketing campaign maintenance.
• They help an analyst communicate their findings.

4. Google Analytics collects data from: (Choose all that apply)

• Emails
• Phone Calls
• Sites
• Apps

5. If a marketing analyst needs to evaluate the success of an ad campaign in generating sales, a good starting point for gathering insight is…

• A web analytics tool
• An A/B test
• An outside consultant

6. If you want to find data on retention rates in Google Analytics, you can look at…

• The Events section
• The Life Cycle section
• The User section

7. True or false: Facebook Ads Manager can help you determine what is working with an active advertising campaign.

• True.

• False.

8. A spreadsheet can be used to: (Choose all that apply)

• Gather data from browsers
• Run formulae on data
• Sort data
• Collect data

9. True or false: When sorting your data, your column labels are referred to as the header row.

• False
• True

10. Some common data visualization chart types include: (Choose all that apply)

• Scramble graph
• Cake chart
• Line graph
• Bar chart

11. True or false: Google Analytics is free for anyone to use.

• True.

• False.

12. The events section of Google Analytics includes information about: (Choose all that apply)

• Moments when your site went offline
• Purchases linked to a certain promotion
• Conversions that happened on your site
• Specific data about clicks and scrolls

13. Some common ways to indicate the end of a conversion include: (Choose all that apply)

• Error page
• Thank you, page
• Receipt page
• Acknowledgement page

14. True or false: CPM measures the price a business pays to have their ad put in front of users a thousand times.

• True.

• False.

15. When you cannot write a descriptive label for every column, you need to create a legend or code book. True or False?

• True

• False

16. If you saw that your site visitors jumped on a specific day, what might have happened?

• It’s probably an error in Analytics tracking.
• Spikes are normal with organic growth, so it wasn’t affected by just one thing.
• A post you shared on social media might’ve been shared by others or gone viral, leading to visitors to your site.
• You sent out an email newsletter filled with CTAs that link to your site.

17. Google Analytics lets you see the path by which users move through your site.

• True.

• False.

18. What does CPM measure?

• How much it costs for 1 conversion.
• How much it costs for 1000 impressions.
• How much it costs for 1 click-through.
• How much it costs for 1 impression.

19. What does CTR measure?

• Percentage of those commenting on a social media post.
• Percentage of those clicking on the link in an ad.
• Percentage of those signing up for an email list.
• Percentage of those purchasing an item.

Week 4: Data and Privacy

In addition to the settings on a device, some platform specific privacy settings can include:

• Deleting a post
  • Turning off incoming messages
  • Customizing publicly accessible information

• All of the above

True or false: The most important person in the advertising ecosystem is the advertiser

• True

• False

Second party data is:

• Data that a consumer shares about their friends or family
  • Data that is gathered about browsing habits via cookies

• First party data shared among trusted partners

• First party data that is used twice

PRACTICE QUIZ: CONSUMERS AND DATA

1. T​rue or false, most online publishers don’t make any money from advertising and offer their content for free.

• True
• False

2. T​rue or false, consumers generally prefer that the information advertisers use come from their browsing habits.

• T​rue
• F​alse

3. T​rue or false: An ad blocker will stop a website from showing you an ad on your device or browser.

• F​alse
• T​rue

4. V​PN stands for:

• V​ery Personalized Notifications
• Velocity Per Node
• V​irtual Private Network

5. Privacy settings on your device let you (choose all that apply)

• Request a new phone number
• L​imit the things specific apps or programs can control or access
• Edit or turn off location tracking
• Change the way a consumer is tracked online

6. True or false, the vast majority of online time Americans spend consuming media is supported by ads.

• F​alse
• T​rue

7. W​hen asked, most people are most comfortable with advertisers using:

• Information gathered from their browsing habits
• Information they (consumers) intentionally provided.

8. Ad Blockers are primarily used to what?

• S​top an advertisement from showing.
• B​lock advertisers from contacting you.
• Remove your personal information from advertisements.
• S​top an advertisement from sending back information to the advertiser.

PRACTICE QUIZ: ADVERTISER ECOSYSTEM

1. Who is part of the advertising ecosystem? (Choose all that apply)

• Consumers
• Advertisers
• Regulators and gatekeepers
• Publishers and partners

2. True or False: Second party data is data shared between trusted partners.

• False
• True

3. Second party data is…

• Data about consumers that is shared between partner companies
• Data gathered about consumers from their browsing habits
• Data from surveys taken on websites

4. True or false: Third party data is data gathered from browsing habits and activities by a party the user does not have a direct relationship with.

• False
• True

5. Who is not part of the advertising ecosystem?

• Regulators and gatekeepers
• Influencers
• Consumers
• Advertisers

6. True or false: First party data comes directly from a consumer.

• True
• False

7. Third party data is…

• Data about consumers that is gathered by cookies and other tracking tools from parties the consumer doesn’t have a direct relationship with.
• Data willingly offered by the consumer
• Data gathered about consumers from their friends and family

GRADED QUIZ: DATA AND PRIVACY

1. True or false: The use of advertising to support free or inexpensive content is new in the digital age.

• True
• False

2. True or false: An ad blocker will stop a site from saving a cookie in a browser.

• False
• True

3. In addition to the settings on a device, some platform specific privacy settings can include:

• Deleting a post
• Turning off incoming messages
• Customizing publicly accessible information
• All of the above

4. Advertising that is relevant to the specific viewer of a page or site is called…

• Data-based Advertising
• Tracked Advertising
• Contextual Advertising
• Per-person Advertising

5. In the advertising ecosystem, the regulators and gatekeepers include: (Choose all that apply)

• Advertisers
• Browsers and Device Platforms
• Industry Organizations
• Governments

6. First party data is different from third party data, because…

• Third party data is gathered about a consumer’s browsing habits without them knowing it
• Third party data is information shared between trusted partners
• First party data is available to anyone who owns or manages a website

7. Generally, laws written to protect consumer privacy focus on: (Choose all that apply)

• A consumer’s right to profit from their own data
• A consumer’s right to opt in or out of data collection
• A consumer’s right to know the data that is being collected about them
• A consumer’s right to remove data that has been collected about them

8. There are a number of laws that governments around the world have put in place to protect consumers and their privacy. Some of the most prominent ones are: (Choose all that apply)

• GRDE
• CCPA
• COPPA
• GDPR

9. The GDPR law that regulates the use of consumer data requires that consumers can ask to download the data that was collected about them by websites.

• False
• True

10. In addition to industry self-regulation, most large online platforms and websites have:

• An Internal Watchdog
  • A Government Representative

• A Data Policy

11. True or false: COPPA was signed into law to protect children online.

• False
• True

12. VPN stands for…

• Virus Plotting Network
• Virtual Private Network
• Volumes Prioritized Network
• Verified Platform Network

13. You can change the tracking setting on most devices to allow or stop an app’s or program’s information gathering about your browsing habits.

• False
• True

14. Data-based advertising allows advertisers to:

• Tailor ads that are more interesting for a consumer
• Tailor ads that a user has requested via survey
• Tailor ads that are built specifically for a consumer

15. True or false: an advertisement for a running shoe on a running website is most likely a data-based advertisement

• True

• False

16. Most free or discounted online content is supported by…

• Online advertising
• Local government
• Creators
• Corporate philanthropy

17. A tool that can be added to your browser to prevent a website or online server from storing information in your browser is called a…

• VPN
• Cookie blocker
• Ad blocker

18. True or false: The YourAdChoices program was established by the DAA

• False
• True

19. The advertising ecosystem includes: (Choose all that apply)

• Manufacturers
• Regulators and gatekeepers
• Consumers
• Publishers and partners

20. True or false? Consumers are equally comfortable with advertisers using information they have provided and information that was assumed based on their browsing habits.

• True
• False

21. A good way for a consumer to control their private online data is:

• A VPN.
• Turning off “Tracking” for all apps on their mobile devices.
• Changing the settings of their social media platforms.
• All of the Above

22. True or false, even though it costs more, an advertiser always has an option to directly use a consumer’s personal data.

• True
• False

23. True or false: First-party data is information that a consumer offers directly to a company.

• True
• False

24. Which EU citizen data right is not included in the General Data Protection Regulation (GDPR)?

• The right to have all the information that was collected and saved about them erased.
• The right to data portability.
• The right to access the personal information received about them.
• The right to not be discriminated against for exercising their rights.

25. Which Californian citizen data right is not included in the California Consumer Privacy Act (CCPA)?

• The right to know what information is being collected about them.
• The right to access the personal information received about them.
• The right to prior consent.
• The right to data portability.

Course 2: Introduction to Data Analytics

Week 1: Working with Data

The stage of the OSEMN framework which transforms dirty data to clean data is ________.

• Cleaning
  • Obtaining

• Scrubbing

• Exploring

What might need to be done to the data below before conducting further analysis?

User_IDPurchase_IDPurchase_DatePurchase_Amount2894758729443896705/24/20$84.9594387957598034750December 9th 2020$77.872894758729443896724th May 2020$84.95382974052938759991-2-21$115.00

• Understand who user 28947587 is
  • Remove duplicates

• Ensure Purchase_Date has a consistent format and remove duplicates.

• Reformat the Purchase_Amount column.

During the Obtain step of the OSEMN framework, you would collect data for the next steps. What do we call data that has been collected by a company directly from its audience?

• 1st party

• 2nd party
• 3rd party
• 4th party

PRACTICE QUIZ: GOALS AND KEY PERFORMANCE INDICATORS

1. Which of the following is true about having access to data? Choose all that apply.

• It allows you to track key performance indicators.
• It is difficult to come by.
• It helps marketers evaluate the success of advertising.
• It helps to plan and forecast the results of marketing action.

2. Before obtaining data (the “O” in the OSEMN process), which should be the very first step in the cycle?

• Come up with a marketing plan.
• Determine the objective of the analysis.
• Gather your sample of 1,000 people.
• Seek out investors.

3. What does the R in the SMART acronym stand for?

• Relax
• Relocate
• Relevant
• Renovate

4. True or false: KPIs are measurable values that can help you track your progress towards your goal.

• True
• False

PRACTICE QUIZ: THE OSEMN PROCESS

1. Looking at some data about user profiles for a website, we notice that a relatively large portion of the users (25%) have their age listed as over 100 years old. Is this dirty data? (Select the most appropriate answer.)

• It IS dirty data because there’s no way that many users are over 100 so it can’t be accurate.
• It’s NOT dirty data because people can be over 100 years old.
• It’s PROBABLY dirty data but we need to know more about the data before deciding what to do with it.

2. Another popular framework for data analytics projects is the Cross Industry Standard Process for Data Mining (CRISP-DM). It has six stages: Business Understanding, Data Understanding, Data Processing, Modeling, Evaluation and Deployment. The CRISP-DM phase of Evaluation is likely closest to which stage of the OSEMN framework?

• Scrubbing
• Obtaining
• Exploring
• Modeling
• INterpret

3. An online bookstore wants to analyze what book titles they should advertise to drive more sales. They’ve already pulled their historic sales and web traffic data as well as book title details. What is the MOST likely best next step based on the OSEMN framework?

• Start creating models that predict the amount of sales if different book titles were promoted.
• Begin digging into the details of the data and start looking at statistics such as which book genres were most popular.
• Look for more data about what past customers loved about their book purchases. Possibly even surveying the customers since the business doesn’t have this information already available.
• Ensure that the data gathered is generally “clean” & well-formatted and make changes as necessary.

GRADED QUIZ: AN ANALYTICS CASE STUDY

1. You’ve been asked to conduct an analysis on customer interests to identify other product offerings these consumers might be interested in. Using the OSEMN framework what would be a sensible approach?

• Ask questions, find the largest and smallest statistics, go to market
• Get the data, ensure it is accurate and well-formatted, conduct statistical analysis, generate predictions and insights, translate results to tell a story.
• Analyze statistics, build models, focus on production
• Mail out surveys, read the results, form an opinion

2. Which stage of the OSEMN process works to generate predictions and insights from the data?

• Scrubbing
• iNterpreting
• Modeling
• Exploring

3. An analyst notices that the data they are working with contains many duplicate records. In which stage of the OSEMN process would they fix these duplicate records?

• Scrubbing
• Interpreting
• Exploring
• Obtaining

4. During the Obtain step of the OSEMN framework, you would collect data for the next steps. What do we call data that has been collected by an entity that doesn’t have a clear relationship with its audience?

• 4th party
• 3rd party
• 1st party
• 2nd party

5. True or False: Creating visualizations of your data is another way to explore your data.

• F​alse
• T​rue

6. True or False: The iNterpret stage of the OSEMN framework is where you’ll explain your findings to your stakeholders from earlier stages?

• True
• False

7. What does the M in the SMART acronym stand for?

• Money
• Measurable
• Modest
• Meticulous

8. KPIs are measurable values that can help you track your progress towards your goal.

• False
• T​rue

9. Select the best match to complete the following statement:

After modeling, the next stage of the OSEMN process is ________ .

• Exploring
• Naming
• Scrubbing
• Interpreting

10. Which stage of the OSEMN process has the goal of trying to understand the data as a whole and learn the patterns in the data?

• Modeling
• Scrubbing
• iNterpreting
• Exploring

11. The iNterpret stage of the OSEMN framework is the last stage of the process. What is the primary goal of a data analysis project?

• Collect as much data as possible.
• Create beautiful visualizations.
• Create and use the most accurate models with your data.
• Generate insights and understanding.

12. Mark all that are true about KPIs values.

• KPIs values are only used if you have a difficult business problem
• KPIs values are measurable
• KPIs values directly relate to your goal
• KPIs values are directional

13. KPIs are measurable values that are suggested targets but don’t usually align with your goals.

• Third party data is gathered about a consumer’s browsing habits without them knowing it
• Third party data is information shared between trusted partners
• First party data is available to anyone who owns or manages a website

14. What does the T in the SMART acronym stand for?

• Timely
• Tailored
• Total
• Temporary

15. During the Explore step of the OSEMN framework, you attempt to get familiar with your data. Which of the following is NOT a way to examine your variable distributions and relationships?

• Create a statistical model to make predictions about our data
• Observes the minimum and maximum values of numerical columns
• Observed how common the top values are in categorical columns
• Create visualizations

16. An analyst has been working with their clients to define business goals and identified questions to answer. They are now ready to dive into the OSEMN process. Which stage of the OSEMN process would likely be the next step for this analyst?

• Scrubbing
• Exploring
• Obtaining
• Interpreting

17. During the iNterpret stage of the OSEMN framework, you translate your analytical findings back to a business context. Which of the following would you likely do in this stage?

• Recommend actionable insights to your stakeholders based on what you’ve done during your analysis.
• Create a statistical model to make predictions about our data.
• Collect more data to check that your analysis is correct.
• Create visualizations to show variable relationships.

18. Which stage of the OSEMN process works to generate predictions and insights from the data?

• Modeling
• iNterpreting
• Exploring
• Scrubbing

19. Here are some examples of goals for an online clothing store that sold goods for about $80,000 in revenue over the past half year. Which ones do you think are SMART?

• Increase the number of visitors for the website
• Increase the average checkout value to $100 by the end of the year
• Sell clothes for a total of $100,000 in revenue during the second half of this year

20. What does the acronym OSEMN stand for in data analysis?

• Orchestrate Scaffold Examine Maximize Numerical
• Obtain Scrub Explore Model iNterpret
• Optimize Search Examine Model Name
• Organize Size Extrapolate Merge Name

21. Imagine a database containing records of sales from a company’s own website. What kind of data is this?

• 2nd-Party Data
• None of the above.
• 1st-Party Data
• 3rd Party Data

22. Which of the following is an example of dirty data? Select all that apply.

• Text Data that are not in English
• Fields that are blank for some records
• Inaccurate data
• Data that contain duplicate records

23. Which of the following is NOT true about models?

• Machine Learning models make predictions that are 100% accurate.
• All models are wrong, but some are useful.
• Algorithms are used to train models.

24. What is the primary goal of a data analysis project?

• To gather the most data possible
• To generate insights and understanding
• To build the most complex models
• To build the most accurate models

Week 2: Python for Data Analysis

GRADED QUIZ: LOADING AND RUNNING A PYTHON PROGRAM

1. JSON files are structured in a nested structure. True or False?

• True
• False

2. JSON files are tab delimited. True or False?

• True
• False

3. It is important to memorize all of the syntax and every function. True or False?

• True
• False

4. Python is Object-Oriented. True or False?

• True
• False

5. Python is only used for data analytics. True or False?

• False
• True

6. When writing code in a Jupyter notebook, you should separate your code into different cells into logical chunks.

• False
• True

7. Sometimes you need a little help while writing code in a Jupyter notebook. You can use a question mark before or after a function and then execute the cell to learn more about the function.

• True
• False

8. Which of the following data types store tabular data? Choose all that apply.

• JSON
• CSV
• XLSX
• TXT

9. Logical thinking is a skill that must be practiced like any other. True or False?

• True
• False

10. Which of the following describes Python? Check all that apply.

• Low level
• General Purpose
• Open Source
• Object-Oriented

11. Being good at math is more important than being able to think logically. True or False?

• False
• True

12. It is okay to keep code references, look things up, and to copy and paste code you have used in the past instead of memorizing everything. True or False?

• False
• True

13. When writing code in a Jupyter notebook, you should separate your code into different cells so there is only one line per cell. True or False?

• True
• False

14. Which of the following data types typically have delimited data? Select all that apply.

• XLSX
• JSON
• TXT
• CSV

15. It is okay to keep code references, look things up, and to copy and paste code you have used in the past instead of memorizing everything. True or False?

• False
• T​rue

PRACTICE QUIZ: PYTHON

1. What does the following code output?

my_list = [10,30,40]

if my_list[1] < 20:

print(“first”)

elif len(my_list) == 2:

print(“second”)

elif my_list[0] + 25 > my_list[1]:

print(“third”)

elif len(my_list) > 1:

print(“fourth”)

• “second”
• “first”
• “third”
• “fourth”

2. Which are legitimate Python variable names?

• in
• 1_is_the_lonliest_number
• my_cool_variable
• MyCoolVariable
• dog_8_my_homework

3. Which of the following are built-in types?

• Number
• Array
• Text
• Dictionary
• Boolean
• Float
• Integer

4. What is the output of this code?

for count in range(1,5):

print(count)

if count > 1:

print("Hello")

elif count <= 3:

print("Hi")

else:

print("*")

print("All Done")

• 1
• Hi
• 2
• Hi
• 3
• Hi
• 4
• Hi
• All Done

• 1 (CORRECT)
• Hi
• 2
• Hello
• 3
• Hello
• 4
• Hello
• 5
• Hello
• All Done

• 1
• Hi
• All Done
• 2
• Hello
• All Done
• 3
• Hello
• All Done
• 4
• Hello
• All Done

• 1
• Hi
• 2
• Hi
• 3
• Hi
• 4
• Hi
• All Done

5. Which of the following restrictions do Python dictionaries have?

• Dictionary values must be unique.
• Dictionary values cannot be lists or dictionaries.
• Dictionary keys must be unique.
• Dictionary keys cannot be lists or dictionaries.

GRADED QUIZ: PYTHON FOR DATA ANALYSIS

1. Which built-in function would you use to find the smallest number in a list?

• min()
• small()
• max()
• smallest()

2. If the function you’re writing isn’t returning anything, you should NEVER include a return statement in the function. True or False?

• False
• True

3. Consider the following code:

total = 0

for n in range(5):

total = total + n

print(total)

If we run the code, what will the output of the above code be?

• 20
• 15
• 10
• 5

4. Variables in Python can have numbers in the variable names but only if you separate the numbers with underscores ( _ ) in the name.

• False
• True

5. You are given a string variable defined like so, my_str = “5”. How would you cast (change the variable type) the variable to a float type?

• int(my_str)
• cast(my_str, ‘float’)
• my_str.float()
• float(my_str)

6. What would the conditional statement evaluate to? ”3” == “3.0”

• True
• False

7. You are going through someone else’s code, when you find a built-in function you do not know.

Which built-in function would you use to look up the definition of the other function?

• look()
• library()
• def()
• help()

8. When you put a return statement with no value after it, it’ll return the same thing as if you didn’t have a return statement. True or False?

• False
• True

9. What would the conditional statement evaluate to? not (“Hello” != “Good-bye”)

• False
• True

10. Variables in Python can have underscores ( _ ) in the variable names.

• True
• False

11. Every function you write must have a return, even if it’s just to return “nothing”. True or False?

• False
• True

12. Which file type always stores data in a nested, semi-structured data format?

• TXT
• XLSX
• CSV
• JSON

13. Which of the following describe Python? Please select all that apply.

• Low-Level
• General Purpose
• Open Source
• Object-Oriented

14. Why is it important to add comments to your code?

• Adding comments is the only way to segment code in Jupyter.
• It makes it easier for everyone to read your code and understand what is going on.
• The code will not run if you don’t add comments.
• It is not important to add comments to your code.

