Course outline
Module 1
Module 1: What Is Data and Why It Matters
What Is Data and Why It Matters
Knowledge check
Q1. Which of the following is the best example of data?
- A. A feeling of excitement about a new project
- B. A spreadsheet listing daily temperatures recorded in a city ✓
- C. A general opinion that summer is better than winter
- D. A vague memory of a past vacation
Why: Data is recorded, factual information that can be measured, counted, or observed. A spreadsheet of daily temperatures is a concrete, recorded set of values, while the other options are subjective or not recorded.
Q2. What is the difference between qualitative and quantitative data?
- A. Qualitative data is always more accurate than quantitative data
- B. Quantitative data describes numbers and amounts, while qualitative data describes characteristics or qualities ✓
- C. Qualitative data can only be stored on paper
- D. Quantitative data cannot be used to make decisions
Why: Quantitative data consists of numerical measurements such as height or sales totals, while qualitative data describes categories or qualities such as color, job title, or customer feedback.
Q3. Why does data literacy matter in everyday life?
- A. It helps people avoid using computers altogether
- B. It allows people to read, understand, and question information so they can make better-informed decisions ✓
- C. It guarantees that all data sources are trustworthy
- D. It is only useful for professional statisticians
Why: Data literacy is the ability to read, interpret, and critically evaluate data. It helps individuals make informed choices about health, money, and news, rather than relying on guesses or misleading claims.
Q4. A survey asks 100 people their favorite fruit. Which type of data does the answer 'apple' represent?
- A. Quantitative data
- B. Numerical data
- C. Categorical (qualitative) data ✓
- D. Time-series data
Why: A favorite fruit is a category rather than a number, so it is categorical or qualitative data. Counting how many people chose each fruit would then produce quantitative summaries.
Q5. Why is it important to check where data came from before trusting it?
- A. Data sources never affect the quality of data
- B. Data collected with biased methods or unreliable sources can lead to incorrect conclusions ✓
- C. Only government data needs to be checked
- D. Checking the source makes data easier to store
Why: The reliability of any conclusion depends on how the data was collected. Biased samples, flawed measurements, or unreliable sources can produce misleading results, so questioning the source is a core data literacy skill.
Module 2
Module 2: Reading Charts and Graphs
Reading Charts and Graphs
Knowledge check
Q1. A bar chart shows monthly sales for January through June. Which element of the chart represents the sales value for each month?
- A. The color of the bars
- B. The height (length) of each bar ✓
- C. The labels on the horizontal axis
- D. The title of the chart
Why: In a bar chart, the height or length of each bar is proportional to the value it represents, so taller bars mean higher sales. Colors and labels help identify categories but do not encode the numeric value.
Q2. A line graph shows a company's website visitors over 12 months. The line rises steadily from March to August. What does this trend indicate?
- A. Visitors decreased during those months
- B. Visitors stayed the same during those months
- C. Visitors increased over those months ✓
- D. The data for those months is missing
Why: A line that rises from left to right shows that the value on the vertical axis is increasing over time. Here, website visitors grew steadily from March through August.
Q3. A pie chart shows how a family's budget is divided: 50% housing, 20% food, 10% transport, and 20% other. Which category takes up the largest share?
- A. Food
- B. Transport
- C. Other
- D. Housing ✓
Why: In a pie chart, each slice's size reflects its percentage of the whole. Housing at 50% is the largest slice, which is more than half of the total budget.
Q4. A chart's vertical axis starts at 90 instead of 0, making a small increase in value look dramatic. What is the main concern a careful reader should have?
- A. The chart cannot show any numbers
- B. The chart may exaggerate differences and mislead the viewer ✓
- C. The chart is automatically incorrect and should be discarded
- D. The chart can only be read by experts
Why: A truncated axis can visually magnify small differences, making changes look much larger than they are. Good readers check axis starting points before drawing conclusions.
Q5. A scatter plot shows hours studied on the horizontal axis and exam scores on the vertical axis. The points generally move upward from left to right. What relationship does this suggest?
- A. Studying more hours is associated with higher exam scores ✓
- B. Studying causes exam scores to drop
- C. There is no relationship between the two variables
- D. Exam scores determine how many hours are studied
Why: An upward pattern in a scatter plot indicates a positive association: as one variable increases, the other tends to increase too. This shows association, not proof that studying alone causes the higher scores.
Module 3
Module 3: Spotting Misleading Statistics
Spotting Misleading Statistics
Knowledge check
Q1. A news headline reports that a new diet pill 'doubles weight loss.' The study found participants lost an average of 2 pounds instead of 1 pound with a placebo. What is the most important missing context?
- A. The sample size of the study
- B. The absolute difference in weight loss (1 pound) versus the relative change (100%) ✓
- C. The color of the pill packaging
- D. Whether the study was published online
Why: Relative changes can make small absolute differences sound dramatic. Going from 1 pound to 2 pounds is a doubling, but the real difference is only 1 pound, which may not be meaningful for health.
Q2. A chart shows a company's sales rising sharply, but the vertical axis starts at 980 instead of 0. Why is this potentially misleading?
