Skip to content

MODULE 1 · LESSON 1 · Data foundations

What data literacy means

Turn a vague claim into an answerable question and identify the evidence needed.

By Laurence Svekis · Self-paced · All worked data is synthetic unless you supply your own source.

Try the practice ↓

PredictInspectCalculateCheckExplainTransfer

Your starting point

Prerequisites: No prior data-analysis experience is needed.

Definition: Data literacy is the ability to read, question, analyze and communicate data in context. A dataset is an organized collection of recorded observations; it is not the underlying reality itself.

Begin with the decision

An analysis is useful when it helps someone answer a question. “Our course is doing well” is a claim, but it does not say what doing well means. It could refer to enrollment, attendance, independent performance or learner satisfaction. These are different measurements. Choose the intended decision before opening a spreadsheet. A teacher deciding what to reteach needs evidence about misconceptions, not merely a count of logins.

Separate observations from interpretations

An observation is what was recorded: twenty learners submitted an activity. An interpretation connects that record to a meaning: the activity may have been accessible or motivating. A recommendation proposes an action: keep the activity next week. The interpretation and recommendation need reasoning beyond the count. You should be able to point to the evidence for each statement and say what additional information could change your mind.

Use the Vibe Learning loop

Predict what you expect to find, then inspect the records yourself. Ask an AI assistant to challenge a definition or suggest a checking question after your first attempt. Keep responsibility for the calculation, source and conclusion. A fluent explanation can still use the wrong denominator. Record one limitation beside every finding rather than hiding limitations after a confident headline. A small, defensible conclusion is more useful than a large unsupported one.

Two worked examples

Course participation

A fictional class has 30 enrolled learners and 24 submissions. Submission rate is 24 ÷ 30 × 100 = 80%. This describes participation in one activity. It does not show that 80% mastered the concept. To investigate mastery, inspect an independent task aligned with the learning goal and explain the criteria used.

A shop decision

A fictional shop sells 40 items on Saturday and 30 on Sunday. Saturday has ten more item sales, but the shop was open eight hours versus five. The rates are 5 and 6 items per hour. Which comparison matters depends on whether the owner is planning total stock or staffing per open hour.

Where this becomes useful

A community workshop organizer wants to improve attendance. Distinguish registrations, arrivals and people who stayed to the end. A single attendance percentage cannot answer every planning question, and counts from different stages should not be silently substituted.

Make an attempt

Open Table Explorer with Course engagement. Write one question about weekly completion. Name the row unit, numerator and denominator before calculating. Compare your prediction with two rows and explain why completion is not the same as learning.

Open the accompanying interactive lab →

Misconception check

Claim: A larger number always means a better result.

Inspect the correction

Counts need definitions and context. More support tickets may reflect more customers, a service failure, or better reporting.

Independent application

Find a non-sensitive count from your own routine. State a decision, define the observation and its unit, calculate one comparison, and list one thing the number cannot establish. Ask a reader whether your conclusion follows from the evidence.

Completion records practice and self-review. It is not certification of statistical competence.