15. What type would “15.0” be?

• Float
• Boolean
• Integer
• String

16. 1. my_list = [ 4, 8, 15, 16, 23, 42 ]

Given the following variable, what will my_list[2] return?

• 4
• 16
• 8
• 15

17. Consider the program below:

total = 0

for v in range(4):

total = total + v

print(total)

If we run the program, what will the output of the above code be?

• 6
• 10
• 0, 1, 2, 3
• 7

18. What built-in function would you use to find the biggest number in a list?

• largest()
• max()
• big()
• upper()

19. True or False?

def doubler(n):

result = n * 2

return result

In the code above, the “result” variable is a global variable.

• False
• True

Week 3: Data Cleaning and Processing

PRACTICE QUIZ: FILTERING DATA WITH GOOGLE SHEETS

1. If you have a list of numbers, and you’d like to arrange them from lowest to highest, you would:

• All of the above
  • Visualize them
  • Filter them

• Sort them

2. True or false: Filtering data in a spreadsheet deletes the information that is no longer shown.

• True

• False

3. Which function would you use to find the mean of a set of data in a spreadsheet?

• =MEAN()

• =AVERAGE()

• =MEDIAN()

4. True or false: Once a spreadsheet has determined an appropriate visualization for your data, you can’t make changes to it.

• True

• False

PRACTICE QUIZ: SQL SELECT STATEMENTS

1. Use the table of advertising expenditures below to answer ALL the questions in this quiz.

Company Quarter Internet TV Print

FocusVu 1 3,000 5000 3000 Paola Snaps 1 1500 5000 500 Calla & Ivy 1 2500 9000 400 Inu + Neko 1 2000 5000 700 FocusVu 2 3000 7000 1000 Paola Snaps 2 1500 11000 600 Calla & Ivy 2 2300 7000 400 Inu + Neko 2 1800 5000 200 FocusVu 3 3000 5500 550 Paola Snaps 3 5000 15000 400 Calla & Ivy 3 2200 9000 500 Inu + Neko 3 3000 6000 700 FocusVu 4 3500 10000 900 Paola Snaps 4 6300 5000 1100 Calla & Ivy 4 2000 8500 250 Inu + Neko 4 3400 8000 300

AdvertExpend Table

Which query will return the company, internet expenditure, and quarter in descending order of internet expenditure?

SELECT Company, Internet

FROM AdvertExpend

ORDER BY Internet DESC

SELECT Company, Internet, Quarter

FROM AdvertExpend

ORDER BY Quarter DESC

SELECT Company, Internet, Quarter

FROM AdvertExpend

SELECT Company, Internet, Quarter

FROM AdvertExpend

ORDER BY Internet DESC

2. Which of the following queries will return the unique companies found in the table and arrange them in alphabetical order?

SELECT Company

FROM AdvertExpend

ORDER BY Company

SELECT DISTINCT(Company)

FROM AdvertExpend

ORDER BY Company DESC

SELECT DISTINCT(Company)

FROM AdvertExpend

SELECT DISTINCT(Company)

FROM AdvertExpend

ORDER BY Company

3. What will the following query have in its return-set?

SELECT Company, Quarter, TV

FROM AdvertExpend

ORDER BY TV

LIMIT 4

The return-set will contain only the four companies that have spent the least amount of TV advertising.

The return-set will have company, quarter, and TV expenditure values for the four rows that have the least TV advertising values.

The return-set will contain all the values found in the Company, Quarter, and TV columns.

The return-set will contain the company, quarter, and TV values for the four rows that have the highest values in the TV column.

PRACTICE QUIZ: SQL FILTERING + GROUPING

1. For the ALL the following questions use the table of advertising expenditures given below.

Company Quarter Internet TV Print

FocusVu 1 3,000 5000 3000 Paola Snaps 1 1500 5000 500 Calla & Ivy 1 2500 9000 400 Inu + Neko 1 2000 5000 700 FocusVu 2 3000 7000 1000 Paola Snaps 2 1500 11000 600 Calla & Ivy 2 2300 7000 400 Inu + Neko 2 1800 5000 200 FocusVu 3 3000 5500 550 Paola Snaps 3 5000 15000 400 Calla & Ivy 3 2200 9000 500 Inu + Neko 3 3000 6000 700 FocusVu 4 3500 10000 900 Paola Snaps 4 6300 5000 1100 Calla & Ivy 4 2000 8500 250 Inu + Neko 4 3400 8000 300

AdvertExpend Table

Which query will return the quarters for which Calla & Ivy had a print advertising expenditure less than $400?

SELECT Quarter

FROM AdvertExpend

WHERE Print = 400 AND Company = ‘Calla & Ivy’

SELECT Quarter

FROM AdvertExpend

WHERE Print < 400

SELECT Print

FROM AdvertExpend

WHERE Quarter < 400 AND Company = ‘Calla & Ivy’

SELECT Quarter

FROM AdvertExpend

WHERE Print < 400 AND Company = ‘Calla & Ivy’

2. Which query will get us the total TV expenditure in each quarter across all companies?

SELECT Quarter, MAX(TV)

FROM AdvertExpend

GROUP BY Quarter

SELECT Quarter, TV

FROM AdvertExpend

GROUP BY Quarter

SELECT Quarter, SUM(TV)

FROM AdvertExpend

GROUP BY TV

SELECT Quarter, SUM(TV)

FROM AdvertExpend

GROUP BY Quarter

3. What will the following query have returned?

SELECT AVG(Internet)

FROM AdvertExpend

WHERE Company = ‘Calla & Ivy’

GROUP BY Quarter

The query will return Calla & Ivy’s average internet expenditure across all quarters.

The query will return the internet expenditure for an average quarter at Calla & Ivy.

The query will return Calla & Ivy’s total internet expenditure for each quarter.

The query will return Calla & Ivy’s average internet expenditure for each quarter.

PRACTICE QUIZ: FINDING AND REMOVING DUPLICATE RECORDS

1. Given that you have a Pandas DataFrame df, how would you export the DataFrame to the CSV file “my_data.csv”?

• df.to_csv(“my_data.csv”)

• df.to_csv = “my_data.csv”

• df.save(“my_data.csv”)
• df[“my_data.csv”]

2. You’re given a CSV and load it to a DataFrame assigned to the variable df. Running df.head() gives you the following

Column 1 Column 2 Column 3 Column 4 0 5.92 heating 1418 twins 1 2.48 santa cruz 1171 enrollment 2 5.23 ought 1616 pork 3 3.13 emily 9442 corey 4 2.20 rising 4620 berry

What code would get you just the data for Column 2?

• df = ‘Column 2
  • df[2]

• df[‘Column 2’]

• df(‘Column 2’)

3. What code would get you how many rows and columns are in a DataFrame df?

• df.shape()
  • df.size
  • df.size()

• df.shape

GRADED QUIZ: PANDAS AND SQL ASSESSMENT

1. You are given the following data loaded as a DataFrame df using Pandas.

Meta Marketing Analytics – Course 2 Week 3 (Image 1)

What code would you write to get all the rows where subscriptionTier has the word “Free”?

• df[ df[subscriptionTier].str.contains(“Free”) ]

• df[subscriptionTier].contains(“Free”)
• df[ df[subscriptionTier].contains(“Free”) ]
• df[subscriptionTier].str.contains(“Free”)

3. Say I have the given data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 2)

What code would I write to find out how many customers there are in each industry?

• df.groupby(‘industry’)[‘customerID’].count()

• df[‘customerID’].groupby(‘industry’).count()
• df.groupby(‘customerID’).count()

4. You can find the list of columns with df.columns()

• T​rue

• False

5. You are given the following data loaded as a DataFrame df using Pandas.

Meta Marketing Analytics – Course 2 Week 3 (Image 3)

What code would you write to get all the rows where industry starts with the letters “Re”?

• df[ df[‘industry’].contains(“Re”) ]
  • df[ df[‘industry’].str.contains(“Re”) ]

• df[ df[‘industry’].str.startswith(“Re”) ]

• df[ df[‘industry’].startswith(“Re”) ]

6. Say I have the given data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 4)

What code would I write to find out how many customers there are that have the security add on?

• df.groupby(‘customerID’).count()
  • df[‘customerID’].groupby(‘addOn_security’).count()
  • df.groupby(‘customerID’)[‘addOn_security’].count()

• df.groupby(‘addOn_security’)[‘customerID’].count()

7. Which code would you write to filter a DataFrame df so that you keep only the first instance of a duplicate?

• df[ ~df.duplicated() ]

• df[ df.duplicated() ]
• df[ df.duplicated(keep=False) ]
• df[ ~df.duplicated(keep=False) ]

8. You are given the following data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 5)

How would you interpret this output?

df[ 'totalCosts' ].quantile(0.6)

4.99

60% of the data has a totalCost of 4.99 or more

60% of the data has a value of 4.99 or less for the totalCost column

60% of the data has a totalCost of exactly 4.99

40% of the data has a totalCost of 4.99 or less

9. You are given the following data loaded as a DataFrame df using Pandas.

Meta Marketing Analytics – Course 2 Week 3 (Image 6)

What code would you write to get just the single column totalCost?

• df[‘totalCost’]

• df.column[‘totalCost’]
• df.column(‘totalCost’)
• df(‘totalCost’)

10. Say I have the given data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 7)

What code would I write to find out how many customers there are in each subscription tier?

• df.groupby(‘customerID’).count()
  • df[‘customerID’].groupby(‘subscriptionTier’).count()

• df.groupby(‘subscriptionTier’)[‘customerID’].count()

• df.groupby(‘customerID’)[‘subscriptionTier’].count()

11. You are given the following data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 8)

df[ 'totalCosts' ].quantile(0.8)

8.99

80% of the data has a value of 8.99 or less for the totalCost column

20% of the data has a totalCost of exactly 8.99

80% of the data has a totalCost of 8.99 or more

20% of the data has a totalCost of 8.99 or less

12. You are given the following data loaded as a DataFrame df using Pandas.

Meta Marketing Analytics – Course 2 Week 3 (Image 9)

What code would you write to get all the rows where industry starts with the letter “R”?

• df[ df[‘industry’].str.startswith(“R”) ]

• df[‘industry’].str.starts(“R”)
• df[ df[‘industry’].startswith(“R”) ]
• df[ df[‘industry’].starts(“R”) ]

13. Which code would you write to filter a DataFrame df so that you only have values that had no duplicate rows?

• df[ ~df.duplicated(keep=False) ]
  • df[ df.duplicated(keep=’False’) ]

• df[ ~df.duplicated(keep=’last’) ]

• df[ df.duplicated(keep=’last’) ]

14. You are given the following data loaded as a DataFrame df using Pandas. We know that the customerID column has a unique value (representing a different customer).

Meta Marketing Analytics – Course 2 Week 3 (Image 10)

What code would I write to find out how many customers there are in each subscription tier?

• df.value_counts()[‘subscriptionTier’]
  • df[‘subscriptionTier’].values

• df[‘subscriptionTier’].value_counts()

• len(df[‘subscriptionTier’])

15. You are given the following data loaded as a DataFrame df using Pandas.

Meta Marketing Analytics – Course 2 Week 3 (Image 11)

What code would you write to get all the rows where totalCost is less than $6?

• df[‘totalCost’] < 6.00
  • df[‘totalCost’].less_than(6.00)
  • df[ df[‘totalCost’].less_than(6.00) ]

• df[ df[‘totalCost’] < 6.00 ]

16. Which ways can you filter data using Google Sheets? Select all that apply.

• By Font Size

• By Color

• By Condition

• By Values

17. What will the following code give in the return set?

SELECT DISTINCT company

FROM advert

ORDER BY company DESC

LIMIT 5

• It returns the list of all companies in reverse alphabetical order.
  • It returns the first five entries from the list of companies in alphabetical order.

• It returns the first five entries from the list of companies in reverse alphabetical order.

• It returns the list of all companies in alphabetical order.

18. For the data below

Meta Marketing Analytics – Course 2 Week 3 (Image 12)

What are the resulting data for the SQL query:

SELECT company, quarter, internet

FROM adverts

WHERE internet >= 500

• The return-set will consist of the Company, Quarter, and Internet column values for only those rows where the internet value is 500 or greater.

• The return-set will consist of the Internet column values for only those rows where the internet value equals 500.
• The return-set will consist of the Company, Quarter, and Internet column values for only those rows where the internet value is less than 500.
• The return-set will consist of the Company and Internet column values for only those rows where the internet value is 500 or greater.

19. The tenure column records how many months an individual has been a customer. Which code blocks would correctly filter the data to individuals who had been a customer for a year or more? Select all that apply.

• 1 mask = df[ ‘Tenure’ ] == 12
  • 2 df[mask]

• 1 df[df[ ‘Tenure’] >= 12]

• 1 mask = df[ ‘Tenure’ ] > 11

• 2 df[mask]

• 1 df[df[ ‘Tenure’] >= 12]

20. Which code would correctly remove all duplicate values? Select all that apply.

• 1 deduplicated = df.filter(df.duplicated())
  • 1 deduplicated = df[df.duplicated()]

• 1 mask = ~df.duplicated()

• 2 deduplicated = df[mask]

• 1 deduplicated = df[~df.duplicated()]

21. Which code correctly groups customers by subscription tier and returns the total monthly sales from each tier group?

• df.groupby([‘subscriptionTier’, ‘totalCost’]).sum()
  • df.groupby(‘subscriptionTier’)[‘totalCost’].mean()
  • df.groupby(‘totalCost’)[‘subscriptionTier’].sum()

• df.groupby(‘subscriptionTier’)[‘totalCost’].sum()

22. How would you interpret this output? Select all that apply.

1 df['totalCosts'].quantile(.75)

2 7.99

25% of the data has a totalCosts of 7.99 or less.

75% of the data has a totalCost of 7.99 or more.

25% of the data has a totalCosts of 7.99 or more.

75% of the data has a value of 7.99 or less for the totalCosts column.

Week 4: Introduction to Data Visualization

PRACTICE QUIZ: CHART TYPES AND BASIC TABLEAU GRAPHS

1. Which chart type best describes this chart:

• Scatter Plot
  • Line Chart
  • Pie Chart

• Bar Chart

2. What does the trend line in this scatter plot suggest about the relationship between the duration of Old Faithful’s eruptions and the wait-time between eruptions?

Meta Marketing Analytics – Course 2 Week 4 (Image 1)

• The longer an eruption lasts the shorter the time you’re likely to have waited between eruptions

• The longer you wait between eruptions the longer an eruption is likely to last

• That the average wait time between eruptions is approximately 64 minutes
• That the average duration of an eruption is approximately 39 minutes

3. True or false: Tableau can only connect to data from an Excel file or CSV file?

• True

• False

.

4. Which type of chart is usually best suited for visualizing the relationship of measurements to another ordered series of data, such as time?

• A Line Chart

• A Map
• A Scatter Plot
• A Bar Chart

5. In Tableau, charts are created in a worksheet. Which of the following actions will create a new worksheet?

• Which query will return the company, internet expenditure, and quarter in descending order of internet expenditure?
  • Clicking a “New Worksheet” button at the bottom of an open worksheet screen
  • Connecting to a data source from the Tableau Start Page, when you start a new project
  • Clicking a “New Worksheet” button at the bottom of the Data Source screen

• A, B, and C, above, are all correct

• None of the above are correct

6. True or false: The order in which you double-click a data field may affect the chart that Tableau generates?

• False

• True

7. On the Tableau start page, which of the following connection types would you select if you want to connect to data in a CSV file?

• Spatial file
  • Odata

• Text file

• Microsoft Access
• JSON file
• Microsoft Excel

8. True or false: If you change the name of a column in Tableau’s data preview pane, this will change the data in your Excel or CSV file.

• True

• False

PRACTICE QUIZ: BUILDING CHARTS IN TABLEAU II PRACTICE

1. True or False: you can use the “Show Me” tool even after you’ve created a chart using other methods?

• False

• True

2.

Meta Marketing Analytics – Course 2 Week 4 (Image 2)

According to the chart above, which U.S. State hired workers for 17,342,587 jobs in 2013?

• Texas.
  • Wyoming.
  • Alaska.

• California.

Meta Marketing Analytics – Course 2 Week 4 (Image 2)

In the map from the chart above, California is the state with the darkest green color and, therefore, the highest number of jobs.

3. In Tableau, for charts that are drawn on a pair of axes, how do you specify what data you want represented on the vertical axis (or Y-axis)?

• By dragging the target data field from the Data Pane to the “Detail” button on the Marks Shelf.
  • By dragging the target data field from the Data Pane to the “Label” button on the Marks Shelf.

• By dragging the target data field from the Data Pane to the “Row Shelf.”

• By dragging the target data field from the Data Pane to the “Column Shelf.”

4. Of all the chart-making options we’ve covered, which of these is “easiest” (i.e., requires the least input from you)?

• The “double-click” method.

• The “Show Me” tool.
• The “drag-and-drop” method.

EXEMPLAR: TABLEAU INTERACTIVITY PRACTICE

1. Create a Date filter for the % of Mobile Usage by Operating System chart.

Here’s a quick test to see if your interactive elements are working properly. Using your Date filter and the various highlighters, find out what the “Avg. Percent of Usage” was for the “SymbianOS” operating system on 8/1/2013. What answer do you get?

• 6.33

• 21.79

• 14.24

GRADED QUIZ: INTRODUCTION TO DATA VISUALIZATION

1. True or False: It’s important to craft a story for your audience so your audience has an easier time understanding complex information and process from your project.

• T​rue

• False

2. True or False: When creating a story around your data for your audience, making the story entertaining is one of the most important requirements.

• False

• True

3. True or False: When strengthening your story, you should include an explanation of the investigation steps and describe the analysis.

• T​rue

• False

4. True or False: Considering you have quantitative data, you will likely want to consider visualizations that show distributions of numerical data.

• T​rue

• False

5. True or False: Using colors that are similar to one another in your visualization, such as differing shades of red in your pie chart, will help your audience concentrate harder on the story you’re telling.

• T​rue

• False

6. True or False: You should avoid using built-in color palettes in visualization software. They’re only there for people who are too lazy to design their visualization from scratch.

• T​rue

• False

7. True or False: In discussing how to build a good and compelling story, the climax of the story is where we wrap up our story.

• T​rue

• False

8. Which parts of your story structure help engage the situation you are trying to describe?

• Narrative & Charisma
  • Visualization & Narrative

• Narrative & Data

• Visualization & Data

9. True or False: It’s important to craft a story for your audience to show people how much you know.

• T​rue

• False

10. True or False: When creating a story around your data for your audience, making the key takeaways clearly identified is one of the most important requirements.

• T​rue

• False

11. True or False: When strengthening your story, you should include data results and visualizations in the story.

• False

• True

12. Considering you have quantitative data, select all visualization types that usually do best for this kind of data. (Select all that apply)

• Bar graphs
  • Pie charts

• Scatter plots

• Line plots

13. True or False: Swapping colors from their normal usage such as using red for “cold” and blue for “hot” are great ways to keep your audience engaged.

• False

• T​rue

14. True or False: When creating a story around your data for your audience, making the key takeaways clearly identified is one of the most important requirements.

• T​rue

• False

15. True or False: When strengthening your story, you should include intermediate findings and any key results.

• False

• T​rue

16. True or False: Using more color in your visualization is usually a better option; if your visualization only uses two or three colors you’ll want to add more to keep it interesting for your audience.

• T​rue

• False

17. True or False: Red and green are great contrasting colors for your visualizations.

• T​rue

• False

18. From what we discussed, what are the different parts of a story structure that can lead to an audience’s understanding and persuasion? (Select all that apply)

• Charisma

• Narrative

• Visualization

• Data

19. True or False: In discussing how to build a good and compelling story, the four parts were the set-up, the build-up, the climax, and the conclusion.

• T​rue

• False

20. True or False: When creating a story around your data for your audience, ensuring the visualizations used are appropriate is one of the most important requirements.

• T​rue

• False

21. True or False: Colorblindness is so rare that you really don’t need to worry about picking an accessible palette.

• T​rue

• False

22. Which of these charts best represents a “scatter plot?

• Meta Marketing Analytics – Course 2 Week 4 (Image 3)
• Meta Marketing Analytics – Course 2 Week 4 (Image 4)
• Meta Marketing Analytics – Course 2 Week 4 (Image 5)
• Meta Marketing Analytics – Course 2 Week 4 (Image 6)

In a scatter plot each measurement is represented as an individual point in a Cartesian coordinate grid. This type of chart can be used to graph any pair of numerical data, one variable on each axis, to look for a relationship.

