# Correlation vs Causation

> Why two things moving together does not prove one causes the other. How a hidden third thing can link them, and what a line of best fit shows.

**Course:** [Probability and Statistics](https://learn.benibix.com/learn/general-math)  
**Time:** 12 min

**After this lesson you can:**

- Read a correlation from -1 to 1
- Find a confounding variable
- Say what it takes to show causation

## Why does correlation not prove causation?

Correlation is how closely two things rise and fall together, on a scale from -1 to 1. Near 1, they rise together. Near -1, one rises as the other falls. Near 0, there is no straight-line link. Causation is when one thing truly makes another happen. A strong correlation does not show causation.

Ice cream sales and sunburn rise and fall together. Ice cream does not cause sunburn. Hot, sunny weather drives both. A confounding variable is a hidden third thing like that, which moves two others at once so they look linked.

Sometimes the arrow points the other way. Cities with more police have more crime. Police do not cause crime. Crime brings in more police. A correlation alone cannot tell you which way the cause runs.

And sometimes it is pure chance. Search through enough pairs of numbers and some will line up by accident. The number of films one actor makes in a year can track the number of people who drown in pools. Nothing links them.

The best way to show a cause is to split people at random into two groups. Then change only one thing, for one group. Random splitting spreads each hidden factor evenly. So any difference that appears can be put down to the change. That is how new medicines are tested.

Regression analysis fits a line through data to show how one thing changes when another does. Plot flat size against price, and the line might show that each extra square metre adds a certain amount. It describes the link, but on its own it still does not prove a cause.

The common mistake is to read a news story that says linked to and hear causes. People who drink wine live longer, says the headline. Maybe richer people drink more wine and also get better health care. Always look for the third thing.

![A box at the top reads hot weather. Two solid arrows lead down from it, one to a box reading ice cream sales and one to a box reading sunburn. A dashed line joins the two lower boxes, marked move together. A note under it says neither causes the other.](https://learn.benibix.com/diagrams/gen-confounder.svg)

### Example: A study about breakfast

A study finds children who eat breakfast get better grades. A school plans to hand out free breakfast to raise test scores.

A teacher points out that families who serve breakfast may also check homework and enforce bedtimes. The school runs a trial in half its classes first.

**Words in this lesson:** [Correlation](https://learn.benibix.com/term/general/correlation), [Causation](https://learn.benibix.com/term/general/causation), [Confounding Variable](https://learn.benibix.com/term/general/confounding-variable), [Regression Analysis](https://learn.benibix.com/term/general/regression-analysis)

**Question:** Towns with more churches have more crime. What is the most likely reason?

**Answer:** Bigger towns have more of both. Town size is the confounding variable. More people means more churches and more crime, with no link between the two.

---

Source: https://learn.benibix.com/learn/general-math/correlation-vs-causation
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