- A. Starting the axis above zero always makes data accurate
- B. It exaggerates small differences, making modest changes look dramatic ✓
- C. It hides the data points from the viewer
- D. It makes the chart impossible to read
Why: A truncated y-axis stretches small variations across the visual space, so a change of a few percent can look like a massive jump. Always check where the axis begins.
Q3. A survey of 40 people finds that 70% prefer Brand X. A headline says '70% of consumers prefer Brand X.' What is the main problem?
- A. The percentage is calculated incorrectly
- B. The sample is too small and possibly unrepresentative to generalize to all consumers ✓
- C. Surveys are never useful for research
- D. Brand X must have paid for the survey
Why: Forty respondents is a small sample, and the margin of error would be large. Without knowing who was surveyed and how they were chosen, the claim about all consumers is not well supported.
Q4. A city reports that crime increased by 50% this year. Last year there were 2 crimes reported and this year there were 3. What should a careful reader consider?
- A. Crime has clearly become a massive problem
- B. The raw numbers are very small, so one or two incidents can cause large percentage swings ✓
- C. Percentages can never be used with crime data
- D. The city must be lying about its numbers
Why: With tiny counts, percentages are extremely unstable. Going from 2 to 3 is a 50% increase, but it represents just one additional incident, which may be random variation.
Q5. A study finds that ice cream sales and drowning deaths both rise in summer. What does this most likely show?
- A. Eating ice cream causes drowning
- B. Drowning causes people to buy ice cream
- C. Both are influenced by a third factor, warm weather, so they correlate without one causing the other ✓
- D. The data must be fabricated
Why: This is a classic confounding variable example. Hot weather increases both ice cream consumption and swimming, so the two trends move together even though neither causes the other.
Module 4
Module 4: Understanding Averages and Variation
Understanding Averages and Variation
Knowledge check
Q1. A class of five students scored 60, 70, 70, 80, and 100 on a quiz. What is the mean score?
- A. 70
- B. 76 ✓
- C. 80
- D. 60
Why: The mean is the sum of all scores divided by the number of scores. 60 + 70 + 70 + 80 + 100 = 380, and 380 divided by 5 is 76.
Q2. Using the same scores (60, 70, 70, 80, 100), what is the median?
- A. 70 ✓
- B. 76
- C. 80
- D. 100
Why: The median is the middle value when the data is ordered from lowest to highest. With five values, the third value is the middle one, which is 70.
Q3. Which measure of average is most affected by a single extreme value?
- A. Median
- B. Mode
- C. Mean ✓
- D. Range is not an average, but the median is the most affected
Why: The mean uses every value in its calculation, so a single very large or very small value pulls it up or down. The median depends only on the middle position, so extreme values have little effect on it.
Q4. Two datasets both have a mean of 50. Dataset X has values ranging from 45 to 55, while Dataset Y has values ranging from 10 to 90. What does this tell you?
- A. Dataset Y is more accurate than Dataset X
- B. The datasets have the same variation
- C. The means are the same, but Dataset Y has much greater variation ✓
- D. Dataset X has an error in its calculation
Why: Averages describe the center of the data but not how spread out it is. Dataset Y's values are far more spread out than Dataset X's, even though both have the same mean.
Q5. What does the range of a dataset measure?
- A. The middle value of the data
- B. The most frequently occurring value
- C. The average distance of values from the mean
- D. The difference between the largest and smallest values ✓
Why: The range is calculated by subtracting the smallest value from the largest value. It gives a quick sense of how spread out the data is, though it only considers the two extreme values.
Module 5
Module 5: Asking Good Questions of Data
Asking Good Questions of Data
Knowledge check
Q1. A store manager sees that sales increased after a new display was installed. Which question is most useful to ask before concluding the display caused the increase?
- A. How much did we spend on the display?
- B. Did sales also rise in stores that did not get the new display during the same period? ✓
- C. What color is the display?
- D. Who designed the display?
Why: Comparing with stores that did not get the display helps separate the display's effect from other causes, such as seasonal demand or a holiday, that could have raised sales everywhere.
Q2. A dataset reports the average household income in a town is $95,000. Which follow-up question would best help you understand whether that average is representative?
- A. What font was used in the report?
- B. Is the average pulled up by a few very high incomes? ✓
- C. How many people attended the presentation?
- D. Which software was used to make the chart?
Why: Averages can be skewed by extreme values. Asking whether a few very high incomes drive the average helps you check whether the typical household looks different from the mean.
Q3. A survey found that 80% of respondents who use a fitness app say they feel healthier. What is the most important question to ask about this result?
- A. What is the app's logo?
- B. Who chose to respond to the survey, and how were people selected? ✓
- C. Is the app free to download?
- D. How many colors appear in the app?
Why: Self-selected or unrepresentative samples can produce misleading results. Knowing who responded and how they were chosen tells you whether the 80% figure applies beyond those respondents.
Q4. A city reports that crime dropped after changing how it counts reported incidents. What should you ask before comparing this year's numbers to last year's?
- A. Which news outlet first published the numbers?
- B. Was the counting method the same in both years? ✓
- C. How many officers work in the city?