23. Which of these actions will you do first when using Tableau to create a data visualization?

• Preview the data on Tableau’s Data Source screen.
  • Select a specific data table for preview

• Connect Tableau to a data source

• Change the data types that Tableau assumes for your data fields.

24. When you create a chart using the “double-click method,” what must you double-click to create the chart?

• At least one data field

• A specific chart type
• A specific data type
• A worksheet tab

25. Which of the following parts of the worksheet determines which data are represented as “marks” in your chart?

• The “Marks” shelf.
  • The “Columns” shelf.
  • The “Rows” shelf.

• All of the above choices.

• None of the above choices.

26. True or false: a Tableau Dashboard lets you filter the data on multiple charts by interacting with a single chart?

• True

• False

Course 3: Data Analysis with Spreadsheets and SQL

Graded Quiz: Working with Data in Spreadsheets

Which of the following statements is true about spreadsheets?

• Spreadsheets allow you to take large amounts of data and turn it into meaningful insights.

• Spreadsheets automatically correct errors and guarantee 100% accuracy.
• Spreadsheets perform complex data analysis without any limitations.
• Spreadsheets provide built-in machine-learning algorithms for predictive analysis.

In which of the following scenarios would you use spreadsheets to analyze data?

• To automatically correct data errors and duplicates
  • To interpret large data sets for predictive analysis
  • To perform real-time data presenting

• To organize and present data in a clear, concise way

What is one of the limitations of spreadsheets in data analysis? Select all that apply.

• Limited control of modeling and visualizing data

• Limited when handling small data sets

• Limited scalability

• Limited statistical analysis

In which scenario would a data analyst choose to use spreadsheets during the Obtain stage of data analysis?

• They are performing advanced statistical analyses
  • They are working with complex, large-scale datasets
  • They are searching for automated large-scale data visualization capabilities

• They are working with smaller datasets that don't require complex processing

A data analyst obtains a dataset with customer information. They notice there are multiple entries with the same email addresses. What functionality do spreadsheets offer that will help them resolve this issue?

• Spreadsheets offer complex querying capabilities for data extraction.
  • Spreadsheets enable integration with external databases.

• Spreadsheets offer data cleaning features like removing duplicates and sorting and filtering.

• Spreadsheets offer collaboration and real-time sharing capabilities.

A data analyst receives a dataset containing customer purchase history. How do spreadsheets help them explore this data and gain insights into customer behavior?

• Spreadsheets offerbuilt-in functionalities for creating visual representations, such as charts and graphs, to visualize purchasing trends, patterns, and relationships.

• Spreadsheets generate predictive models for customer behavior analysis.
• Spreadsheets allow integration with social media platforms for customer interaction analysis.
• Spreadsheets provide real-time collaboration features for team-based data analysis.

Which of the following tasks require specialized tools like Python for modeling in data analysis?

• Building machine learning models

• Importing data from several sources
• Creating bar charts for visualization
• Conducting data cleaning and formatting

In which of the following scenarios would it be beneficial to use a powerful programming language like Python instead of spreadsheets?

• Handling large datasets and performing complex data analyses

• Creating simple charts and graphs for data presentations
• Collaborating with team members to interpret data
• Conducting simple calculations and basic visualizations

Graded Quiz: Data Analysis with Spreadsheets

When working with data in Google Sheets, you begin by uploading the data. How do you upload the data?

• Import data by clicking “Import”
  • Copy and paste all columns to Google Sheets
  • Drag and drop data the from desktop directly into Google Sheets

• Upload files to Google Drive then open with Google Sheets

What conditional filters can you apply when working with data in Google Sheets? Select all that apply.

• “Text contains”

• “Is equal to”

• “Sort A to Z”

• “Date is before”

What is the purpose of formatting data in spreadsheets?

• It makes the spreadsheet more visually appealing
  • It automatically performs calculations

• It helps ensure the data is consistent, accurate, and ready for analysis

• It organizes data in alphabetical order

A data analyst uses a spreadsheet to track monthly sales data and aims to determine the average monthly sales to assess the team's performance. Why would the analyst use functions to determine the average monthly values?

• Functions allow them to quickly calculate averages, sums, and more from large data sets

• Functions allow them to import data sources into the spreadsheet
• Functions help create visually appealing graphs
• Functions help organize data in a spreadsheet

What are the formulas for calculating the highest and lowest values in a range in Google Sheets?

• =MIN(values) and =MAX(values)

• =AVERAGE(values) and =SUM(values)

• =MEDIAN(values) and =AVERAGE(values)

• =HIGH(values) and =LOW(values0

A data analyst aims to determine the relationship between a company's promotions and sales. What formula should they use to determine the correlation between the two data points?

• =CORREL(data_range1, data_range2)

• =CORREL(data_range1)(data_range2)

• =CORR(data_range1, data_range2)

• =CORREL(data_range)

A data analyst aims to determine dietary habits by analyzing daily caloric intake across five food groups. What chart should the analyst use to show how much of a whole each food group represents?

• Bar graph
  • Scatter plot
  • Line chart

• Pie chart

Which of the following relationships describes a negative correlation?

• When website visits increase, sales decrease

• When customers increase, sales stay the same
• When website visits increase, new customers stay the same
• When product categories increase, sales increase

Fill in the blank: _____ is a method by which a set of inputs and related outputs are provided to a computer system, and this process is referred to as training.

• Data visualization
  • Linear regression

• Machine learning

• Trend line

What would you use a linear regression model for?

• To predict a variable’s value based on another variable’s value and make predictions

• To use machine learning in data modeling
• To calculate the average of a data set
• To create data visualizations and charts

Graded Quiz: Extracting Data with SQL

What term describes the process of extracting and shaping data to answer specific questions?

• Aggregating
  • Analysis
  • Manipulating

• Querying

What is one of the benefits of learning a new programming language like SQL?

• It allows you to automate repetitive tasks when working in spreadsheets

• It improves your skills as a data analyst when working with databases and data analytics programs beyond spreadsheets

• It improves the quality of your data by enabling you to extract and shape relevant data
• It allows you to perform advanced data manipulation in spreadsheets

True or False: You can use SQL to select specific data and perform calculations, like finding a dataset's maximum or minimum values.

• True

• False

Which of the following parts are required when using the QUERY function? Select all that apply.

• Type

• Query

• Data

• Headers

A data analyst working in Google Sheets writes the statement "SELECT A, C." What does this query intend to do?

• Retrieve results from columns A and C in that order
  • Add the values in columns A and C
  • Sort the data in columns A and C

• Retrieve results from columns A and C in no particular order

What are non-numeric values called?

• Strings

• Integers
• Operators
• Booleans

True or False: The ORDER BY clause enables you to include in your query how many resulting rows you want or the number of resulting rows up to a limit.

• True

• False

When working in Google Sheets, how would you modify your query to calculate the sum of values from columns D and E?

• Include D + E directly after selecting columns

• Include D, E directly after selecting columns

• Include D & E directly after selecting columns
• Include D_E directly after selecting columns

You are working with a data set containing a company's sales figures, including columns for item costs (D) and quantity sold (E). Which of the following queries will calculate the average item cost?

• SELECT SUM(D), COUNT (D) / SUM(E), COUNT (E)

• SELECT SUM(D), COUNT (D), SUM(E), COUNT (E)
• SELECT SUM(D), COUNT (E)
• SELECT SUM(D), COUNT (D) + SUM(E), COUNT (E)

Which aggregation functions are commonly used with the GROUP BY clause?

• COUNT, SUM, AVG, MIN, MAX

• ORDER BY, MIN, MAX
• WHERE, AND ORDER BY
• COUNT, SUM, AVG, AND ORDER BY

Graded Quiz: Data Visualization

Which of the following data analysis tasks can you complete in Google Sheets or Excel? Select all that apply.

• Advanced data modeling
  • Building simple dashboards

• Quick changes and edits

• Creating visualizations

Which of the following statements accurately describes the roles of visualization tools in data analysis?

• Advanced visualization tools are typically used during the Explore phase of data analysis, and spreadsheets are used during the iNterpret stage.
  • Advanced visualization tools offer basic data storytelling features, and spreadsheets offer advanced exploring, cleaning, and insights into data.

• Advanced visualization tools offer more flexibility and advanced features for storytelling with data, and spreadsheets are used for exploring, cleaning, and providing a general overview of data.

• Advanced visualization tools offer less flexibility but more advanced features for storytelling with data, and spreadsheets are used to interpret that data.

What types of charts are typically used to show percentages in different groups?

• Line charts

• Pie charts

• Scatter plots
• Bar charts

In which of the following scenarios would you use a pie chart?

• To compare recruitment efforts across four channels: job boards, referrals, career fairs, and online applications
  • To display the distribution of customer ages and locations across the United States

• To display a company’s average experience level compared to the industry average

• To compare the performance of two products over a year across different department stores

What are trend charts commonly used for in data analysis?

• To summarize data
  • To display the relationship between variables
  • To compare the distribution of numerical data

• To represent the change of data over time

Fill in the blank: In data analysis, _____ are used to visually represent data values as dots, and each dot represents two variables.

• heat maps
  • pie charts

• scatter plots

• bar charts

What happens when you connect your data to your source file in Tableau?

• Tableau automatically generates a dashboard
  • You can immediately begin creating visualizations

• The file appears in the Data Source screen

• Your file is shared with collaborators

After linking your Excel data in Tableau Public, how do you connect the specific data you want to work with?

• Grab the sheet from your desktop and drag it to the Tableau screen
  • Use the “File” menu to import data

• Grab the sheet from the left-side pane and drag it to the “Drag tables here” area

• Click “Data” and select your data

When would you use Tableau for data visualization instead of spreadsheets?

• To perform basic calculations

• For simple and flexible data presentation

• To simplify data cleaning
• For real-time team collaboration

You’re creating a scatter plot in Google Sheets. After setting the horizontal and vertical titles for the chart, you add a trendline. What steps did you follow to add this trendline?

• In Settings, click “Trendline”
  • In Chart Editor, click “Trendline,” then check the “All” box

• In Chart Editor, click “Customize,” then check the “Trendline” box

• Double-click on the main screen and select “Trendline”

Which of the following statements is true about data visualization?

• Data visualization is suitable for small datasets instead of large datasets

• The type of visualization you use depends on the question you are trying to answer

• All data visualization tools are open-source
• Data visualization is used for static representations

What type of chart best represents the change of data trends over time?

• Bar graph
  • Histogram

• Line chart

• Pie chart

A data analyst compares a company's recruitment efforts across four channels: job boards, referrals, career fairs, and online applications. What type of chart will help them complete this task?

• Pie chart

• Line graph
• Scatter plot
• Bar graph

In which of the following scenarios would you use a scatter plot to visualize your data?

• To examine the sales generated by several product categories

• To examine the relationship between hours of study and test scores

• To display the predicted rainfall across cities
• To compare the total population in five countries

Which of the following statements is true about Tableau Public?

• It is used to perform advanced statistical analysis
  • It can connect to a select few data sources

• It can connect to a wide variety of datasets stored in multiple ways

• It is a paid software with no free trial available

When connecting to a CSV file in Tableau, which file option should you select?

• Microsoft file
  • JSON file

• Text file

• PDF file

True or False: Tableau Public and spreadsheets offer identical capabilities, and the choice between them depends on your preference.

• True

• False

Graded Quiz: Creating Dashboards

Which of the following statements accurately describes dashboards in data analysis?

• A dynamic visualization tool that displays data and provides a view of key metrics

• A visual that combines and displays small datasets
• A method for building large-scale data models
• A type of software used for cleaning data

What should you do before designing a dashboard?

• Choose the style and appearance of your dashboard

• Establish the objectives, and the key metrics and data that align with these objectives

• Choose which software to is best suited for your data
• Collect and upload your data to the software tool you are using

A data analyst is designing a dashboard to show how production costs have affected profitability over the last five years. They aim to keep the dashboard simple and easy to understand. Which of the following best practices should they consider to simplify the dashboard?

• Include irrelevant data for a broader overview
  • Keep titles long and open to interpretation
  • Use different font sizes and colors throughout the dashboard

• Avoid clutter by including key data only

A data analyst connects an Excel workbook to a new Tableau project to display their findings on sustainability standards. What is the next step in creating their dashboard?

• Add a chart to the dashboard
  • Choose a layout for the dashboard
  • Add interactivity to the dashboard

• Create visualizations like bar and line charts

In Tableau, what is the purpose of the Filtering Action?

• To provide users with a way to customize the data that they see

• To provide users with a way to navigate to another sheet
• To provide users with a way to dynamically change their visualizations when selecting a subset of data from another visualization
• To provide users with a way to navigate to external data sources

Which of the following actions helps make dashboards in Tableau interactive?

• Add a dashboard navigation action
  • Insert a group action

• Insert a URL action

• Create a chart

You are creating a presentation to communicate the findings of your analysis. You gather your data and the charts and graphs showing the main patterns and trends. What else do you need to create a compelling data story?

• A narrative that provides context for the data and visuals

• An interactive dashboard for the audience to access
• A list of credible sources used in the analysis
• A prediction for future outcomes

Which of the following is a common color-related issue which you should avoid when working data visualizations?

• Considering people with colorblindness

• Using too much color

• Using familiar colors in familiar ways
• Using colors that are easy to tell apart

You’ve gathered the findings of your analysis and are putting together a presentation. How should you start your story?

• With an overview of the key findings through data visualization
  • With an outline of the steps required to address the reason for the analysis

• With a hook, a question or concern that communicates the theme of the story

• With an explanation of the steps taken during the analysis and an overview of the findings

Which of the following best practices should you consider when designing a dashboard?

• The target audience is irrelevant, as all dashboards follow a standard structure
  • Interactive elements should be limited to one per dashboard
  • Using different fonts and colors are easier to read and understand

• Adding interactive elements like filters and sorting options improves the user experience

Course 4: Python Data Analytics

Graded Quiz: Introduction to Python

Which of the following is something you would likely produce in the Explore step of the OSEMN process?

• Visualizations

• Supportive data
• Presentations
• Reports

A data analyst is labeling containers of stored information. What is the name for these labels?

• Methods
  • Functions
  • Dictionaries

• Variables

What type of variable is the following?

inches_of_rain = 5.02

• Decimal
  • Boolean

• Float

• String

Given the following code snippet, how can we “cast” or change the data type of the string value to a float?

math_grade = “100”

• str(math_grade)

• float(math_grade)

• int(math_grade)
• bool(math_grade)

A data analyst is working with a list of store locations in Python. Examine this code and select the expected output:

store_locations = ['ATL', 'AUS', 'CHI', 'NYC', 'SFO']

store_locations[2]

• 'NYC'

• 'CHI'

• IndexError

• None

A data analyst is working with a list of ice cream flavors in Python. Examine this code and select the expected output:

ic_flavors = ['ChocChip', 'Van', 'Choc', 'MintChip', 'Straw']

ic_flavors[0:3]

• ['ChocChip', 'Van', 'Choc', 'MintChip', 'Straw']

• ['Choc Chip', 'Van']

• ['MintChip', 'Straw']

• ['ChocChip', 'Van', 'Choc']

A data analyst is working with a dictionary of dog breed sizes in Python. Examine this code and select the expected output:

dog_size = { 'lab': 'medium', 'terrier': 'small', 'great dane': 'large', 'chihuahua': 'xsmall' }

dog_size['great dane']

• 'great dane': 'large'

• ‘large’

• ‘xsmall’

• 'small’

A data analyst is working with a list of the most popular items at a restaurant in Python. Examine this code and select the expected output:

pop_items = ['hot dog', 'hamburger', 'pizza', 'calzone', 'salad', 'water']

'soda' in pop_items

• ‘drink’

• False

• No
• True

You are working on a data analysis project for an airline. You’ve decided to use if, elif, and else clauses to sort passengers by how often they fly. You have written the following code:

annual_flights = 8

if annual_flights >= 10:

print('Frequent Flier')

elif annual_flights >= 5:

print('Occasional Flier')

print('Standard Flier')

What would you expect the output of this code to be?

• Frequent Flier
  • Standard Flier
  • You get an error message

• Occasional Flier

When working with functions in Python, what term describes the actual data given to a function via its parameters?

• Arguments

• Data types
• Variables
• Keys

Graded Quiz: Obtaining and Scrubbing Data with Pandas

A data analyst is going to use the library addup and wants to give the library the alias au. Which of the following pieces of code should the analyst use?

• import addup as au

• rename au to addup

• alias au as addup

• apply alias au to addup

A data analyst is using Pandas to analyze recent trends in their social media campaigns. They have recent data saved in a CSV named “smcdata”. Which of the following pieces of code would allow them to import this data?

• pandas.import_csv('smcdata.csv')

• pandas.read_csv('smcdata')

• pandas.read_csv('smcdata.csv')

• import_csv as ('smcdata.csv')

If you want to preview the first five rows of a DataFrame assigned to the variable df, which of the following methods should you use?

• df.prev()

• df.first5()

• df.head()

• head.df()

When using Pandas, what is a series object?

• A random sample pulled from a DataFrame

• A single array of data, like a column of data from a DataFrame

• A preview of the first five rows of a DataFrame
• A single horizontal slice, like a row of data from a DataFrame

You want to create a mask that identifies a subset of customers who visit your store at least twice a week. The DataFrame is assigned the variable df and the applicable information is stored in the weeklyvisits column. Which of the following masks should you use?

• my_mask_mult_weekly_visits = df['weeklyvisits'] >= 2

• my_mask_mult_weekly_visits = df['weeklyvisits'] <= 2
• my_mask_mult_weekly_visits = df['weeklyvisits'] == 2
• my_mask_mult_weekly_visits = df['ordertotal'] == 2

When scrubbing data in Python, what is one example of an issue that will likely require additional context before fixing?

• Duplicate data
• Missing data
• Unsupportive information
• Formatting issues

You are scrubbing a DataFrame (df) and need to remove an unnecessary column called date_of_sale_copy. Which of the following methods can you use?

• df_clean = df.pull(columns='date_of_sale_copy')

• df_clean = df.drop(columns='date_of_sale_copy')

• df_clean = df.delete(columns='date_of_sale_copy')
• df_clean = df.remove(columns='date_of_sale_copy')

You are scrubbing a DataFrame and want to find exact copies of rows in your dataset. Which of the following methods can you use?

• duplicated()

• cloned()
• copied()
• multiple()

You are scrubbing a DataFrame and want to find missing values in your dataset. Which of the following methods can you use?

• isnull()

• nullna()
• empty()
• ismissing()

You are scrubbing a DataFrame (df) and notice that a number of age values for subscribers are negative. You know from context that people’s ages should be all positive integers and these instances are typos. You want to replace negative values in df.subscribers with positive values in your dataset. Which of the following pieces of code will change those negatives to positives?

•   negative_ages = df.ages = -10

df.ages[negative_ages] = -1 * df.ages[negative_ages]

•   negative_ages = df.ages < 0

df.ages[negative_ages] = invert[df.ages[negative_ages]

•   negative_ages = df.ages < 0

df.subscribers[negative_ages] = -1 * df.ages[negative_ages]

•   negative_ages = df.ages < 0

df.ages[negative_ages] = pos df.ages[negative_ages]

Graded Quiz: Exploring Data with Python

Which of the following tools cannot be used to create visualizations like graphs and charts?

• Seaborn

• Sci-kit-learn
• Pandas
• MatPlotlib

Which method is used to view a specified number of rows from the end of a Pandas dataFrame?

• head()

• tail()

• sample()
• info()

You are given a DataFrame stored in a variable, df, and it includes a column of sales_total. How can you filter the DataFrame to only show the rows that have a sales total of $1000 or more?

• df.sales_total <= 1000
  • df[‘sales_total’] <= 1000

• df.sales_total >= 1000

• df[‘sales_total’] >= 1000

You are given a DataFrame stored in a variable, df. You want to create a boxplot of only the column with the name ‘petal_width’. Which of the following code snippets in Pandas would NOT be a viable option to achieve this?

• df.petal_width.plot.box()

• df['petal_width'].plot.box()

• df[‘petal_width’].plot(box)

• df.plot.box(column='petal_width')

Which type of exploratory visualization can be used to compare how one variable goes up or down compared to another?

• Normalized

• Relationship

• Category
• Distributions

Which type of chart should you use to compare the relationship between two variables, but you don't want the data points to seem connected?

