Heads up: this browser isn't saving anything for this site, so progress and settings reset when you leave the page. Everything still works while you're here.
Some of DataForge’s cast are still learning. When you teach them, YOU learn it best — catch what they get wrong, then quiz them.
Teach Tell
You be the teacher — Tell is still learning. Helping Tell figure it out is the practice. (Tell's progress stays on this device; nothing is sent anywhere.)
🎓 In a minute you'll be the teacher. Get ready to teach Tell: correlation is not causation.
Two things moving together isn't proof one causes the other. A hidden third factor, like hot weather, can drive both.
You've helped them one at a time. The real understanding is how the ideas CONNECT — teach that next.
Catch (data collection — every dataset has a collector, a purpose, and omissions) ×Tell (interpretation — correlation is not causation; report confidence, not certainty)
A survey of only one neighborhood is used to claim a fact about a whole city. How do Catch and Tell say that goes wrong?
Catch then says: “You can draw a city-wide conclusion from a single neighborhood's data with full confidence.” — is that right?
The link: the interpretation can never claim more than the collection supports.
Gather narrowly, and you may only conclude narrowly.
Tidy (data cleaning — every cleaning choice changes meaning; document the choices) ×Graph (data visualization — which chart tells the truth, not the loudest one)
The same dataset is shown two ways — one drops the outliers, one starts its y-axis at 90 — and they tell opposite stories. How do Tidy and Graph connect?
Tidy then says: “Cleaning data and choosing a chart are neutral steps that can never change the story the data tells.” — is that right?
The link: cleaning and charting are both silent places the data can mislead.
Every cleaning and every chart is a choice that shapes the story.
Capstone — work one dataset honestly together
Three honest data moves. Bring in the cast member for each.
Note who collected it and what is missing. Who?
Who do you bring in?
Clean it and document every choice. Who?
Who do you bring in?
Interpret it as correlation, not proof. Who?
Who do you bring in?
The synthesis: note the collection, clean with care, and interpret with humility — data work you can trust.
