Rullst AcademyRullst Academy/Lesson
Data, probability and statistics I · Lesson 12 / 12

Mission: a conclusion others can check

Aurora station needs a report on two routes. Your mission is not to choose the prettiest number: it is to make a bounded recommendation with visible evidence and uncertainty.

Learning paths24 min

Let's discover together

  1. 1

    Load Challenge, which differs from the initial example. First define a question: typical duration, consistency or deliveries within five minutes? State population, unit, criterion and your prediction before calculating.

  2. 2

    Check missing values and ids. Compare groups using counts, mean, median, range and on-time proportion. Keep the original table. Make a justified scenario change and record how the conclusion responds; do not erase a delay merely because it is inconvenient.

  3. 3

    Add a selection comparison: all cases versus a sample. Report method, ids and seed when used. A different recommendation can be coherent with a different criterion; justify it without claiming causation or a future guarantee.

  4. 4

    Fill in question, interpretation and limitation in the workshop; download data and report or send the report to the editor. The activity editor keeps one file in this browser; the account records completion/XP. The ZIP is a template, not an automatic copy of your edits. GitHub is optional.

  5. 5

    Ask someone to check one calculation and question one conclusion, or record that external review is pending. After a break, investigate a new table without copying the previous report. Explain any help, including AI, and what you checked yourself.

Evidence lab

Experiment with fictional deliveries at Aurora station. Analysis runs in this browser. Nothing entered here is sent to the server.

The workshop resets when you leave or reload. Download data and report to keep your work, or send the report to the activity editor, which keeps a draft in this browser. Completion and XP belong to the account.

Header id,group,minutes; one delivery per row; unique id; groups A/B; decimal point; duration 0–1440 with up to two decimal places. Blank means unknown. Up to 100 rows. No quotes or decimal commas. Use invented data.

Selection uses the entered table, including missing values. A draw does not guarantee representativeness. The same seed reproduces selection; it cannot recover cases outside the table.

Make a prediction and analyze the table.

Virtual bag: model with replacement

There are four equally likely tokens; choose how many are blue. Each token returns before the next draw. This is a deterministic simulation, without prizes, money or real observations.

Repeating the seed repeats the sequence. More draws do not guarantee a closer result in every run and do not validate the real-world model.

Two rules, the same accuracy

Ten fictional cases: nine normal and one failure. Rules defined for this example; no AI training or real equipment testing. Same number correct, different consequences.

Two rules, the same accuracy
RuleCorrect / totalMissed failuresFalse alarms

Your investigation report

Official links and next step

✦
YOUR MISSION

Conduct a small original investigation, record limits and revise after feedback.

Now it's your turn

Discovery workshop

Predict, check, explain

Conduct a small original investigation, record limits and revise after feedback.
Build your answers and check when you are ready.
A moment to understand

What lets another person investigate your submission?

I need a hint

Automated assessment checks bounded decisions. Your report, variation and review demonstrate more than XP; they are not professional certification.

Loading your journey…

How can I tell what I learned?

Use the objectives and challenge below for reflection or a conversation with someone who can help. This is guided self-assessment: it sends no answers, awards no XP and does not automatically verify independence.

In Foundations, change an example, predict results, check a normal case and an error case, and explain your choices. If you need help, identify what to practice again.

Your transfer challenge

Create a second dataset with at least eight fictional deliveries. Ask another question, include a boundary case and record when your recommendation would change. After a few days, compare your initial and revised explanations.

Keep evidence: prediction, attempt, result, an original change and what you still cannot explain. Seek feedback when possible; if studying alone, return later without copying and compare attempts.

Try again another time

After a break, explain the idea without opening the solution and try a different example. Compare with your first attempt: what can you do independently, and where do you need a hint? You may write, speak or draw; choose a way to check the same idea. Record help received, including AI, and revisit the part you need. There is no universal deadline or extra XP for this record.

Completions and XP record Rullst Academy assessments. An introductory track can help everyday life and prepare further study; alone it does not prove complete mastery or professional readiness. Level indicates depth, not age.

Take it with you

Create a second dataset with at least eight fictional deliveries. Ask another question, include a boundary case and record when your recommendation would change. After a few days, compare your initial and revised explanations.

At your own pace

My files and GitHub

Every lesson can become your own record: code, notes or a practice plan. Saving a file to GitHub is optional and does not change your XP.

Student guide

The editor and downloads open when this lesson is available to your account. Check access below or return to the track map.

Checking your access to this lesson…

Rullstpetbot

AI can make mistakes. Check the lesson material.