• Violin plot

• Scatter plot

• Box plot
• Histogram

Which of the following is an example of a Python aggregation function?

• count()

• plot()
• describe()
• groupby()

Which method in Python allows us to “split” the data by values in a column then aggregate the information based on those values?

• agg()
  • apply()
  • mean()

• groupby()

Which method is used to set the style in the Seaborn visualization library?

• orient()

• style()

• set()

• seaborn()

Which code snippet correctly calls for a violin plot by using the Seaborn visualization library as ‘sns’ and Pandas dataframe as ‘df’?

• sns.violin(data=df, y=’height_cm’, x= ‘age’, hue = ‘sex’)

• sns.violinplot(data=df, y=’height_cm’, x= ‘age’, hue = ‘sex’)

• sns.violin.df(y=’height_cm’, x= ‘age’, hue = ‘sex’)
• sns.violinplot =[data=df, y=’height_cm’, x= ‘age’, hue = ‘sex’]

Matplotlib and Seaborn build on your data to create which kind of visualizations?

• Graphs

• Data tables
• Methods
• Libraries

Which method is used to view a general breakdown of data including mean, standard deviation, min, max, and quartiles?

• sample()

• describe()

• head()
• info()

You are given a DataFrame stored in a variable, df, and it includes a column of sales_total. How can you filter the DataFrame to only show the rows that have a sales total of $1000 or more?

• df.sales_total <= 1000

• df.sales_total >= 1000

• df[‘sales_total’] <= 1000

• df[‘sales_total’] >= 1000

You are given a DataFrame stored in a variable, df. How can you use Pandas to create a box plot of the numerical columns?

• df.plot.box()

• df.plot(box)
• df.box.plot()
• df.chart.box()

Which type of exploratory chart can be used to illustrate the percentage of voters by age in a local election?

• Relationship

• Category

• Distributions

• Normalized

When reviewing both the distribution and magnitude of a particular variable, which of the following chart types would work best?

• Box plot
  • Stacked bar chart
  • Histogram

• Violin plot

Which of the following code snippets correctly uses the groupby() method to compare the average heights of male and female giraffes with columns ‘sex’ and ‘height_cm’?

• df.groupby(‘sex’).mean(‘height_cm’)

• df.groupby(‘sex’)[‘height_cm’].mean()

• df.groupby(‘sex’).[‘height_cm’].mean()
• df.groupby(‘sex’).mean() = [‘height_cm’]

The Seaborn method set() without any parameters is used to do which of the following?

• Apply the described theme to the visualization.

• Use Seaborn’s default theme

• Use matplotlib’s default theme
• Make the dataset immutable

What is the required first parameter when building a Seaborn visualization using a method like boxplot()?

• the x variable

• the DataFrame

• the y variable
• the chart type

Graded Activity: Full OSEMN

Question 1

Remove all rows that have are missing either the Product_Name or the Product_Category. Assign the cleaned DataFrame to the variable df (overwriting the original DataFrame.).

df = df.dropna(subset=['Product_Name', 'Product_Category'])

Question 2

Find any clearly "incorrect" values in the Price column and "clean" the DataFrame to address those values.

Ensure you make the changes to the DataFrame assigned to the variable df.

# Convert all non-numeric values to NaN

df['Price'] = pd.to_numeric(df['Price'], errors='coerce')

# Remove rows with negative or zero values

df = df[df['Price'] > 0]

# You might also want to remove extremely high values, for example, anything above $10,000

df = df[df['Price'] <= 10000]

Question 3

After you've done the cleaning above, remove any column that has more than 500 missing values.

Ensure you make the changes to the DataFrame assigned to the variable df.

df = df.dropna(thresh=len(df) - 500, axis=1)

Question 4

Address the other missing values. You can replace the values or remvove them, but whatever method you decide to clean the DataFrame, you should no longer have any missing values.

Ensure you make the changes to the DataFrame assigned to the variable df.

# For numerical columns

for col in df.select_dtypes(include=['float64', 'int64']).columns:

df[col] = df[col].fillna(df[col].mean())

# For categorical columns

for col in df.select_dtypes(include=['object']).columns:

df[col] = df[col].fillna(df[col].mode()[0])

Question 5

Create a Subtotal column by multiplying the Price and Quantity values. This represents how much was spent for a given transaction (row).

df['Subtotal'] = df['Price'] * df['Quantity']

Question 6

Determine most common category (Product_Category) purchases (number of total items) for both Product_Line categories. Assign the (string) name of these categories to their respective variables common_category_cat & common_category_dog.

# Assuming 'df' is your DataFrame and it has columns 'Product_Line' and 'Product_Category'

grouped = df.groupby('Product_Line')['Product_Category'].value_counts()

common_category_cat = grouped['cat'].idxmax()

common_category_dog = grouped['dog'].idxmax()

Question 7

Determine which categories (Product_Category), by Product_Line have the median highest Price. Assign the (string) name of these categories to their respective variables priciest_category_cat & priciest_category_dog.

# Assuming 'df' is your DataFrame and it has columns 'Product_Line', 'Product_Category' and 'Price'

grouped = df.groupby(['Product_Line', 'Product_Category'])['Price'].median()

priciest_category_cat = grouped['cat'].idxmax()

priciest_category_dog = grouped['dog'].idxmax()

Question 8

You want to emphasize to your stakeholders that the total number of product categories sold differ between the two Product_Line categories ('cat' & 'dog').

Create a horizontal bar plot that has Product_Category on the y-axis and the total number of that category sold (using the Quantity) by each Product_Line category. Also change the axis labels to something meaningful and add a title.

You will likely want to use Seaborn. Make sure you set the result to the variable ax like the following:

ax = # code to create a bar plot

import seaborn as sns

import matplotlib.pyplot as plt

# Assuming 'df' is your DataFrame and it has columns 'Product_Line', 'Product_Category' and 'Quantity'

grouped = df.groupby(['Product_Line', 'Product_Category'])['Quantity'].sum().reset_index()

plt.figure(figsize=(10, 8))

ax = sns.barplot(x='Quantity', y='Product_Category', hue='Product_Line', data=grouped)

ax.set_xlabel('Total Quantity Sold')

ax.set_ylabel('Product Category')

plt.title('Total Quantity of Product Categories Sold by Product Line')

plt.show()

Question 9

Based on the plot from Question 8, what would you conclude for your stakeholders about what products they should sell? What would be the considerations and/or caveats you'd communicate to your stakeholders?

Write at least a couple sentences of your thoughts in a string assigned to the variable answer_to_9.

The cell below should look something like this:

answer_to_9 = '''

I think that based on the visualization that ****.

Therefore I would communicate with the stakeholders that ****

'''

answer_to_9 = '''

Based on the visualization, it appears that certain product categories are more popular in each product line. For the 'cat' product line, the most popular categories are X, Y, and Z, while for the 'dog' product line, the most popular categories are A, B, and C.

Therefore, I would communicate to the stakeholders that focusing on these popular categories could potentially increase sales. However, it's important to consider that this data only shows the quantity of products sold, not the profit generated from each sale. It's possible that less popular categories could be more profitable due to higher prices or lower costs.

Additionally, this data is historical and may not accurately predict future trends. Market conditions, customer preferences, and other factors can change over time. Regularly reviewing sales data and adjusting the product strategy accordingly would be a prudent approach.

'''

Question 10

The plot you created for Question 8 is good but could be modified to emphasize which products are important for the business.

Create an explanatory visualization that emphasizes the insight you about the product category. This would be a visualization you'd share with the business stakeholders.

Make sure you set the result to the variable ax like the following:

ax = # code to create explanatory visualization

import matplotlib.pyplot as plt

import seaborn as sns

import pandas as pd

# Assuming df is your DataFrame and it has columns 'Product' and 'Sales'

df = pd.DataFrame({

'Product': ['Product A', 'Product B', 'Product C', 'Product D', 'Product E'],

'Sales': [1000, 2000, 3000, 4000, 5000]

})

# Sort the products by sales

df_sorted = df.sort_values(by='Sales', ascending=False)

# Create a bar plot

plt.figure(figsize=(10, 6))

ax = sns.barplot(x='Sales', y='Product', data=df_sorted, palette='viridis')

# Set labels

ax.set_xlabel('Sales')

ax.set_ylabel('Product')

ax.set_title('Sales by Product')

plt.show()

Graded Quiz: Modeling and Interpreting Data with Python

Which phase of the OSEMN framework uses the data we have collected to try to consider what might happen next?

• Scrub

• Model

• Interpret
• Explore

What type of models help identify groups of data that are similar but don't rely on pre-defined groups?

• Forecasting
  • Regression

• Clustering

• Classification

Which of these Python libraries uses machine learning to create models?

• Matplotlib

• Scikit-learn

• Pandas
• Seaborn

Which of the following best describes the prediction in a regression analysis?

• The group in which a particular piece of data belongs
  • Other similar types of data from your dataset

• A number based on the provided data from the other features.

• The length of time of your model

Which of the following is most likely to cause your model to fail?

• Using the model only for what it was designed for
  • Running your model too long

• Model rot

• Using data from unbiased sources

After sharing your findings with stakeholders what should you do?

• Suggest next steps

• Clean up “dirty data”
• Create models
• Investigate numerical quantities

Your goal is to determine whether your new customer falls into the “casual shopper”, “experienced browser”, or “high roller” category. Which type of model should you use?

• Clustering
  • Regression

• Classification

• Grouping

Which one of the following describes a difference between exploratory and explanatory visualizations?

• Explanatory visualizations don’t need to consider how technical the audience is.

• Explanatory visualizations are created to highlight important findings to others.

• Explanatory visualizations are not intended to show to others.
• Explanatory visualizations are for learning more about the data.

You want to better understand your data for a classification model with a 0.60 mean accuracy score. What should you do?

• Use the predictions to make recommendations
  • Start with a new model from scratch

• Verify if items were correctly classified so you know the model works for those items

• Remove any data points from your data set that conflicted with the model

Which scenario best represents when you should use an explanatory visualization?

• You need to find out how many users you expected to gain after an email campaign
  • You want to see if your data has any bias in it
  • You want to figure out if you are experiencing “model rot”

• You need to demonstrate how certain campaigns resulted in low conversion metrics

Course 5: Statistics for Marketing

The formula for finding the z-score for a data value is z = (value – mean)/std.

• True

• False

What is the formula for finding the mean of a dataset in a spreadsheet? (Assume that the data is in the cells A1 to A100.)

• =MEAN(A1:A100)

• =AVERAGE(A1:A100)

• =AVE(A1:A100)
• AVERAGE(A1-A100)

What is the formula for finding the range of a dataset?

• (min value – mean)/std
  • min value – max value

• max value – min value

• (max value – min value)/std

What is the mode for the following set of numbers? 5, -1, 3, 8, 2, 1, 0

• There is no mode.

• The mode is 1.
• The mode is -1.
• The mode is 5.

What is the median for the given dataset? 1, 3, 7, 5, 3

• The median is 4.

• The median is 3.

• The median is 5.
• The median is 7.

What is the mean of the given set of numbers? 10, 20, 30, -15, -25, -20

• The mean is 0.

• The mean is 10.
• The mean is 30.
• The mean is -25.

What does a measure of variation tell you about a dataset? I. How spread out the data is II. Where the center of the data is III. How large the dataset is IV. All of these

• II

• IV

• III

• I

What do measures of central tendency tell you about a dataset?

1. They represent how spread out the data is
2. They represent the middle of the dataset

III. They tell you how large the dataset is

• I, II, and III
  • I

• II

• III

Week 1: Descriptive Statistics

PRACTICE QUIZ: MEASURES OF CENTRAL TENDENCY

1. Which of the following is NOT a measure of central tendency?

• Median
• Variance
• Mean
• Mode

2. Based on the video, what are measures of central tendency?

• They are numbers that tell you how accurate the data is.
• They are numbers that represent how spread out the data is in a dataset.
• They identify which number in the dataset is the middle one.
• They are numbers that represent the “middle” of a dataset.

3. How might a marketer find value in knowing the middle of a dataset?

• I. It can help predict future sales numbers.
• II. It can help assess the impact of marketing efforts.
• III. It can provide a reasonable baseline for what to expect from a particular demographic.
• II and III.
• I and III.
• III only.
• I, II, and III.

4. What is the mean of the following set of numbers?

• 1, 4, 3, 10, 12
• The mean is 3.
• The mean is 4.
• The mean is 6.
• The mean is 30.

5. Which measure of central tendency would be the most reasonable for defining the middle of the dataset below?

• -2, 4, 1, -1, 3, 73
• Mean, median, or mode is suitable.
• The median.
• The mean.
• The mode.

6. Calculate the median for the following set of numbers.

• 1, 2, 2, 3, 14, 2
• The median is 2.
• The median is 1.
• The median is 4.
• The median is 14.

7. In a spreadsheet, the following formula will find the mean of the numbers in the cells E200 to E350.

=AVERAGE(E200:E350)

• T​rue
• False

8. What is the mode for the following set of numbers?

3, 1, 10, 9, 2, 5

• There is no mode.
• The mode is 4.
• The mode is 5.
• The mode is 10.

9. What is an advantage the median has over the mean?

• It better represents the middle for large datasets.
• It better represents a typical value when the values in the dataset are all close to each other.
• It handles negative numbers better.
• The median is insensitive to outliers.

10. What is the mean of the following set of numbers?

• 1, 2, 2, 3, 14, 2
• The mean is 2.
• The mean is 24.
• The mean is 14.
• The mean is 4.

11. In a spreadsheet, the following formula will find the mode of the numbers in the cells A1 to A1000.

=(MODE A1:A1000)

• T​rue
• False

12. Calculate the median for the following set of numbers.

-4, 1, 7, -2, 48, 22, -11

• The median is 1.
• The median is 48.
• The median is 0.
• The median is -2.

13. In a spreadsheet, the following formula will find the mean of the numbers in the cells D2 to D20.

AVERAGE(D2:D20)

• T​rue
• False

14. Which of the following is/are measure(s) of central tendency?

• Variance
• Mean
• Median
• Mode

• Mean, Mode, and Median
• Variance, Median, Mode
• Variance, Mean, Mode
• Variance, Mean, Median

15. What is the mode(s) for the following set of numbers?

7, -7, 4, 0, -1, -7, 0

• The mode is 0.
• The modes are -7 and 0.
• The mode is -7.
• There is no mode.

PRACTICE QUIZ: MEASURES OF DISPERSION

1. How can a z-score be useful?

• I. It can help in determining if a data value is high or low in the population.
• II. It tells you how many standard deviations from the mean a data value is.
• III. It can be used to determine data outliers.
• II and III
• All three are ways a z-score can be useful.
• I and III
• I and II

2. Measures of variation is an alternative name for measures of central tendency.

• True.
• False

3. The formula for finding the z-score for a data value is

z = (value – mean)/std.

• True
• False

4. What is the purpose of a measure of variation?

• It provides an indication of how spread out the data is.
• It gives an idea of where the middle of the data is.
• It determines the size of the dataset.
• It determines the accuracy of the data.

5. Which of the following are examples of measures of variation?

• I. Range
• II. Standard deviation
• III. Mean
• All three.
• I and II
• II and III
• I and III

6. What is the range for the following dataset?

2, 3, -5, 8, 0, -2

• -5
• 8
• 13
• 5.5

7. Suppose that you are given the following data. Would the range be a reasonable measure of the spread in the data? Why or why not?

2, 1, 5, 10, 6, 45

• Yes, it is reasonable because there are no negative numbers in the dataset.
• Yes, it is reasonable because the range is positive.
• No, it is not reasonable because the range is too large.
• No, it is not reasonable because there is an outlier.

8. For a normal distribution how many data values should you expect to fall within two standard deviations of the mean?

• 13.6%
• 95.2%
• 68%
• 47.6%

9. Suppose a dataset has a standard deviation of 4 and a mean of 3. What is the z-score for a data value of 6?

• The z-score is -1
• The z-score is 0.75
• The z-score is 1.0.
• The z-score is -0.75

10. What is the range for the following dataset?

-7, 1, -3, -2, 4, -1

• -7
• 0
• 4
• 11

GRADED QUIZ: DESCRIPTIVE STATISTICS

1. What is the formula for finding the standard deviation in a spreadsheet? (Assume that the data is in the cells A1 to A100.)

• =STDEV(A1:A100)
• =STD(A1:A100)
• =(DEV A1:A100)
• =STANDARDDEVIATION(A1:A100)

2. What is the range for the given dataset?

23, 20, 31, 11, 15, 19

• 23
• 11
• -20
• 20

3. What is the mode for the following set of numbers?

5, -1, 3, 8, 2, 1, 0

• There is no mode.
• The mode is 5.
• The mode is -1.
• The mode is 1.

4. In a normal distribution, what percentage of data values are found above the mean?

• 34%
  • 95.2%
  • 68%

• 50%

5. What is the median for the given dataset?

1, 3, 7, 5, 3

• The median is 4.
• The median is 3.
• The median is 5.
• The median is 7.

6. True or false: The mean is sensitive to outliers.

• True
• False

7. What is the mean of the given set of numbers?

-1, 3, 6, 5, -3

• The mean is 2.
• The mean is 3.
• The mean is 6.
• The mean is 0.

8. What does a measure of variation tell you about a dataset?

• I. How spread out the data is
• II. Where the center of the data is
• III. How large the dataset is
• IV. All of these
• II
• IV
• I (CORRECT)
• III

9. Which of the following is not how a marketer can use a measure of central tendency.

• I. Identifying sales frequency
• II. Predicting customer behavior
• III. Risk analysis
• I
• II
• III (CORRECT)
• None of these

10. Suppose a dataset has a standard deviation of 2 and a mean of 7. What is the z-score for a data value of 3?

• The z-score is -0.75
• The z-score is 0.60.
• The z-score is 2.0.
• The z-score is -2.0

11. What is the mode for the following set of numbers?

• 6, 1, 4, 0, 1, 1, 0
• The mode is 0.
• There is no mode.
• The mode is 1.
• The mode is 4.

12. What is the median for the given dataset?

• 19, 42, 33, 15, 21
• The median is 33.
• The median is 15.
• The median is 21.
• The median is 45.

13. True or false: The median is sensitive to outliers.

• False
• True

14. What is the mean of the given set of numbers?

10, 20, 30, -15, -25, -20

• The mean is -25.
• The mean is 30.
• The mean is 10.
• The mean is 0.

15. How can a marketer use a measure of variation?

• I. Data reliability
• II. Range targeting
• III. Risk analysis
• IV. All of these
• I
• II
• IV (CORRECT)
• III

16. What do measures of central tendency tell you about a dataset?

• I. They represent how spread out the data is
• II. They represent the middle of the dataset
• III. They tell you how large the dataset is
• I
• III
• II (CORRECT)
• I, II, and III

17. What is the median for the given dataset?

1, -2, 3, -1, 2, -3

• The median is -3.
• The median is 3.
• The median is 1.
• The median is 0.

18. True or false: The median is preferred for datasets that have outliers

• True
• False

19. What is the mean of the given set of numbers?

4, 7, 3, 1, 2, 1

• The mean is 0.
• The mean is 2.5.
• The mean is 3.
• The mean is 1.

20. What is the formula for finding the median of a dataset in a spreadsheet? (Assume that the data is in the cells A1 to A100.)

• MEDIAN(A1:A100)
• =MEDIAN_A1:A100
• =MEDIAN(A1:A100)
• =MDN(A1:A100)

21. What is the mode for the following set of numbers?

26, 11, 45, 0, 7, 7, 0

• The mode is 45.
• The mode is 0.
• The modes are 7 and 0.
• The mode is 7.

23. Which of the following is the correct formula for Median?

• MEDIAN(A1:A3)
• =MEDIAN A1:A3
• =MEDIAN(A1:A3)

24. What is the range of the following set of numbers?

• 24, 11, 13, 26, 18, 21, 15
• 13
• -15
• 17
• 1​5

25. What is a popular cut-off for outliers?

• Anything less than 3 standard deviations away from the mean.
• Anything more than 3 standard deviations away from the mean.
• Anything more than 2 standard deviations away from the mean.
• Anything more than 1 standard deviation away from the mean.

26. The equation for z-score is…

• = (Value-Standard Deviation) / Mean
• = ZSCORE(A1 : A3)
• = (Mean – Value) / Standard Deviation
• = (Value-Mean) / Standard Deviation

27. Contingency tables look at how many categorical variables?

• One categorical variable.
• Two or more categorical variables.
• No more than two categorical variables
• None. Contingency tables do not look at categorical variables

28. A correlation coefficient of -0.65 is considered…

• Medium Correlation
• High Correlation
• Low Correlation
• No Correlation

Week 2: Making Predictions with Inferential Statistics

PRACTICE QUIZ: SAMPLING

1. What is the difference between a population and a sample?

• A population includes every individual in a group, while a sample is a subset of a population used to represent a group.