- D. What time of day is it when the numbers are released?
Why: If the definition or method of measurement changed, differences in the numbers may reflect the change in counting rather than real changes in crime. Comparable measurements are essential for valid comparisons.
Q5. Which question best helps you judge whether a correlation between two variables might be caused by a third, hidden factor?
- A. Is the chart colorful?
- B. Could something else, such as a shared underlying cause, explain both variables moving together? ✓
- C. How large is the dataset's file size?
- D. Who is the author's favorite teacher?
Why: Two variables can move together because of a confounding factor rather than because one causes the other. Asking about alternative explanations is a core habit of good data questioning.
Module 6
Module 6: Data Privacy and Ethics
Data Privacy and Ethics
Knowledge check
Q1. Which of the following is the best example of personally identifiable information (PII)?
- A. The average temperature in a city on a given day
- B. A person's full name combined with their home address ✓
- C. The total number of website visitors last month
- D. A product's price listed in a catalog
Why: PII is information that can be used to identify a specific individual. A full name paired with a home address directly identifies a person, while the other options describe aggregate or non-personal information.
Q2. What does 'informed consent' mean in the context of data collection?
- A. Data is collected automatically without the user noticing
- B. Individuals are told what data is collected, why, and how it will be used, and they agree to it ✓
- C. Data is shared with third parties unless the user opts out
- D. Only the company's employees are allowed to read the data
Why: Informed consent means people understand what data is being gathered, its purpose, and how it will be used before they agree to provide it. This transparency is a core principle of ethical data practice.
Q3. Why is anonymizing a dataset before sharing it important?
- A. It makes the dataset larger and more detailed
- B. It removes or masks identifying details so individuals are harder to re-identify ✓
- C. It guarantees the data will never contain errors
- D. It allows the data to be sold at a higher price
Why: Anonymization removes or obscures identifying details to protect individuals' privacy. It reduces the risk that someone could be re-identified from the shared data, though it is not always foolproof.
Q4. A company uses customer purchase history to predict future buying habits. Which ethical principle is most relevant to consider?
- A. Data minimization, meaning collecting only what is necessary for the stated purpose ✓
- B. Data speed, meaning how quickly predictions are generated
- C. Data storage, meaning how much disk space the records require
- D. Data color, meaning how the charts are visually styled
Why: Data minimization asks whether the company needs all the data it collects for its stated purpose. Using purchase history for predictions can be reasonable, but ethical practice requires limiting collection and use to what is genuinely needed.
Q5. Which practice best protects data privacy in an organization?
- A. Giving every employee full access to all databases
- B. Storing passwords in a shared spreadsheet for convenience
- C. Limiting access to data based on job need and using strong authentication ✓
- D. Keeping data indefinitely in case it becomes useful later
Why: Role-based access limits who can see sensitive data to those who need it, and strong authentication helps prevent unauthorized access. Together they reduce the risk of misuse or breaches.
Module 7
Module 7: Telling Stories with Data
Telling Stories with Data
Knowledge check
Q1. Which element is most important for making a data story easy for an audience to understand?
- A. Including as many charts and statistics as possible
- B. Starting with a clear main message or takeaway ✓
- C. Using complex terminology to sound credible
- D. Presenting the raw data tables in full
Why: A clear main message gives the audience a reason to pay attention and a frame for interpreting the data. Without it, even accurate charts can overwhelm or confuse viewers.
Q2. A bar chart shows monthly sales, and the y-axis starts at 90 rather than 0. What is the main concern with this design choice?
- A. Bar charts should never show monthly data
- B. The bars may exaggerate small differences, misleading viewers about the size of changes ✓
- C. The chart will be too difficult to print
- D. Viewers will not be able to read the month labels
Why: Bar lengths are meant to be compared against a zero baseline. Starting the axis at a higher value makes small differences look dramatic, which can mislead the audience about how large the change really is.
Q3. Which of the following best describes the purpose of 'annotation' in a data visualization?
- A. Encrypting the data so only analysts can read it
- B. Adding labels or notes that highlight key points and explain context ✓
- C. Converting numbers into percentages automatically
- D. Removing outliers from the dataset
Why: Annotations, such as callouts or text labels, direct attention to important features and provide context, helping the audience understand what the visual means without guessing.
Q4. When telling a story with data, why is it useful to know your audience?
- A. Audiences only care about the software used to create charts
- B. The right level of detail, terminology, and visuals depends on what the audience already knows and needs ✓
- C. It determines which dataset is legally allowed to be shared
- D. It lets you skip the analysis entirely
Why: A executive, a technical team, and the general public need different levels of detail. Tailoring the story to what the audience knows and cares about makes the message clearer and more persuasive.
Q5. A presenter says, 'Sales rose 12% after the campaign launched.' What is missing that would make this claim stronger?
- A. A rainbow-colored chart
- B. A comparison baseline and time period, such as what sales were before and over what dates ✓
- C. A longer title for the slide
- D. A quotation from a famous economist
Why: A percentage alone lacks context. Knowing the time period and what the prior value was lets the audience judge whether the 12% increase is meaningful and whether the campaign plausibly caused it.