In one line: A correlation means two things move together. That is all it says.
In summer, ice-cream sales go up. So do sunglasses sales. In winter, both fall.
They rise and fall together — that is a correlation.
Notice what a correlation does not say: buying an ice cream does not make anyone buy sunglasses.
The two just travel together.
Coffee and alertness
People who drink more coffee are often more alert. The pattern alone doesn't say why — maybe people who NEED to stay alert reach for coffee.
Exercise and happiness
People who exercise more tend to be happier. They move together — but which causes which? The correlation alone can't say.
Shoe size and vocabulary
Children with bigger feet know more words. Spooky? No — older children have both.
Memory hook: Correlation = they move together.
It describes a pattern. It does not say WHY.
Free preview
This is the free notes preview
You're reading the free notes. Aimnova Pro unlocks the full study experience — and you can try it free for 7 days:
- FlashcardsLock in vocabulary and key terms with spaced repetition.
- Practice questionsAnswer exam-style questions and get instant AI marking.
- Mock exams & past-paper vaultSit full mocks and see exactly how examiners award marks.
- Personalised study planA daily plan built around your exam date and weak areas.
In one line: Causation means one thing MAKES the other happen.
Stay in the summer, but now look at a different pair: hot weather and ice-cream sales.
When a heatwave hits, sales jump. When it cools down, they fall. The heat makes people buy ice cream.
That is causation — there is an arrow from one thing to the other.
Rainy days and car accidents
Rain makes the roads slippery, so accidents rise. A dry week → fewer accidents. The rain directly changes the driving conditions — a cause.
Smoking and lung cancer
Smoking damages the cells lining the lungs — it CAUSES the cancer risk to rise. Quit, and the risk falls. Change one → the other changes.
Sun and sunburn
Stay out unprotected and the sun burns your skin. Block it with sunscreen → no burn. A direct cause.
Wait — doesn't the heat cause the ice-cream sales?: Yes! And that is exactly the point.
Correlation and causation describe the pair you are looking at.
Heat → ice cream: causation. Ice cream ↔ sunglasses: correlation.
Always ask: is there an arrow between these two things, or do they just move together?
Memory hook — the quick test: Change one thing. MUST the other change?
Cool the weather → ice-cream sales fall. That's causation.
Ban ice cream → sunglasses sales don't care. Just a correlation.
Know your predicted grade
Take timed mock exams and get detailed feedback on every answer. See exactly where you're losing marks.
Key idea: The trap: in the data, a correlation LOOKS exactly like causation.
Here is the classic example.
In summer, ice-cream sales rise — and so do drowning accidents. A strong correlation.
So does ice cream drown people? Of course not. Something hidden drives both.
Three reasons a correlation is not a cause
A third variable
Something else causes both. Hot weather drives ice cream AND swimming (so drownings).
Reverse causation
The arrow might point the other way: B causes A, not A→B. The ice-cream van parks where the crowd is — but does the van draw the crowd, or the crowd draw the van?
Coincidence — it's just luck
Sometimes two things line up by pure luck. One summer, ice-cream sales and exam results might both rise — a fluke that vanishes the next year. Compare enough pairs of things and a few will match by accident.
Third variable · Reverse · Coincidence
Take a real headline: 'teens who use social media more are more anxious'.
It is tempting to say social media causes anxiety. But anxious teens might use it more to cope (reverse causation), or loneliness might drive both (a third variable).
The correlation alone cannot tell us which story is true.
Go further — higher-level insight: Only a true experiment can show causation.
By changing one variable (the IV) while controlling everything else, an experiment rules out third variables and reverse causation.
A correlational study never can — it can only flag a link worth testing.
How this is tested: Causality is one of the four named concepts for Paper 2 Section B. A classic move is to give a correlational study and ask you to discuss it — the top answer spots that it cannot show cause, and names the third-variable / reverse-causation problems.
A study finds that people who eat more breakfast tend to get better grades. A newspaper reports: 'Breakfast boosts grades.' Discuss this study with reference to causality.
Model answer plan
See the mark-by-mark plan — for / against / judgement, with marking guidance — in study mode.
Common mistakes: 1. Accepting the causal claim. Spot that it's correlational.
2. Naming 'third variable' with no example. Give a plausible one.
3. No judgement. A [15] answer weighs and concludes.