• A sample includes every individual in a group, while a population is a subset of a sample used to represent a group.
• These terms are synonymous.
• A population involves people, but a sample does not.

2. Which of the following are conclusions of the Central Limit Theorem?
3. Large samples should have the same mean and standard deviation as the population.
4. Large samples normalize data.

III. The accuracy of data analysis will always increase as more data is collected.

I and II

I and III

II and III

All of these are conclusions of the theorem.

3. True or false: The minimum sample size should always be 50% of the population.

• True

• False

4. What does the plateau effect state?

• That larger populations yield more reliable results from analysis.

• That after a certain point, adding more data to the sample will not increase accuracy.

• That larger sample sizes are always better.
• That all sample sizes are acceptable in performing analysis.

5. What are the four types of sampling techniques introduced in the lesson?

• I. Simple random, systematic, stratified, cluster
  • II. Simple random, systematic, fast random, cluster
  • III. Simple random, complex random, cluster, point-wise

• I (CORRECT)

• II
• III
• None of these

6. What type of sampling is illustrated in the following scenario?

A company wishes to gauge customer satisfaction. They know that 30% of their population is under the age of 50 and 70% is above the age of 50. They decide to poll 100 customers by choosing 30 customers who are under 50 and 70 who are over 50.

• This is an example of simple random sampling.

• This is an example of stratified sampling.

• This is an example of systematic sampling.

• This is an example of cluster sampling.

7. A company has worksites across the country. Each of the worksites has roughly the same number of employees in similar roles. The company wants to sample their workers, but they are unable to visit all sites to collect their data. How should they go about sampling their population of employees?

• Cluster sampling

• Simple random sampling
• Systematic sampling
• Stratified sampling

8. True or false: When choosing a sample, size doesn’t matter.

• False

• True

PRACTICE QUIZ: DISTRIBUTIONS

1. How can knowing the probability distribution of customer data help a marketer?

• I. It can be used to predict future customer behavior
  • II. It can be used to determine the purchase history of specific customers
  • III. It can inform a marketer about customer preferences
  • I and II

• I and III (CORRECT)

• II and III
• I, II, and III

2. How does data with a high variance affect the shape of a distribution?

• The distribution will have a short, wide shape.

• The distribution will have a tall, wide shape.
• The distribution will have a short, narrow shape.
• The distribution will have a narrow, tall shape.

3. What does a narrow and tall distribution tell you about the variance of the underlying data?

• That the dataset has low variance.

• That the variance is increasing
• That the variance is not important.
• That the dataset has high variance.

4. Which of the following is not a type of distribution discussed in the lesson?

• I. Positive
  • II. Exponential
  • III. Poisson

• I (CORRECT)

• II
• III
• All of these

5. True or false: Data transformations can be used to correct for both skew and kurtosis in the data.

• False

• True

6. What does kurtosis describe?

• It describes how symmetric the data is about the mean.
  • It describes how the data may be pulled to the left or the right.
  • It describes how wide the data is.

• It describes how data may be pulled up or down relative to the normal distribution.

7. What does skew describe?

• It describes how the data may be pulled to the left or the right.

• It describes how wide the data is.
• It describes how data may be pulled up or down relative to the normal distribution.
• It describes how sharp the peak of the data is when compared to the normal distribution.

8. True or false: The following are the four transformations discussed in the lesson:

Cube Root, Square, Square Root, Logarithmic

• False

• True

PRACTICE QUIZ: VARIABLE TYPES

1. What is a quantitative variable?

• It is a variable that represents only large numbers.
  • It is numerical data that is used for labeling.

• It is a variable that represents a numerical value that can be interpreted mathematically.

• It is a variable that represents numbers that can be counted.

2. Which of the following are examples of quantitative variables?

• I. Sales data
  • II. Jacket colors
  • III. Ticket prices
  • All of these are quantitative data types.
  • II and III

• I and III (CORRECT)

• I and II

3. Which of the following are examples of qualitative variables?

• I. The amount earned by a charity drive
  • II. The order of individuals in a list
  • III. Yelp ratings
  • I and II
  • All of these are qualitative data types.

• II and III (CORRECT)

• I and III

4. Quantitative variables can be broken down into two categories. What are they?

• Discrete and continuous

• Discrete and nominal
• Ordinal and continuous
• Nominal and ordinal

.

5. True or false: The position of a company on the Fortune 500 list is an example of an ordinal variable.

• True.

• False.

6. There are two categories of qualitative variables. What are they?

• Nominal and ordinal

• Ordinal and continuous
• Discrete and continuous
• Discrete and nominal

7. True or false: The number of people in a coffee shop is an example of a continuous variable.

• False.

• True

8. True or false: The color of a ball is an example of a nominal variable.

• True.

• False

9. True or false: The count of cars in a parking lot is an example of a discrete variable.

• True.

• False

GRADED QUIZ: SAMPLING, DISTRIBUTION, AND VARIABLES

1. How does the skew affect the shape of the graph of a distribution?

• Skew determines how narrow the graph is.
  • Skew determines how wide the data is.
  • Skew determines how tall the graph is.

• Skew will cause the graph to lean either to the left or right.

2. What sampling technique is depicted in this scenario?

A university athletics department wants to assess the quality of life for its student athletes. There are 1000 student athletes at the school, with 60% male and 40% female. The department polls 100 athletes, choosing 60 male athletes and 40 female athletes.

• Clustering
  • Systematic
  • Simple random

• Stratified

3. True or false: Transformations can correct for skew.

• True

• False

4. What is a quantitative variable?

• A variable that uses numbers as labels.
  • A variable that represents numerical rank.

• A variable that represents a quantity.

• A variable that represents quality.

5. Which of the following is not an example of a qualitative variable?

• The number of stars on a customer review.
  • The place of a runner in a race.

• The square footage of a house.

• A person’s marital status.

6. Which is a subtype of quantitative variables?

• Discrete

• Ordinal
• Random
• Nominal

7. What is a qualitative variable?

• A variable that is numeric.
  • A variable that represents the size of an object.
  • A variable that represents a quantity.

• A variable that represents a quality of an object.

8. What is the exponential distribution?

• A distribution that gives the probability of something happening based on the number of times something else has happened.

• A distribution that involves a component of time.

• A distribution that is shaped like a bell.
• A distribution in which all values have an equal chance of happening.

9. What sampling technique is depicted in this scenario?

A restaurant wants to add a new menu item. The cost of the item to the restaurant is significant, so they only are interested in doing it if they believe that the customers will purchase the dish. They survey the first 20 customers who enter the restaurant each day for a month for feedback.

• Clustering
  • Simple random

• Systematic

• Stratified

10. True or false: Transformations cannot correct for kurtosis.

• False

• True

11. Which of the following is not an example of a quantitative variable?

• The volume of gasoline in a car’s tank.
  • The price of an item on a restaurant menu.
  • The time it takes to fly between two cities.

• A person’s phone number.

12. What are dependent variables?

• They are variables that are numeric.
  • They are the variables that you can control in a test or experiment.
  • They are variables that describe the order of objects.

• They are variables that you measure in a test.

13. What is the uniform distribution?

• A distribution that gives the probability of something happening based on the number of times something else has happened.

• A distribution in which all values have an equal chance of happening.

• A distribution that depends on time.
• A distribution that is shaped like a bell.

14. Which of the following is an example of a quantitative variable?

• The amount paid in taxes.

• A person’s social security number.
• A person’s position in line at the ticket counter.
• The names of the majors at a college.

15. Which one of the following is a subtype of qualitative variables?

• Discrete

• Ordinal

• Continuous
• Random

16. What is the Poisson distribution?

• A distribution in which all values have an equal chance of happening.

• A distribution that gives the probability of something happening based on the number of times something else has happened.

• A distribution that depends on time.
• A distribution that is shaped like a bell.

17. What are the two subtypes of quantitative variables?

• Discrete and continuous

• Nominal and discrete
• Continuous and ordinal
• Ordinal and nominal

18. Which of the following is an example of a qualitative variable?

• Your commute time to work.
  • Rental prices in your town.

• The days of a month.

• The number of lions at the zoo.

19. How does kurtosis affect the shape of the graph of a distribution?

• Kurtosis determines how wide and right-leaning the graph is.
  • Kurtosis determines if the graph leans to the right or left.
  • Kurtosis determines how short and right-leaning it is.

• Kurtosis will cause the graph to be either tall and narrow or short and wide.

20. True or false: Transformations can correct for kurtosis.

• True

• False

21. A sample is…

• A small subset of a population

• The majority of a population
• The same thing as a population

22. Larger sample sizes…

• Are more likely to have the same mean and standard deviation as the population
  • Are more likely to be a normal distribution
  • Are important for accurate statistics

• These are all correct

23. DCB Cleaning mostly works with small or medium companies, but they do also work with a couple large companies. They want to make sure their survey represents small, medium, and large companies. What sampling method should they use?

• Stratified Sampling

• Simple Random Sampling
• Cluster Sampling
• Systematic Sampling

24. If your distribution is tall and skinny, what does that tell you about your variance?

• Nothing; there is no connection between variance and distribution.

• The variance is small

• The variance is high

25. If Calla and Ivy, a florist, wants to look at how many customers enter the store before they sell one of their big bouquets, what distribution would they expect?

• Normal Distribution
  • Uniform distribution

• Poisson Distribution

• Exponential Distribution

26.

Meta Marketing Analytics – Course 3 Week 1 (Image 1)

The above image is an example of what?

• Positive Skew

• Negative Skew
• Positive Kurtosis
• Negative Kurtosis

27. All numbers are continuous variables. True or False?

• False

• True

28. A dog food company wants to record the type of dog a customer owns. Dog Breed would be what kind of variable?

• Discrete
  • Continuous

• Nominal

• Ordinal

29. You have two designs for a logo. You create two banner ads, one with each logo, and you count how many times each banner is clicked. In this example, the logo is your…

• Dependent Variable

• Independent Variable

30. In the context of the graph of a distribution, what is the difference between skew and kurtosis?

• Skew affects the lean of the graph. Kurtosis affects the height and width of the graph.

• Kurtosis causes the graph to lean to the left. Skew causes the graph to lean to the right.
• Kurtosis affects the lean of the graph. Skew affects the height and width of the graph.
• Kurtosis causes the graph to be short and narrow. Skew causes the graph to be tall and wide.

31. What sampling technique is depicted in this scenario?

A student club at a large high school wants to put on a movie night for the rest of the students. They poll ten students from each class (freshmen, sophomores, etc.) to determine the movie.

• One-at-a-time
  • Systematic

• Clustering

• Simple random

32. What are independent variables?

• They are variables that are numeric.
  • They are variables that describe the order of objects.

• They are the variables that you can control in a test or experiment.

• They are variables that you measure in a test.

33. Which one of the following is a subtype of qualitative variables?

• Nominal

• Random
• Continuous
• Discrete

34. What are the two subtypes of qualitative variables?

• Ordinal and discrete

• Ordinal and nominal

• Continuous and discrete
• Nominal and continuous

35. What is the difference between independent and dependent variables?

• Dependent variables are quantitative, while independent variables are qualitative.
  • Independent variables are quantitative, while dependent variables are qualitative.
  • Dependent variables can be controlled in a test or experiment while independent variables are measured.

• Independent variables can be controlled in a test or experiment while dependent variables are measured.

Week 3: Designing Experiments and Testing Hypotheses

EXPERIMENTAL DESIGN AND HYPOTHESES

1. In the context of this course, what is an evaluation question?

• A question that motivates a study or experiment.
• A question about the accuracy of an experiment.
• A question about the results of an experiment.

2. What are possible sources for evaluation questions?

• I. Data
• II. Stakeholders
• III. Managers
• I
• II
• All three.
• III

3. Which of the following is/are parts of a hypothesis?

• I. What will change?
• II. How will it change?
• III. What will cause the change?
• I. and II.
• I. and III.
• All three are the parts of a hypothesis.
• II. and III.

4. What is a hypothesis?

• It is the result of a statistical analysis.
• It is another name for a theory.
• It is a question that motivates a study.
• It is a tentative answer to the evaluation question.

5. What are the two types of studies used to test a hypothesis?

• Experimental and actual.
• Observational and experimental.
• Observational and simple.
• Data driven and actual.

6. Which of these is an example of an observational study?

• Data mining.
• Repeated measures.
• Random trials.
• A/B test.

7. True or false: A/B testing is an example of an experimental study.

• False
• True

8. What are the five steps in experimental design?

• Question, hypothesis, measurement, solving, and analysis.
• Question, hypothesis, define variables, measurement, and analysis.
• Question, theory, define variables, measurement, and analysis.
• Prediction, question, hypothesis, define variables, and analysis.

9. Which of the following is not a part of a hypothesis?

• I. What will change?
• II. How fast is it changing?
• III. What will cause the change?
• All of these.
• II (CORRECT)
• III
• I

10. True or false: Simple surveying is an example of an experimental study.

• False
• True

PRACTICE QUIZ: HYPOTHESIS AND AB TESTING

1. What is AB testing?

• A test to determine if the analysis has bias.
• A study that compares two unrelated things to see which performs better.
• A test to determine the stakeholders of an analysis.
• A study that compares two different versions of something to see which performs better.

2. When performing AB testing, the alternate hypothesis H1 makes what claim?

• That there is no significant difference in the effect between A and B.
• That A and B perform the same or similar.
• That A performs better than B.
• That there is a significant difference in the effect between A and B.

3. In general, what do you conclude for a p-value where p > 0.05?

• Accept H0, accept H1.
• Reject H0, accept H1.
• Accept H0, reject H1.
• Reject H0, reject H1.

4. What does a 95% confidence interval represent?

• The chance of making a type 1 error.
• The range of values within which you may be 5% sure that the true mean falls.
• The chance of making a type 2 error.
• The range of values within which you may be 95% sure that the true mean falls.

5. Which common hypothesis tests were mentioned in the video?

• I. t-test
• II. ANOVA
• III. Chi-squared
• All of these.
• II.
• III.
• I.

6. True or false: The correct syntax for using a t-test in a spreadsheet is:

=ttest(Group1, Group2, Tails, Type)

• False.
• True.

7. When performing AB testing, the null hypothesis H0 makes what claim?

• That there is a difference in the effect between A and B.
• That B performs better than A.
• That A performs better than B.
• That there is no difference in the effect between A and B.

8. True or false: The correct syntax for using a t-test in a spreadsheet is:

=ttest(Group, Tails, Type)

• False.
• True.

GRADED QUIZ: EXPERIMENTAL DESIGN AND TESTING

1. What is a type 2 error?

• When both the null and alternate hypotheses are rejected.
• When the null is falsely accepted.
• When the null hypothesis is falsely rejected.
• When the alternate hypothesis is falsely accepted.

2. Which of the following is not a step in experimental design?

• Present to stakeholders
• Hypothesis
• Select an analysis
• Question

3. Suppose that a car company wants to know if a new fuel additive increases the fuel efficiency of their vehicles. They undertake an AB test to investigate. What is the null hypothesis in this test?

• That the additive decreases fuel efficiency significantly.
• That the fuel additive does not affect the fuel efficiency significantly.
• That the additive is too expensive.
• That the additive increases the fuel efficiency significantly.

4.

Alpha = 0.05

P-value = 0.04

With the information above, what conclusions can you draw?

• There is no significant difference. Reject H0, reject H1.
• There is a significant difference. Reject H0, accept H1.
• There is a significant difference. Accept H0, accept H1.
• There is no significant difference. Accept H0, reject H1.

5. Repeated measures, AB testing, and randomized control trials are all studies of what type?

• Experimental
• Observational
• Statistics
• Bias

6. What is a statistical assumption?

• Something that you know about the data.
• An assumption about the target audience of the analysis.
• Something that must be true for the analysis to be correct.
• An assumption about the outcome of an analysis.

7. What is the alpha for a 90% confidence interval?

• 0.05
• 90%
• 0.10
• 0.90

8. What is confirmation bias?

• When one hypothesis is more reasonable than any others.
• When you confirm a hypothesis that is not true.
• When a study falsely confirms that the sample is representative of the population.
• When an analyst specifically looks for data or other information to prove a hypothesis correct.

9. What is a type 1 error?

• When the null hypothesis is falsely rejected in favor of the alternate hypothesis.
• When the alternate hypothesis is falsely rejected.
• When both the null and the alternate hypothesis are rejected.
• When the null hypothesis is falsely accepted.

10. In experimental design, what is the order of the five steps?

• 1) Hypothesis; 2) Required variables; 3) Question; 4) Select analysis; 5) Measurement
• 1) Question; 2) Hypothesis; 3) Required variables; 4) Select analysis; 5) Measurement
• 1) Question; 2) Hypothesis; 3) Required variables; 4) Measurement; 5) Select analysis
• 1) Question; 2) Required variables; 3) Hypothesis; 4) Select analysis; 5) Measurement

11. Which of these is not a statistical assumption?

• Linearity
• Bias
• Required sample size
• Normality

12. When in doubt, what confidence interval and alpha should you use?

• Confidence Interval: 95%; Alpha: 0.05
• Confidence Interval: 90%; Alpha: 0.10
• Confidence Interval: 99%; Alpha: 0.05
• It doesn’t matter, but alpha should always be 0.05.

13. Which of the following are steps in experimental design?

• I. Measurement
• II. Hypothesis
• III. Communicate
• I. and II.
• II. and III.
• I. and III.
• All of these.

14. A retail store is considering increasing their current discount on a product to see if it will sell more. They decide to perform an AB test. What is the alternate hypothesis?

• That the greater discount leads to significantly more sales of the item.
• That the greater discount leads to no significant change in sales of the item.
• That the item is popular.
• That the item is underpriced.

15. What are five common types of bias?

• Survey, Culture, Confirmation, Observation, and Selection
• Survey, Culture, Confirmation, Observation, and Unfair
• Survey, Culture, Support, Observation, and Selection
• Survey, Recording, Confirmation, Experimental, and Selection

16. A food wholesaler is looking to reduce its costs by shipping to its customers three days a week rather than five. However, the company believes that this may cause it to lose some customers. It decides to use an AB test to test their hypothesis. What is the null hypothesis of this test?

• That shipping five days a week is a bad idea.
• That shipping fewer days does cause a significant loss of customers.
• That shipping three days a week is a bad idea.
• That shipping fewer days does not cause a significant loss of customers.

17. What is observational bias?

• When analysts don’t observe the differences in culture between themselves and the sample.
• That observing people can cause them to act in a manner inconsistent with their true actions.
• When you can’t see what is happening.
• When you select a sample by observing the population incorrectly.

18. What type of error falsely rejects the null hypothesis in favor of the alternate hypothesis?

• Type AB error
• Type 2 error
• Type 1 error
• Analytic error

19. Simple surveys, counting data, and data mining are all studies of what type?

• Bias
• Statistics
• Observational
• Experimental

20. Assuming that the data sample is large enough for the analysis is an example of what kind of statistical assumption?

• Required sample size
• Normality
• Homogeneity of variance
• Linearity

21.

Alpha = 0.05

P-value = 0.08

With the information above, what conclusions can you draw regarding H0 and H1 in a hypothesis test?

• There is a significant difference. Reject H0, accept H1.
• There is no significant difference. Reject H0, reject H1.
• There is no significant difference. Accept H0, reject H1.
• There is a significant difference. Accept H0, accept H1.

22. How do observational studies differ from experimental studies?

• In an observational study, the results of the study are watched in person, while for an experimental study, they are recorded on video.
• In an experimental study, one does not influence the progress of the study. In an observational study, one directly influences the study and watches the effects of this influence.
• They are not different.
• In an observational study, one does not influence the progress of the study. In an experimental study, one directly influences the study and watches the effects.

23. What is the alpha for a 96% confidence interval?

• 96%
• 0.04
• 0.96
• 0.05

24.

Alpha = 0.06

P-value = 0.05

With the information above, what conclusions can you draw?

• There is no significant difference. Accept H0, reject H1.
• There is a significant difference. Accept H0, accept H1.
• There is a significant difference. Reject H0, accept H1.
• There is no significant difference. Reject H0, reject H1.

