Correlation vs. causation
Correlation means two numbers move together; causation means changing one changes the other. Moving together doesn't prove that one causes the other.
Select any words here to ask your Maestro about them.
Keep only the weeks at 86°F or hotter, all about equally hot. What happens to ice cream and injuries?
The difference: a correlation says two numbers move together. Causation means changing one changes the other. You can measure the first from any table; the second takes more: an experiment, or ruling out whatever else could move them.
Why they get mixed up: often a third thing moves both (a confounding variable), or the cause runs the other way. On a scatter plot both look the same.
A linear regression doesn't prove a cause either: it describes the line the dots follow, whatever the reason.
Practice it in How do I look at the relationship between two columns without claiming a cause?.
How it's used
Three questions before you say "cause"
You found that A and B move together
- Is something moving both?A third variable, like the season or the size of the store.
- Could it run the other way?Maybe B causes A: stores that sell more hire more staff, not the other way around.
- Did you test it by changing only A?An experiment, like an A/B test, is the most direct way to know whether A causes B.
When to look closer
The promotion stores
Sales per store, in thousands of dollars
- marked: With the promotion: 41 · Without: 30
The promotion stores sold 37% more. What would you need to see before saying the promotion did it?
Ask your Maestro about Correlation vs. causation
It answers from the free course page closest to this word, the way it answers while you study.
You: What does "Correlation vs. causation" mean, in plain words?
Your Maestro: I'll explain it with a case of yours: it sticks better than a definition. Which two numbers at your work move together?
Asking about: Answers from the page "When to use a line chart? Showing change over time"
Only this browser keeps what you ask here. How it works
Learn more
Related terms
- Correlation
Correlation measures how closely two numbers move together, from −1 to 1. Near 1: when one rises, so does the other. Near 0: no straight-line link.
- Scatter plot
A scatter plot draws one dot per case, with one variable on each axis, to show whether two numbers move together: when one goes up, does the other go up, go down, or do nothing?
- Linear regression
Linear regression draws the straight line that best follows the points of two variables, to estimate one from the other: y = a + b·x.
- Population and sample
The population is the whole group you want to know about; the sample is the part of it you actually measure to estimate the rest.