Skip to content
BENIBIX Learn

Correlation vs Causation

People see two things rise together and think one causes the other, and that does not follow. Correlation only says they move together. Causation says that changing one changes the other. A hidden third thing can drive both, so you need a fair test with random groups to show a cause.

General🔢 Math & Statistics

Correlation

How closely two things rise and fall together. It runs from -1 to 1.

Correlation measures how closely two things move together. It is a number from -1 to 1. Near 1, when one goes up the other goes up too. Near -1, when one goes up the other goes down. Near 0, there is no straight-line link at all. A strong correlation does not show that one thing causes the other.

Example
For 30 days, Lucy's café notes the heat and her cold drink sales. The correlation is 0.82, so hot days and high sales go together.
Why it matters
Correlation is often the first clue that two things are linked. It shows where to look next.
Full entry
General🔢 Math & Statistics

Causation

One thing truly makes another happen. Change the cause and the effect changes.

Causation means one thing actually makes another thing happen. Change the cause, and the effect changes too. A correlation only shows that two things move together. To show causation, you usually need a fair test. One group gets the change and another does not, and people land in each group at random.

Example
A drug trial gives the real pill to a random half of 400 patients and a dummy pill to the rest. Only the first half gets better, so the pill caused it.
Why it matters
Decisions need causes, not just links. Paying for a thing that only travels with a result changes nothing.
Full entry

In one line

Correlation
How closely two things rise and fall together. It runs from -1 to 1.
Causation
One thing truly makes another happen. Change the cause and the effect changes.