25. What is the alpha for a 90% confidence interval?

• 0.90
• 0.05
• 0.10
• 90%

26. What kind of study is this?

• Experimental Study
• Observational Study

27. Which of the following is not a part of Experimental Design?

• Run the Study
• Question
• Select an Analysis
• Required Variables

28. Does this mean that your hypothesis was wrong or correct?

• Correct
• Wrong

29. A company is comparing the results of two different ad campaigns. The results of their analysis are as follows:

Alpha = 0.05

P-Value = 0.04

With the information above, what conclusions can you draw?

• There is NO difference. Accept the Null Hypothesis and reject the Alternative Hypothesis.
• There is a significant difference! Reject the Null Hypothesis and accept the Alternative Hypothesis

30. The Confidence Interval is influenced by Variance. True or False?

• True
• False

31. Using the default alpha of 0.05, p-value of 0.04 means…

• There is a significant difference between the two versions.
• There is not a significant difference between the two versions.

32. Is the above survey free of bias?

• No
• Yes

33. You interpret the results of your analysis to mean that there was no difference between the colors of tulips, but that isn’t correct. What type of error is this?

• Type II Error
• Type I Error

34. Which of the following is not a common statistical assumption?

• Linearity
• Heterogeneity of Variance
• Minimum Sample Size
• Normality

Week 4: Data Modeling

PRACTICE QUIZ: STATISTICAL MODELING

1. What is statistical analysis?

• I. Equations used to analyze data.
• II. Field of study based around the use of data.
• III. Processes used to analyze data.
• All three.
• I.
• II.
• III.

2. What is statistical modeling?

• The equations or processes used in analyzing data.
• The field of study based around the use of data.
• The application of a statistical analysis to data.
• It is the result of analyzing data with a model.

3. What is a statistical model?

• The equations used to analyze data.
• The field of study based around the use of data.
• The results from statistical modeling.
• The application of a statistical analysis.

4. True or false: Time series analysis includes a time factor.

• True
• False

5. What are the two versions of machine learning?

• Unsupervised and clustering
• Regression and classification
• Regression and clustering
• Supervised and unsupervised

6. What type of machine learning would be suitable for data that is unlabeled?

• Supervised
• Regression
• Unsupervised
• Categorical

7. Regression and Classification models fall under which type of machine learning?

• Supervised
• Unsupervised

PRACTICE QUIZ: SIMPLE LINEAR REGRESSION

1. In simple linear regression, what does the word “linear” mean?

• That the regression is easy to perform.
• That there is only one independent variable.
• That the independent and dependent variables are not related.
• That a line is used to relate the independent and dependent variables.

2. What does the r2 in a linear regression mean?

• It is the accuracy of the model.
• It is the slope of the line created by the regression.
• It tells you how good the model is.
• It is a measure of how much of the variance is explained by the independent variable.

3. What is the residual?

• It is the set of data values that are close to the regression line.
• It is the set of outliers in the data.
• It is the difference between the recorded data value and the predicted data value.
• It is the collection of data that was not used to construct the model.

4. Which of the following is one of the assumptions in simple linear regression?

• I. Linearity
• II. Randomness
• III. Maximum sample size
• I. (CORRECT)
• II.
• III.
• All of these.

5. Regression and classification models are similar in that they both:

• Predict categorical variables.
• Use dependent variables to predict independent variables.
• Predict numerical variables.
• Use independent variables to predict dependent variables.

6. True or false: Naive Bayes is not a type of classification model.

• False
• True

PRACTICE QUIZ: CLUSTER ANALYSIS

1. What is market segmentation?

• It is the process of creating sub-groups in a customer base using common traits or needs.
• It is the use of statistical models on a target population.
• It is the belief that markets are diverse.
• It is the assumption that sub-groups of the population have the same likelihood of occurring.

2. How is clustering analysis useful to a marketing analyst?

• It homogenizes the sample.
• It determines what marketing strategy to employ.
• It determines if a marketing strategy is effective.
• It facilitates market segmentation.

3. What clustering method is often considered the default method?

• Mean shift.
• K-means.
• Hierarchical.
• Density-based spatial.

4. What is the assumption of homogeneity of variance in K-means clustering?

• That every cluster has the same likelihood of occurring.
• That the clusters are approximately elliptical, or round.
• That the minimum sample size is 50 times the number of clusters.
• That all the variables in the analysis have similar variance.

PRACTICE QUIZ: TIME SERIES

1. What does a time series analysis do?

• It shortens the length of time to complete a statistical analysis.
• It evaluates a qualitative variable to see how it changes in time.
• It evaluates a quantitative variable to see how it changes in time.
• It tracks how the independent variable changes with time.

2. What is the purpose, or most common use, for time series analysis?

• It keeps track of how long an analysis takes to complete.
• It records the past values of the dependent variable.
• To predict, or forecast, future values of the dependent variable.
• It identifies different sub-groups in the data that share similar traits.

3. Which of the following is NOT an assumption in time series analysis?

• I. Dependence
• II. Independence
• III. Minimum sample size
• III.
• I.
• All three.
• II. (CORRECT)

4. True or false: The minimum sample size in time series analysis is 50.

• True
• False

5. True or false: When time is measured in years, the minimum sample size in a time series analysis is 12.

• True
• False

GRADED QUIZ: STATISTICAL MODELING

1. Consider the assumptions in simple linear regression. What is the assumption of normality?

• The data creates a normal distribution.
• All independent variables have similar variance.
• The minimum sample is 20.
• The independent variables do not affect one another.

2. Which one of the following is a modeling technique in clustering analysis?

• I. Logistic regression
• II. Interpolation
• III. Fuzzy C-Means.
• III. (CORRECT)
• II.
• I.
• All of these.

3. In time series analysis, the assumption that the data values all come from the same source is known as:

• dependence.
• minimum sample size.
• constant time.
• stationarity.

4. In time series analysis, you can convert longer units of time into shorter units of time.

• False.
• True.

5. What is a classification model?

• A model that predicts a qualitative variable.
• A model that predicts numerical data.
• A model that predicts the amount of something.
• A model that predicts a quantitative variable.

6. What is the assumption of sphericity for K-means clustering?

• That the dataset can’t be clustered.
• That the entire dataset is elliptical or round.
• That the clusters are approximately elliptical or round.
• That the clusters meet the minimum size.

7. In time series there are three assumptions: minimum sample size, dependence, and:

• stationarity.
• homogeneity.
• independence.
• normality.

8. In time series analysis, what is the assumed minimum sample size if time is measured in months?

• 50 months of information.
• 6 months of information.
• 100 months of information.
• 12 months of information.

9. Which of the following is NOT an assumption in simple linear regression?

• I. Independence
• II. Homogeneity of variance
• III. Sphericity
• All of them are.
• III. (CORRECT)
• I.
• II.

10. Which of the following is a type of quantitative variable?

• Categorical.
• Independent.
• Continuous.
• Dependent.

11. Which one of the following is a modeling technique in clustering analysis?

• I. Simple linear regression
• II. K-means
• III. Logistic regression.
• I.
• II. (CORRECT)
• III.
• All of them.

12. In time series analysis, one of the independent variables must be time.

• False

• True.

13. In time series, what is the assumption of stationarity?

• That the minimum sample size is 50.
• That the mean value of the series is constant.
• That the data values come from the same source.
• That the data follows a normal distribution.

14. In time series analysis, what is the assumed minimum sample size if time is measured in years?

• 5 years of information.
• 1 year of information.
• 50 years of information.
• 25 years of information.

15. Which of the following is an assumption in simple linear regression?

• I. Independence
• II. Sphericity
• III. Dependence
• I. (CORRECT)
• II.
• III.
• All of them are.

16. Which one of the following is NOT a modeling technique in clustering analysis?

• I. Fuzzy C-Means
• II. K-Means
• III. General linear models
• All of these.
• III. (CORRECT)
• I.
• II.

17. In time series analysis, two of the three assumptions are minimum sample size and stationarity. What is the third?

• Dependence.
• Normality.
• Homogeneity.
• Constant time.

18. What is a regression model?

• A model that uses numbers as labels.
  • A model that predicts categorical data.
  • A model that predicts a qualitative variable.

• A model that predicts a quantitative variable.

19. Continuous and discrete are the two types of what kind of variable?

• Independent.
• Quantitative.
• Qualitative.
• Categorical.

20. Consider the assumptions in simple linear regression. What is the assumption of homogeneity of variance?

• Some independent variables have no variance.
• All independent variables have similar variance.
• The data creates a normal distribution.
• The independent variables do not affect one another.

21. In time series analysis, what does the assumption of dependence mean?

• That time must be one of the independent variables.
• That the dependent variable does not change over time.
• That all the observations come from the same place.
• That the dependent variable depends on the independent variable.

22. In time series analysis, what is the assumption that the mean value of the series is constant called?

• Minimum sample size.
• Constant time.
• Dependence.
• Stationarity

23. Which of the following is an assumption in simple linear regression?

• I. Linearity
• II. Variability
• III. Dependence
• All of them are.
• III.
• II.
• I. (CORRECT)

24. Consider the assumptions in simple linear regression. What is the assumption of minimum sample size?

• The minimum sample is 10.
• The minimum sample is 20.
• The minimum sample is 50.
• The minimum sample is 100.

25. What is the assumption of minimum sample size for K-means clustering?

• 50 times the number of clusters.
• 10 times the number of clusters.
• 100 times the number of clusters.
• 20 times the number of clusters.

26. In time series analysis, what is the assumed minimum sample size if time is measured in quarters?

• 4 quarters of information.
• 50 quarters of information.
• 40 quarters of information.
• 100 quarters of information.

27. Quantitative variables consist of two types. What are they?

• Known and unknown.
• Continuous and discrete.
• Continuous and smooth.
• Countable and discrete.

28. In time series analysis, you can convert shorter time units into longer time units.

• False
• True.

29. What is the assumption equal prior probability for K-means clustering?

• That each cluster has the same probability of happening.
• That one of the clusters is more likely to occur than the others.
• That each data value has the same probability of occurring.
• That each cluster has the same number of data points.

30. What is the difference between a classification model and a regression model?

• A classification model predicts a qualitative variable, while a regression model predicts a quantitative variable.
• A classification model is used with qualitative data, while a regression model works with categorical data.
• A classification model is used with numerical data, while a regression model works with qualitative variables.
• A classification model predicts a quantitative variable, while a regression model predicts a qualitative variable.

31. A Classification Model is…

• A statistical model created using a classification analysis
• The results of a regression analysis.
• A type of analysis.
• The process of applying a classification analysis.

32. Data modeling is useful in marketing analytics because…

• You can predict the number of clicks you will get from an advertising campaign based on how much you spent on it.
• You can predict how much you will sell next year.
• You can segment your market to better understand the needs of specific parts of your customer base.
• These are all correct.

33. Which of the following is NOT a model?

• Cluster
• Progression
• Classification
• Regression

34. You can convert a time variable that is recorded in weeks to days. True or False?

• True
• False

35. Independent Variable: Quantitative

Dependent Variable: Quantitative

Purpose: Predict the Dependent Variable using the Independent Variable

Which model is most appropriate for the conditions listed above?

• Cluster Analysis
• Classification Analysis
• Time Series Analysis
• Simple Linear Regression

36. If the Calla and Ivy ad received 5,000 impressions, how many times will it be clicked? What type of model will best answer this question?

• Simple Linear Regression
• Time Series
• Cluster
• Classification

37. How many sales can Carlos from Inu + Neko expect to receive from emailed ads next year? What type of model will best answer this question?

• Cluster
• Time Series
• Classification
• Simple Linear Regression

38. What type of model will help Paola forecast customer spending based on how long they have been customers?

• Classification
• Cluster
• Time Series
• Simple Linear Regression

Course 6: Data Analytics Methods for Marketing

Week 1: Find Your Audience with Segmentation

PRACTICE QUIZ: SEGMENTATION IN MARKETING

1. Segmentation is…

• A way to sort people in groups based on characteristics they have in common

• A way to sort people based on unstructured data
• A way to sort people based on what they buy

2. True or false, segmentation from data analysis is one of the two forms of segmentation.

• True

• False

3. True or false, psychographic segmentation is the most powerful form of segmentation.

• True

• False

4. Which of the following are forms of behavioral segmentation… (Select all that apply)

• Location
  • Values

• Product usage

• Spending habits

5. A contextual targeting vendor understanding the difference between the Miami Dolphins football team and dolphins in the ocean is an example of…

• Semantic understanding

• One to one personalization
• Wisdom of the Crowd
• Segmentation and targeting

PRACTICE QUIZ: CLUSTER ANALYSIS

1. What is“K” defined as in K-means clustering?

• The distance between two centroids
  • The variance of the clusters
  • The Euclidean distance between two points

• The number of clusters

2. What is the Euclidean distance between these two points?

Meta Marketing Analytics Course 4 Week 1 (Chart 1)

• 3.91

• 3.16

• 0.25
• 2.93

3. What is the variance for the following data set: 2,4,5,6,8

• 5
  • 8

• 4

• 6

4. What does the Dunn Index measure?

• The distance between two points

• Both the tightness of clusters and how far apart clusters are

• How far apart clusters are
• How tight clusters are

5. When calculating variance for your clusters in k-means clustering, you are looking for the ______ total variance across clusters

• Highest

• Lowest

GRADED QUIZ: SEGMENTATION

1. Which of the following are NOT types of Segmentation? (Choose two)

• Segmentation developed from a persona
  • Segmentation developed from data analysis

• Segmentation developed from media

• Segmentation developed from product-customer fit

2. Which of the following are kinds of personalization? (Select all that apply)

• Two to one personalization

• Personalization based on segmentation and targeting

• Personalization based on semantic understanding

• Personalization based on wisdom of the crowd

3. A CDP is a database that builds a complete picture of your customers on an individual level. True or False?

• False

• True

4. What is the first step in creating a K-means clustering analysis?

• Establish baseline clusters
  • Calculate the Euclidean distance between each point and each centroid

• Define K

• Establish K number of centroids at random

5. The Elbow Criterion finds the number of clusters for which adding an extra cluster would not add sufficient information. True or False?

• False

• True

6. Profiling Clusters does NOT do which of the following?

• Describe what makes people in a cluster similar to each other.
  • Describe what makes people from different clusters different.
  • Describe what makes people in a cluster similar to each other and what makes people from different clusters different.

• None of these answers.

7. Segmentation helps you find the correct audience and reach them with the right message. True or False?

• True

• False

8. The four segmentation variables commonly used in marketing are…

• Psychographic, infographic, demographic, and behavioral
  • Psychographic, infographic, geographic, and media consumption
  • Psychographic, media consumption, behavioral, and geographic

• Psychographic, demographic, behavioral, and geographic

9. Values, Motivations, and Beliefs are examples of what kind of segmentation variable?

• Infographic

• Psychographic

• Geographic
• Behavioral

10. What does clustering do?

• Groups similar data points together
  • Puts dissimilar things in different groups
  • Segments your data

• All of these are true

11. Which of the following is NOT a kind of personalization?

• Personalization based on systematic understanding

• Personalization based on wisdom of the crowd
• One to one personalization
• Personalization based on segmentation and targeting

12. What is a CDP?

• A database that builds a complete picture of your customers on a regional level
  • A database that builds a complete picture of your customers as a whole
  • A database that builds a complete picture of your customers on a national level

• A database that builds a complete picture of your customers on an individual level

13. The Elbow Criterion is used for…

• identifying points of change in trend analysis
  • determining the number of iterations you should use while creating clusters

• determining the number of clusters to use for an analysis

14. What do you focus on when profiling clusters?

• Describing what makes people in a cluster similar to each other
  • Describing what makes people from different clusters different

• Describing what makes people in a cluster similar to each other and what makes people from different clusters different

• None of these answers

15. Location, Population Density, and Climate are examples of what kind of segmentation variable?

• Psychographic

• Geographic

• Behavioral
• Infographic

16. What kind of analysis is best for segmentation?

• Time Series

• Clustering

• Classification
• Linear Regression

17. What does CDP stand for?

• Customer Data Platform

• Client Data Point

• Common Data Position
• Consumer Data Pool

18. Psychographic, demographic, behavioral, and geographic are the four commonly used segmentation variables in marketing. True or False?

• True

• False

19. Product Usage, Spending Habits, and Media Consumption are examples of what kind of segmentation variable?

• Psychographic
  • Infographic

• Behavioral

• Geographic

20. Cluster Analysis is the most common analytical approach used for segmentation. True or False?

True

False

21. The two forms of segmentation are developed from a persona and developed from data analysis.  True or False

• True

• False

22. The first step in creating a K-means clustering analysis is to Validate the data. True or False?

• True

• False

23. True or False: One to Two is a kind of personalization.

• True

• False

24. What is the last step in creating a K-means clustering analysis?

• Validate the data

• Establish baseline clusters
• Establish K number of centroids at random
• Calculate the Euclidean distance between each point and each centroid

25. Segmentation is important because…

• It helps the audience know us better
  • It helps the audience understand us as individuals

• It helps us know our audience better

• It helps us know specific information about individual customers

26. What are the two forms of Segmentation? (Choose two)

• Segmentation developed from media
  • Segmentation developed from product-customer fit

• Segmentation developed from a persona

• Segmentation developed from data analysis

27. Segmentation does not…

• Help us understand our audience
  • Helps us set up campaigns in our audience buying platforms.

• Help us target the whole world

• Help us reach the right users with our media

29. Which of the following is a segmentation variable commonly used in marketing?

• Infographic
  • Photographic
  • Media Consumption

• Demographic

30. Profiling Clusters means only describing what makes people within a cluster similar to each other. True or False?

• True

• False

31. Which principle can you use to decide on the number of clusters for your analysis?

• Iterate on the number of clusters

• The elbow criterion

• Choose as many clusters as you can.

32. The two forms of segmentation are… (Choose two)

• Segmentation developed from the media
  • Segmentation developed from research

• Segmentation developed from data analysis

• Segmentation developed from a persona

33. The four segmentation variables are…

• Psychographic, media consumption, behavioral, and geographic
  • Psychographic, infographic, demographic, and behavioral

• Psychographic, demographic, behavioral, and geographic

• Psychographic, infographic, geographic, and media consumption

34. Which of the following is NOT a form of personalization?

• Semantic understanding
  • One to one personalization

• Qualitative understanding

• Wisdom of the crowd

35. What is the purpose of clustering?

• Finding trends over time in purchase data

• Finding similarities in the data, and grouping data points by these similarities.

• Finding the median of a data set in order to create clusters.
• Finding the average of data sets in order to create cohorts.

36. What is step 3 of the k-means clustering process, after establishing K number of centroids?

• Calculate the Dunn Index for clusters
  • Find the mean of each new cluster to establish a new centroid

• Calculate the Euclidean distance between each point and each centroid

• Calculate the variance for each cluster

37. Which principle can you use to decide on the number of clusters for your analysis?

• Choose as many clusters as you can

• The elbow criterion

• Iterate on the number of clusters

Week 2: Analytics for Planning and Forecasting

PRACTICE QUIZ: DESCRIPTIVE METHODS

1. You can have multiple secondary KPIs. True or False?

• False
• True

2. “How has inventory moved in the last 12 months?” is a question that would use _____ analytics to find the answer.

• Prescriptive
• Predictive
• Descriptive

3. What is the ROAS for the campaign displayed here?

Product Sold$2,000Advertising Cost$1,000

ROAS for Campaign Display

• 200%
• $3000
• 100%
• $100

4. What are the two key differences between ROI and ROAS?

• ROI is generally used in advertising, while ROAS is generally used in finance
• ROI only uses direct advertising spend, whereas ROAS uses all costs
• ROAS uses revenue, not profit
• ROAS only uses direct advertising spend, whereas ROI uses all costs

5. Which of the following could be examples of customer profitability segmentation strategies? (Choose all that apply)

• CPM analysis
• Persona-based segmentation
• RFM analysis
• B2B vs. B2C segmentation

PRACTICE QUIZ: CUSTOMER LIFETIME VALUE

1. What is the acronym for customer lifetime value?

• CLV
• CTV
• CLTV
• CULV

2. COGS stands for…

• Cost of goods sent
• Core of goods sold
• Cost of goods sold
• Cost of goal sold

3. If the average customer retention period is 2 years with an average of 7 transactions over that time period and the gross profit margin is 30%, what is the overall CLTV of the following data set?

CustomerSalesNumber of transactionsCustomer 1$2002Customer 2$3004Customer 3$2503

• $150
• $300
• $250
• $350

4. If the average customer retention period is 2 years with an average of 7 transactions over that time period and the gross profit margin is 30%, what is the CLTV of Customer 2?

CustomerSalesNumber of transactionsCustomer 1$2002Customer 2$3004Customer 3$2503

• $315
• $350
• $300
• $250

5. If your revenue is $3,000 and your COGS is $1,800, what is your gross profit margin?

• 30%
• 50%
• 40%
• 60%

GRADED QUIZ: PLANNING AND FORECASTING

1. If the average customer retention period is 2 years with an average of 7 transactions over that time period and the gross profit margin is 30%, what is the CLTV of Customer 1?

CustomerSalesNumber of transactionsCustomer 1$2002Customer 2$3004Customer 3$2503

• $300
• $250
• $150
• $420

2. If your revenue is $4,000 and your COGS is $1,000, what is your gross profit margin?

• 50%
• 75%
• 60%
• 25%

3. Questions that can be answered using linear regression include: (select all that apply)

• Does customer satisfaction impact sales?
• Which of these website designs will increase sales?
• What are the main groups of customers in my customer base?
• Do increased email open rates lead to increased sales?

4. Univariate is a type of linear regression. True or False?

• False
• True

5. You can only have one secondary KPI. True or False?

• False
• True

6. The ROAS for the following numbers is 50%. True or False?

Product Sold$2,000Advertising Costs$1,000

• False
• True

7. COGS stands for Cost of Goods Sold. True or False

• True
• False

8. Does customer satisfaction impact sales? Is a question that can be answered using linear regression. True or False?

• False
• True

9. Which of the following are not types of regression? (Select all that apply)

• Logistic
• Linear
• Multinomial
• Legitimate

10. CLTV stands for Customer Lifetime Value. True or False

• False
• True

11. The acronym for customer lifetime value is CLV. True or False?

• False
• True

12. The acronym for Cost of Goods Sold is…

• CGS
• COG
• CG
• COGS

13. The ROAS for the following numbers is 200%. True or False?

Products Sold$2,000Advertising Costs$1,000

• True
• False

14. ROAS use Revenue, ROI use Profits. True or False?

• False
• True

15. If your revenue is $2,000 and your COGS is $1,500, what is your gross profit margin?

• 60%
• 25%
• 50%
• 75%

16. If the average customer retention period is 2 years with an average of 7 transactions over that time period and the gross profit margin is 30%, what is the CLTV of Customer 3?

CustomerSalesNumber of transactionsCustomer 1$2002Customer 2$3004Customer 3$2503

• $350
• $300
• $250
• $315

17. Questions that cannot be answered using linear regression include: (select all that apply)

• Do increased email open rates lead to increased sales?

• Does customer satisfaction impact sales?

• Which of these website designs will increase sales?
• What are the main groups of customers in my customer base?

18. “How many clicks did the ad get this week?” is a question that would use _____ analytics to find the answer.

• Descriptive
• Prescriptive
• Predictive

19. “How much inventory will be moved in the next 12 months?” is a question that would use _____ analytics to find the answer.

• Descriptive
• Predictive
• Prescriptive

20. If I’m trying to answer the question “How many gadgets should I order to sell next Christmas?” I would use…

• Predictive analytics
• Descriptive analytics
• Probable analytics
• Deductive analytics

21.

Product Sold$1,000Advertising Costs$500

What is the ROAS of this campaign?

• $500
• $200
• 500%
• 200%

22. When doing an RFM analysis, your segments are as follows:

• Recency: (5) last 24 hours, (4) last week (3) last month (2) last year (1) more than a year
• Frequency: (5) 10+ (4) 7-9 (3) 4-6 (2) 2-3 (1) 1
• Monetary: (5) $500+ (4) $300-$499 (3) $200-$399 (2) $100-$299 (1) <$100
• Given the table below, with recency in days, what is the RFM score for customer 2?

Customer IDRecencyFrequencyMonetary1324812945303126435

• 335
• 334
• 414
• 424

23. How many primary KPIs should you have per objective?

• 1
• 2
• 3
• Unlimited

24. A customer lifetime value analysis helps us… (Check all that apply)

• Analyze shifts in the marketplace
• Increase ROI
• Segment our customers
• Focus on acquiring profitable customers

25. The formula for CLTV is:

• Average value of a sale x ________ x customer retention period x profit margin
• Average number of transaction
• Customer NPS
• Average spend
• Linear profit margin

26. Given the inputs below, what is the customer lifetime value?

• 2019: 35 customers
• 2020: 31 customers
• Total sales 2020: $713
• Number of transactions 2020: 68
• COGS 2020: $398

• $18.83
• $23.00
• $14.21
• $16.62

27. What is the goal of a linear regression analysis?

• To determine customer profit
• To compare 3 or more variables
• To learn if one variable correlates with another
• To determine lifetime value

Week 3: Evaluating Advertising Effectiveness

PRACTICE QUIZ: AD EFFECTIVENESS MEASUREMENT

1. SMART Goals are:

• Systematic Marketing and Realty Time-Lines
• Specific Measurable Achievable Realistic Time Bound
• Small Manageable Accurate Real Terrific
• Simple Meaningful Accurate Relevant Targeted

2. KPIs can help because they are specific metrics that can be used to measure progress. True or False?

• False
• True

3. The two methods you can use to evaluate ad effectiveness are:

• Observational methods and KPI evaluation
• SMART Goal setting and Experimental methods
• KPI evaluation and SMART Goal setting
• Experimental and Observational Methods

4. If you are running an ad with a “click to subscribe” button, can you measure the effectiveness of the ad ONLY by counting the number of customers who subscribed by clicking the button?

• Yes
• No

PRACTICE QUIZ: MEASURING AD EFFECTIVENESS WITH EXPERIMENTS

1. Results of an experiment include: (select all that apply)

• A winner
• Report output
• Measure of confidence in the results
• Number of incremental results caused by your treatment

2. What could the effect be of using ITT (Intention to Treat) on the incremental impact of your campaign results?

• The incremental impact you observe may be lower
• Result remains the same

3. Randomization is the process of assigning people to groups based on a common trait that is selected at random. True or False?

• True
• False

4. In an experiment, the group that did not receive a treatment is called what?

• Null group
• Treatment group
• Control group
• Other

5. A hypothesis is a proposed explanation for an observation. True or False?

• False
• True

GRADED QUIZ: EVALUATING ADVERTISING EFFECTIVENESS

1. SMART Goals are Not: (select all that apply)

• Time Bound
• Measurable
• Ambiguous
• Relatable

2. KPIs are… (select all that apply)

• Useful only at the corporate level
• Measurable
• Helpful in evaluating advertising effectiveness
• Specific Metrics

3. Which of the following methods can be used for evaluating ad effectiveness? (Select all that apply)

• SMART Goal setting
• KPI evaluation
• Experimental methods
• Observational methods

4. SMART Goals are: (select all that apply)

• Relatable
• Specific
• Time Bound
• Measurable

5. KPIs have no practical use. True or False?

• False
• True

6. If you are running an ad with a “click to subscribe” button, and you measure the effectiveness of the ad ONLY by counting the number of customers who subscribed by clicking the button, you would be overestimating the results. True or False?

• False
• True

7. Results of an experiment do NOT ALWAYS include: (Select all that apply)

• Number of incremental results caused by your treatment
• Measure of confidence in the results
• Report output
• A winner

8. Using ITT (Intention to Treat) in an experiment to measure the incremental impact of your campaign would not change the results. True or False?

• True
• False

9. What does RCT stand for?

• Randomized Controlled Trials
• Randomized Controlled Tests
• Randomized Cautious Tests
• Really Controlled Trials

10. In an experiment, the group that did receive a treatment is called what?

• Null group
• Control group
• Treatment group
• Other

11. AB Testing does not use a control group. True or False?

• True
• False

12. Multi-Cell, Nested Cell, and Structure Cell are all types of test structures. True or False?

• True
• False

13. SMART Goals are:

• Specific, Measurable, Achievable, Realistic, Time Bound
• Systematic, Marketing And Realty, Time-Lines
• Simple, Meaningful, Accurate, Relevant, Targeted
• Small, Manageable, Accurate, Real, Terrific

14. What are two methods for evaluating ad effectiveness?

• SMART Goal setting and Experimental methods
• Observational methods and KPI setting
• KPI evaluation and SMART Goal setting
• Experimental and Observational Methods

15. If you are running an ad with a “click to subscribe” button, and you measure the effectiveness of the ad ONLY by counting the number of customers who subscribed by clicking the button, what would you expect the results to be?

• There is not enough information to tell
• Overestimated
• Correct
• Underestimated

16. The effect of using ITT (Intention to Treat) on the incremental impact of your campaign results in the incremental impact you observe being lower. True or False?

• True
• False

17. AB Testing is not a good test to evaluate the effectiveness of your campaign, because…

• It has no p-value
• It cannot track data over time
• AB Testing IS a good way to evaluate the effectiveness of your campaign.
• There is no control group.

18. Which of the following are NOT types of test structures?

• Multi-Cell
• Nested Cell
• Structured Cell
• Single Cell

19. AB Testing is a good test to evaluate the effectiveness of your campaign. True or False?

• False
• True

20. What do results of an experiment include? (Select all that apply)

• Report output
• A winner
• Measure of confidence in the results
• Number of incremental results caused by your treatment

21. Randomization does not impact the results of a trial. True or False?

• True
• False

22. In an experiment, the group that did not receive a treatment is called what?

• Control group
• Treatment group
• Other
• Null group

23. Results of an experiment include the number of incremental results caused by your treatment and the measure of confidence in the results. True or False?

• False
• True

24. Experimental and Observational methods can both be used for evaluating ad effectiveness. True or False?

• True
• False

25. Which of the following are types of test structures? (Select all that apply)

• Structured Cell
• Single Cell
• Multi-Cell
• Nested Cell

26. You are running an ad with a ‘click to purchase’ button. Can you measure the effectiveness of the ad by counting the number of purchases that came from people clicking on the ad?

• No, that would underestimate the effectiveness of the ad
• Yes, that would measure how many purchases the ad was responsible for.

27. Why are experimental methods better to measure advertising effectiveness than observational methods?

• In experimental methods you have more control over how similar the different groups are that will be compared to evaluate resultsYou need less budget for experimental methods.
• Both methods don’t really differ.

28. What could the effect be of using ITT (Intention to Treat) on the incremental impact of your campaign results?

• Result remains the same
• The incremental impact you observe may be lower.

29. There are two parts to experiment results, the number of incremental results from your treatment and what else?

• A winner
• A measure of confidence in the results
• A report output

Week 4: Optimizing Your Marketing Mix

PRACTICE QUIZ: MARKETING MIX MODELING

1. Your manager is asking you to put a report together that shows how much incremental sales was generated by the TV campaign you ran last quarter and she also wants to know how that compares to the money that you invested in ads on Facebook during that same time. Which would be the best metric to highlight in your report:

• Cost per Acquisition

• Return on Investment (ROI)

• Customer Lifetime Value

2. Which of the following are typical outputs of a MMM?

An overview of which of my TV ad creatives worked best in the past year.

• Marginal return associated with each marketing channel.

• An overview of how my spending in different marketing channels contributed to success.

• A report that provides detail on how much influence each of your marketing activities had on sales.

3. For which of the following questions could a marketer use a Marketing Mix Model to get the answer:

• Which ad creative performed best in my holiday ad campaign on Facebook?

• What was the ROI of my fall TV campaign I ran last year?

• What would the influence be on sales if I doubled the budget I spend on Instagram Stories next year?

• What would happen to sales if we increase the price of our product?

4. Marketing Mix Modeling is an interaction between a team of modelers and an econometric model. What is the role of the team of modelers?

• Come up with a set of variables that may affect sales and iterate on these variables until a robust model is achieved for the particular company in question and the KPI they are trying to model

• Acquire data for a set number of variables that they know always influence sales in a similar way
• Advise marketers on how to effectively create ads to build successful campaigns

5. Imagine you are working in the marketing department of a restaurant chain and your manager asks you to provide management with a monthly report that provides an update on the effect of each of the media channels used by your company on sales volume. What would be your best response?

• I can provide you with an estimate of the ROI for every media channel based on our monthly spending. And, every 6 months, I will include an update on the actual effect the different channels had on our sales.

• Of course, I will re-run our MMM monthly so we can include the results in the report.

PRACTICE QUIZ: ATTRIBUTION

1. Which of the following business questions can you answer with an Attribution study? (Choose all that apply)

• Which of my creative executions in my video campaign works best to make people buy my product, the video filmed outside or the video filmed in a studio?

• What media channel should I invest more money in next year?

• Which of my advertising campaigns last year drove most of my sales?

• How much of my revenue was influenced by the Instagram campaign I ran in Q4?

2. Which rule-based attribution model is best described by the following definition?

Gives 100% credit to the last click seen from a person before a conversion took place, even if an impression (ad view) was the last interaction.

• Time Decay
  • First Touch

• Last Click

• Last Touch

3. Which rule-based attribution model is best described by the following definition?

Gives more credit to touchpoints (clicks or impressions) based on how recently they happened. This attribution model gives an increasing percentage of the credit for a conversion to touchpoints as they get closer in time to the conversion.

• Time Decay

• Positional
• First Click
• Even Credit

4. Which rule-based attribution model is best described by the following definition?

Gives 100% credit for a conversion that happened to the first click or visit that happened in the conversion path. If there is no click or visit, then it will credit the conversion to the first impression.

• Last Touch
  • First Click

• First Touch

• Positional

5. Which rule-based attribution model is best described by the following definition?

First and last touchpoints (clicks or impressions) are given more credit, while the credit for the remaining touchpoints in the middle is divided equally.

• First Touch
  • Even Credit

• Positional

• Time Decay

PRACTICE QUIZ: SALES FUNNEL ANALYSIS

1. What is this funnel shape called?

• Classic Funnel Image

• A classic funnel

• A blocker funnel
• A reverse funnel
• A footed funnel

2. If you see the shape below and you’re in B2C marketing, what is the most likely thing you want to investigate?

• Check Out Flow Image
  • Your website
  • Your pricing strategy

• Your check out flow

• Your attribution model

3. What is one question you’ll want to ask yourself at the interest and consideration stages of the sales funnel?

• What page are people entering our website on?
  • What is the repurchase rate for returning users?

• What are people searching for on my site? Is it a specific item or category?

• How long are people spending on their first page?

4. “Where do users drop off in the purchase process?” is a question you’d ask yourself in the _____ stage of the sales funnel.

• Awareness
  • Consideration
  • Interest

• Conversion

GRADED QUIZ: OPTIMIZATION

1. True or false? You would run a marketing mix modeling study to show how your advertising on different platforms contributed to company sales.

• True

• False

2. A marketing mix model can help you better allocate your marketing budget by knowing what works and what doesn’t. True or False?

• True

• False

3. Which of the following is correct about a last click attribution model?

• It evenly spreads the credit for a conversion across all the ads a consumer clicked on before finally converting
  • It gives credit to the ads in the conversion path based on a statistical attribution model
  • It gives all the credit to the last ad a user saw or clicked on before converting

• It gives all the credit for a conversion to the last ad a user clicked on before converting

4. Attribution is the process of assigning credit to touch points along a customers conversion path. True or False?

• False

• True

5. True or false? Statistical attribution models are not as robust as rule based attribution models and less accurately reflect reality.

• False

• True

6. Marketing Mix Modeling helps with in-channel optimization. True or False?

• True

• False

7. What is the last step of the Marketing Mix Modeling methodology?

• Modeling

• Identify the variables affecting your outcome

• Data Collection
• Align variable types

8. Which of the following statements is true about connecting touchpoints to one individual person? (Select all that apply)

• Once a cookie is set in a user’s browser, it will be there forever and you can use that to monitor all the person’s actions on your site.

• Facebook Pixel, the SDK and the conversions API allow you to tie actions directly to real people due to Facebook’s ability to track persistent login and a unique identifier associated with a person’s Facebook account.

• Historically, advertisers have relied on cookies to connect a sequence of touchpoints to a person.

• It’s challenging for advertisers to connect the data from a person’s interactions with ads on mobile devices with that same person’s interactions on computers.

9. Awareness, Interest, Conversion, and Retention are the four stages of a sales funnel. True or False?

• True

• False

10. When you encounter a block in your funnel, which of the following approaches should you use to try to fix it?

• Spend more on ads

• Check out the flow

• Change the product being sold
• Blame the customer

11. Which of the following is correct about a time decay attribution model?

• It gives all the credit for a conversion to the last ad a user clicked on before converting.
  • It evenly spreads the credit for a conversion across all the ads a consumer clicked on before finally converting.

• It gives credit to touchpoints (clicks or impressions) based on how recently they happened.

• It gives all the credit to the last ad a user saw or clicked on before converting.

12. True or false? Attribution is mostly used to evaluate the impact of online media channels on a purchase.

• True

• False

13. Why may advertisers want to use attribution modeling studies?

• Attribution modeling can help advertisers understand the effect of their ads on ad recall

• Attribution modeling can help advertisers understand how much influence their ads on different platforms had on their result

• Attribution modeling helps advertisers evaluate the incremental lift in sales caused by each of their ads.
• Attribution studies help to test different variables of an ad and understand which variables work best and drive the best results

14. Which of the following is not true about Marketing Mix Modeling? (select all that apply)

• Need high quality data
  • Great for big picture

• Helps with in-channel optimization

• Great for granularity

15. Which of the following are part of the Marketing Mix Modeling methodology? (select all that apply)

• Align variable types

• Data Collection

• Identify the variables affecting your outcome

• Modeling

16. Which of the following describes some of the most common challenges we face when measuring the effect of advertising across different marketing platforms?

• It’s not always easy to connect data from different platforms and devices. Also, connecting all the advertising touchpoints to one individual user can be challenging

• It is often challenging to create a test with enough power or a high enough confidence interval
• It is hard to connect data from people who log in to Facebook on both their mobile device and on the web
• It can be challenging to randomly assign people to a control or an experimental group

17. When troubleshooting a block in a sales funnel, it is important to check out the flow. True or False?

• False

• True

18. A marketing mix model can only help you understand the impact of organic engagement on your sales. True or False?

• True

• False

19. Attribution has nothing to do with ROI. True or False?

• True

• False

20. True or false? In statistical or math attribution models you let the data speak and you don’t decide on a model ahead of time.

• True

• False

21. True or false? Historically, advertisers have relied on cookies to connect a sequence of touchpoints to a person.

• True

• False

22. Which of the following are stages of a sales funnel? (select all that apply)

• Exploration

• Conversion

• Retention

• Awareness

23. Imagine you work in the marketing department of a large clothing retailer. You want to run a marketing mix modeling study.

Which of the following statements regarding the benefits of conducting this study are true? (Select all that apply)

• Is solely used to determine on which platform your advertisement performed best

• It can help plan how to best spend your money next year to improve results

• It can help you analyze last year’s data to understand which marketing activities contributed most to your results

• It can help you predict what will work in the future for your company

24. What are the four stages of most sales funnels?

• Awareness, Interest, Conversion, Retention

• Curiosity, Interest, Conversion, Retention
• Awareness, Curiosity, Exploration, Conversion
• Awareness, Interest, Exploration, Conversion

25. Before you recommend Marketing Mix Modeling, what should you consider? (select all that apply)

• Helps with in-channel optimization
  • Great for granularity

• Great for big picture

• Need high quality data

26. Imagine you work in the marketing department of a large clothing retailer. You are working on a ‘year in review’ presentation and you would like to show how your advertising on different platforms (TV, radio, Facebook and YouTube) contributed to sales for the denim line you introduced this year.

You reach out to a market research agency to help you with this. What type of study should they do for you?

• They should run a Brand Survey Test
  • They should run an A/B test

• They should run a marketing mix modeling study

• They should conduct a Holdout Test

27. Which of the following are part of the troubleshooting process for a blocked funnel? (Select all that apply)

• Change the product being sold

• Check for missing information

• Check out the flow

• Evaluate the selling process

28. What is the first step of the Marketing Mix Modeling methodology?

• Data Collection
  • Predict your KPI
  • Modeling

• Identify the variables affecting your outcome

29. A marketing mix model can help you… (Choose all that apply.)

• Understand the impact of organic engagement alone on your sales.
  • Understand the impact of Facebook ads alone on your sales.

• Help you better allocate your marketing budget by knowing what works and what doesn’t.

• Better understand the impact of your marketing efforts.

30. Which of the following is correct about a positional model?

• It gives credit to the ads in the conversion path based on a statistical attribution model

• It gives more credit to first and last touch points whether they are clicks or impressions, while the credit for the remaining touchpoints in the middle is divided equally.

• It gives all the credit to the last ad a user saw or clicked on before converting.
• It evenly spreads the credit for a conversion across all the ads a consumer clicked on before finally converting.

DATA ANALYTICS METHODS FOR MARKETING FINAL QUIZ

1. For this final project, we are going to follow James at Snackwall. James launched Snackwall a year ago, and so far, it’s been a real success. Now, James is eager to expand his audience and he is preparing to give his manager an overview of the past year’s success and ask for an advertising budget to help him grow the business.

James knows that going to his boss with a solid plan will help to convince him to allocate marketing budget to the expansion of Snackwall.

As a starting point, James identifies the segments that he should focus on for his advertising campaign. After all, James knows that it would not be a good use of his money to market to everyone. James relies on K-means clustering, using last year’s data on business size and amount spent for Snackwall clients. James worked with Alya, his analyst, and together they ran several iterations of their K-means clustering. Now they are using the chart below to determine the number of clusters James should focus on in his campaign.

Meta Marketing Analytics Chart 1 – Snackwall

How many segments do you suggest James defines for his marketing campaign based on this plot?

• 2 Clusters

• 3 Clusters

• 1 Cluster
• 4 Clusters

2. Based on the K-means clustering, James found 3 clusters that seem to define his current client base. Since James used the dollar amount spent and the business size as the starting variables for his cluster analysis, he knows that the segments are quite distinct in terms of these variables.

Meta Marketing Analytics – K-means clustering

How would you define Cluster 1?

• None of these are true
  • Small businesses that spend a medium amount.

• Medium businesses that spend little.

• Large businesses that spend a little.

3. James decides that he should focus on the third cluster for his marketing campaign. He believes this segment has more potential, because he has seen from his previous campaign that it is a little harder to convince large businesses to subscribe. After the profiling exercise, he decides to call the segment the ‘Health conscious startups’ to help other people understand and remember this segment.

Next, James turns to showing his management that the advertising budget he was given last year was money well spent. So, James calculates the Return on Ad Spend for last year, and he looks at ROAS by cluster.

He shows the following results based on the total ad spend last year of $200K. The total revenue generated was $800K. The total cost invested last year was $500K, so the profit for the year for Snackwall was $300K.

• The ROAS for Snackwall last year was: 400%.

• The ROAS for Snackwall last year was: 150%.
• The ROAS for Snackwall last year was: $800K.
• The ROAS for Snackwall last year was: $200K.

4. James understands that his management will also want to know the ROI for the advertising campaign he ran last year. The equation to calculate ROI is ROI = (net spend / net profit) * 100. True or False?

• False

• True

5. James is hoping to get a substantial advertising budget for next year. To achieve that, he knows that it would help to show the CLTV for his clients. That may help convince management that their investment now will really pay off in the future. But, since James only launched Snackwall a year ago, it is going to be difficult to show CLTV. The problem is the value of the Customer Retention Period. True or False?

• False

• True

6. James decides to estimate the retention period for his clients. He believes that he can keep a client for 3.5 years, which is similar to the retention period for the cleaning subscription side of his business. With this in mind, what is the CLTV for Snackwall if the following is true:

Average order value = $1800

Average number of orders per year = 9

Profit Margin = 63%

• $3,717,000

• $35,721

• $258.125
• $10,629

7. Finally, for his budget presentation, James showed the following chart from a linear regression analysis he ran, evaluating the influence of advertising spending on sales, based on last year’s experience. What does this chart help James prove?

Meta Marketing Analytics – Linear Regression Analysis

• There is a positive correlation between advertising spending and sales, and R2 suggests that we can be confident that our data fit this result.

• There is a positive correlation between advertising spending and sales in 93.5% of the cases
• There is a negative correlation between advertising spending and sales.
• Sales and advertising spending are 93.5% correlated.

8. James’ management is happy with the progress he made last year, and his presentation was a success. He is given a large advertising budget for the next year, in fact, his budget will now be $250K. James’ manager told him that he trusts he will use the budget well, but that he wants to see that the advertising campaigns James runs are resulting in additional subscriptions.

James should plan to run an attribution study. True or False?

• False

• True

9. Before spending any of his budget, James wants to compare the results from all of his different marketing channels over the past year, to see where his budget would make the most impact. What study should James run to analyze the impact of all of his marketing initiatives on sales?

• A/B Testing
  • Random Control Trial

• Marketing Mix Model

• Attribution

10. While optimizing the sales process, James creates a visualization to represent the sales funnel.

Based on this visualization, which approach should James take to increase subscriptions?

• This is a reverse funnel, he needs to increase awareness of his product.
  • This funnel is a blocker, he should consider why customers are getting stuck at this stage.
  • This is a tornado funnel, he needs to check out the flow.

• This is a classic funnel, things are looking healthy, James does not need to change anything in his approach.

11. Based on the K-means clustering, James found 3 clusters that seem to define his current client base. Since James used the dollar amount spent and the business size as the starting variables for his cluster analysis, he knows that the segments are quite distinct in terms of these variables.

Meta Marketing Analytics – K-means clustering

How would you define Cluster 3?

• Medium businesses that spend a medium amount.
  • Large businesses that spend little.
  • None of these are true

• Small businesses that spend a lot.

12. James understands that his management will also want to know the ROI for the advertising campaign he ran last year. Which of the following formulas should James use to calculate the ROI?

• ROI = (revenue made from ads / advertising spend) * 100

• ROI = (net profit / net spend) * 100

• ROI = (net spend / net profit) * 100
• ROI = (net profit * net spend) / 100

13. James is hoping to get a substantial advertising budget for next year. To achieve that, he knows that it would help to show the CLTV for his clients. That may help convince management that their investment now will really pay off in the future. But, since James only launched Snackwall a year ago, it is going to be difficult to show CLTV. What value is James missing to calculate CLTV?

• Average Number of Transactions
  • Profit Margin

• Customer Retention Period

• Average Value of a Sale

14. James decides to estimate the retention period for his clients. He believes that he can keep a client for 3.5 years, which is similar to the retention period for the cleaning subscription side of his business. With this in mind, what is the CLTV for Snackwall if the following is true:

Average order value = $1000

Average number of orders per year = 15

Profit Margin = 46%

• $258.125

• $24,150

• $10,629
• $3,717,000

15. Finally, for his budget presentation, James showed the following chart from a linear regression analysis he ran, evaluating the influence of advertising spending on sales, based on last year’s experience. This chart helps James prove that sales and advertising spending are 93.5% correlated. True or False?

• False

• True

16. James’ management is happy with the progress he made last year, and his presentation was a success. He is given a large advertising budget for the next year, in fact, his budget will now be $250K. James’ manager told him that he trusts he will use the budget well, but that he wants to see that the advertising campaigns James runs are resulting in additional subscriptions.

What type of test should James plan to make sure he can prove this to his boss?

• James should plan to have a marketing mix model created
  • James should plan to run an attribution study

• James should plan to run a random control trial experiment

• James should plan to run an A/B test

17. Before spending any of his budget, James wants to compare all of the results in the different marketing channels last year, to see where his budget would make the most impact. James should run an Attribution Study to analyze the impact of all of his marketing initiatives on sales. True or False?

• False

• True

18. Based on the K-means clustering, James found 3 clusters that seem to define his current client base. Since James used the dollar amount spent and the business size as the starting variables for his cluster analysis, he knows that the segments are quite distinct in terms of these variables.

How would you define Cluster 2?

• None of these are true
  • Medium businesses that spend a lot.

• Large businesses that spend a medium amount.

• Small businesses that spend little.

19. James is hoping to get a substantial advertising budget for next year. To achieve that, he knows that it would help to show the CLTV for his clients. That may help convince management that their investment now will really pay off in the future. But, since James only launched Snackwall a year ago, it is going to be difficult to show CLTV. Which of the values that James requires to calculate CLTV does he have access to? (Select all that apply)

• Customer Retention Period

• Average Number of Transactions

• Profit Margin

• Average Value of a Sale

20. While optimizing the sales process, James creates a visualization to represent the sales funnel.

Based on this visualization, which approach should James take to improve subscription rates?

• This funnel is a blockage, he should consider why customers are getting stuck at the interest stage.

• This is a classic funnel, things are looking healthy, James does not need to change anything in his approach.
• This is a reverse funnel, he needs to increase awareness of his product.
• This is a tornado funnel, he needs to check out the flow.

21. James decides that he should focus on the third cluster for his marketing campaign. He believes this segment has more potential, because he has seen from his previous campaign that it is a little harder to convince large businesses to subscribe. After the profiling exercise, he decides to call the segment the ‘Health conscious startups’ to help other people understand and remember this segment.

Next, James turns to showing his management that the advertising budget he was given last year was money well spent. So, James calculates the Return on Ad Spend for last year, and he looks at ROAS by cluster.

He shows the following results based on the total ad spend last year of $120K. The total revenue generated was $940K. The total cost invested last year was $510K, so the profit for the year for Snackwall was $430K.

• The ROAS for Snackwall last year was: 358%.
  • The ROAS for Snackwall last year was: $430K.
  • The ROAS for Snackwall last year was: $940K.

• The ROAS for Snackwall last year was: 783%.

22. While optimizing the sales process, James creates a visualization to represent the sales funnel.

Based on this visualization, which approach should James take to increase subscriptions?

• This is a reverse funnel, he needs to increase awareness of his product.

• This funnel is a blocker, he should consider why customers are getting stuck at this stage.
• This is a classic funnel, things are looking healthy, James does not need to change anything in his approach.
• This is a tornado funnel, he needs to check out the flow.

23. For this final project, we are going to follow James at Snackwall. James launched Snackwall a year ago, and so far, it’s been a real success. Now, James is eager to expand his audience and he is preparing to give his manager an overview of the past year’s success and ask for an advertising budget to help him grow the business.

James knows that going to his boss with a solid plan will help to convince him to allocate marketing budget to the expansion of Snackwall.

As a starting point, James identifies the segments that he should focus on for his advertising campaign. After all, James knows that it would not be a good use of his money to market to everyone. James relies on K-means clustering, using last year’s data on business size and amount spent for Snackwall clients. James worked with Alya, his analyst, and together they ran several iterations of their K-means clustering. Now they are using the chart below to determine the number of clusters James should focus on in his campaign.

How many segments do you suggest James defines for his marketing campaign based on this plot?

• 2 Clusters
  • 1 Cluster
  • 3 Clusters

• 4 Clusters

24. James decides that he should focus on the third cluster for his marketing campaign. He believes this segment has more potential, because he has seen from his previous campaign that it is a little harder to convince large businesses to subscribe. After the profiling exercise, he decides to call the segment the ‘Health conscious startups’ to help other people understand and remember this segment.

Next, James turns to showing his management that the advertising budget he was given last year was money well spent. So, James calculates the Return on Ad Spend for last year, and he looks at ROAS by cluster.

He shows the following results based on the total ad spend last year of $250K. The total revenue generated was $750K. The total cost invested last year was $500K, so the profit for the year for Snackwall was $250K.

• The ROAS for Snackwall last year was: 100%.

• The ROAS for Snackwall last year was: 300%.

• The ROAS for Snackwall last year was: $750K.

• The ROAS for Snackwall last year was: $250K.

25. Finally, for his budget presentation, James showed the following chart from a linear regression analysis he ran, evaluating the influence of advertising spending on sales, based on last year’s experience. What does this chart help James prove? (Select all that apply)

• There is a negative correlation between advertising spending and sales.
  • Sales and advertising spending are 93.5% correlated.

• R2 suggests that we can be confident that our data fits this result.

• There is a positive correlation between advertising spending and sales.

26. James decides to estimate the retention period for his clients. He believes that he can keep a client for 3.5 years, which is similar to the retention period for the cleaning subscription side of his business. With this in mind, what is the CLTV for Snackwall if the following is true:

Average order value = $1500

Average number of orders per year = 12

Profit Margin = 59%

• $3,717,000
  • $10,629
  • $258.125

• $37,170

27. Before spending any of his budget, James wants to compare the results he achieved in all of his different marketing channels last year, to see where his budget would make the most impact. James should run a Marketing Mix Model to analyze the impact of all of his marketing initiatives on sales. True or False?

• False

• True

28. For this final project, we are going to follow James at Snackwall. James launched Snackwall a year ago, and so far, it’s been a real success. Now, James is eager to expand his audience and he is preparing to give his manager an overview of the past year’s success and ask for an advertising budget to help him grow the business.

James knows that going to his boss with a solid plan will help to convince him to allocate marketing budget to the expansion of Snackwall.

As a starting point, James identifies the segments that he should focus on for his advertising campaign. After all, James knows that it would not be a good use of his money to market to everyone. James relies on K-means clustering, using last year’s data on business size and amount spent for Snackwall clients. James worked with Alya, his analyst, and together they ran several iterations of their K-means clustering. Now they are using the chart below to determine the number of clusters James should focus on in his campaign.

How many segments do you suggest James defines for his marketing campaign based on this plot?

• 2 Clusters

• 3 Clusters
• 1 Cluster
• 4 Clusters

29. James understands that his management will also want to know the ROI for the advertising campaign he ran last year. Which of the following formulas do NOT calculate ROI. (Select all that apply)

• ROI = (net profit / net spend) * 100

• ROI = (net profit * net spend) / 100

• ROI = (revenue made from ads / advertising spend) * 100

• ROI = (net spend / net profit) * 100

30. James’ management is happy with the progress he made last year, and his presentation was a success. He is given a large advertising budget for the next year, in fact, his budget will now be $250K. James’ manager told him that he trusts he will use the budget well, but that he wants to see that the advertising campaigns James runs are resulting in additional subscriptions.

James should plan to run a random control trial experiment. True or False?

• False

• True

31. A marketing mix model can help you… (Choose all that apply.)

• Understand the impact of organic engagement alone on your sales
  • Understand the impact of Facebook ads alone on your sales

• Better allocate your marketing budget by knowing what works and what doesn’t

• Better understand the impact of your marketing efforts

32. How much data do you need for an accurate marketing mix model, at the very least

• Five years’ worth
  • One month’s worth

• Two years’ worth

• One year’s worth

33. A marketing mix model is essentially a series of…

• Regression models

• Cluster models
• Time series models
• Classification models

34. What elements are needed to conduct a successful Marketing Mix Model analysis? (Select all that apply.)

• Variables with inadequate impact
  • Historical data that goes back 5 years

• Long historical data window

• High quality data

35. Which ad caused Kathy to buy the mattress?

• The Facebook Newsfeed Ad

• All ads may have had some effect on Kathy’s decision to buy

• The ad Kathy clicked on
• The YouTube video ad

36. Should Imra conclude to put all her advertising dollars in a Facebook campaign with a coupon next year?

• No

• Yes

37. What does Facebook leverage to help solve the challenge of connecting touchpoints to one person? (Select all that apply)

• Cookies

• A unique identifier linked to a Facebook account

• The pixel

• A persistent login

38. You head into your site analytics tool and see people dropping off after visiting your homepage. What is one of the first questions you might ask your data?

• Where do users drop off in the conversion?
  • What is the repurchase rate for returning users?

• What channel are people coming from?

39. What does a “reverse funnel” shape tell you?

• You may have too many people in the consideration and evaluation phases of the funnel
  • You have too many people in your funnel
  • You have a healthy funnel

• You may have too many people in the conversion phase of the funnel

Course 7: Marketing Analytics with Meta

Week 1: Fundamentals of Facebook Ads Manager

PRACTICE QUIZ: INTRODUCTION TO ADS MANAGER

1. Facebook Ads Manager let’s marketers run advertising campaigns on… (Select all that apply)

• Via Text
• Instagram
• Facebook
• Audience Network

2. True or False? Facebook advertising happens through an auction, rather than the more traditional route of paying directly for advertising space.

• False
• True

3. Which part of the Facebook total value ad auction equation covers how much an advertiser is willing to pay to achieve their desired outcome?

• Advertiser Bid
• Estimated Action Rate
• Ad Quality
• Total Value

4. Let’s say two bike part companies are competing in an auction to show one person, named Marissa, an ad. Marissa lives in Portland, Oregon. She regularly buys her bike parts from internet start-ups with a Portland angle.

Company One’s ads target all American women who cycle, whereas Company Two’s ads target cyclists who live in Portland with Portland-specific messages.

Which part of Company Two’s Total Value score does Marissa’s purchasing history boost?

• Advertiser bid
• Estimated Action Rate
• Ad Quality

5. Which part of the Facebook total value ad auction equation tells you the numerical score Facebook assigns to an ad through the auction?

• Advertiser Bid
• Estimated Action Rate
• Ad Quality
• Total Value

6. Which part of the Facebook total value ad auction equation covers feedback from people that view or hide your ad, as well as findings of “low-quality” attributes such as sensationalized language, engagement bait, and more?

• Advertiser Bid
• Estimated Action Rate
• Total Value
• Ad Quality

7. What is the structure of a Facebook ad campaign?

• Campaign –> ad set –> ad
• Campaign –> ad set
• Ad set –> ad
• Ad set –> ad –> campaign

PRACTICE QUIZ: PLANNING AND SCHEDULING ADS WITH FACEBOOK ADS MANAGER

1. Which marketing goal group focuses on encouraging customers to purchase or use your product or service?

• Awareness
• Conversion
• Traffic
• Consideration

2. Which specific ad campaign objective reaches people more likely to like, comment, and share your post?

• Reach
• Brand Awareness
• Conversion
• Engagement

3. If you choose the Traffic objective on Ads Manager, Facebook will show your ad to people who are:

• Likely to click through to your website
• Likely to visit your physical store
• Likely to buy your product
• Likely to sign up for your newsletter

4. Let’s say you’re trying to achieve a marketing goal for app downloads. You want 40,000 people to download the app, which costs $1. You make $0.50 in profits per download. What’s the maximum amount in dollars you can spend on advertising without losing money?

• > 20,000
• 20,000
• < 25,000

5. Which type of budget in Ads Manager lets you control how much money you spend on each ad set?

• Ad Set Budget
• Campaign Budget
• Campaign Budget Optimization
• Lifetime Budget

6. Which feature in Ads Manager allows Facebook to dynamically assign budget to ad sets based on their performance, therefore maximizing your spending efficiency? (Choose all that apply)

• Ad Set Budget
• Daily Budget
• Campaign Budget Optimization
• Lifetime Budget

7. Which bid strategy does Facebook recommend you select in Ads Manager?

• Target Cost
• Bid Cap
• Cost Cap
• Lowest Cost

8. What are the types of audiences you can create in Ads Manager?

• Core Audience, Custom Audience, and Lookalike Audience
• Page Followers, Website Visitors, and App Users
• Custom Audience and Lookalike Audience
• Core Audience, Page Followers, and Engagement

9. What criteria categories can you adjust when you create a Core Audience?

• Location, Age, Gender, Demographics, Interests, and Behaviors
• Location, Age, Gender, Network, Friends, and Other
• Time Zone, Zip Code, Demographics, and Behaviors
• Demographics, Interests, and Behaviors

10. Which type of optimization is best for driving traffic to a store’s website when defining the Ad Set Optimization and Delivery?

• Link Clicks
• Impressions
• Daily Unique Reach
• Landing Page Views

PRACTICE QUIZ: CREATING AN AD IN ADS MANAGER

1. What formats can Facebook ads come in? (Select all that apply)

• Selections
• Images
• Videos
• Carousels

2. Generally, the order you should create your ad in is:

• Select an image or images > Write the copy > Add the link
• Change audience settings > Select template ad > Launch campaign
• Add links > Submit for review > Edit to add copy and images

3. True or False? It’s a good idea to use stock photos when creating your ads as opposed to your own photos, as stock photos are more universal.

• False
• True

4. When you create an ad, if your photo is too large for a square or horizontal format, you should:

• Pick a new photo
• Pick a new campaign objective.
• Pick a new ad format
• Crop the photo

5. True or False: Ads Manager automatically shortens ad text depending on the placement your ad receives.

• True
• False

6. Which of the following things could cause Facebook to reject your ad campaign while it’s in review?

• Advertising to Teenagers
• Vulgar Language
• “Shock and Scare” Violence
• Sexual Content

7. You design an ad campaign for a weight-loss product with “before and after” pictures. Is Facebook likely to reject this campaign for violating its Ad Policies?

• Yes
• No

GRADED QUIZ: FUNDAMENTALS OF FACEBOOK ADS MANAGER

1. Alex’s ad is in the ad auction. What determines whether their ad is shown to someone in their target audience?

• Maximum Budget
• Campaign Strategy
• Total Value

2. True or false: Estimated Action Rate is partially used to determine an ad’s total value.

• True
• False

3. True or false: The last step in launching your campaign is to define the ads that will be shown.

• T​rue
• False

4. Which bid strategy tells Facebook to bid with the goal of getting you the least expensive price per desired action?

• Cost Cap
• Cost Control
• Target Cost
• Lowest Cost