Imagine that it’s a sunny day at the beach. It’s terribly hot, so you decide to cool off in the ocean. As you make your way to the shoreline, you spot an ice cream stand.
Before you decide whether or not to treat yourself, consider the following statistical fact: when sales of ice cream go up, so do deaths by drowning. How should that information affect your decision?
If you’re like most people, you’ll assume that having ice cream before going into the water is dangerous. But it’s really not, and to understand why, we need to recognize the difference between correlation and causation.
Correlation means that there is a relationship between two things. Causation means that one thing causes another thing to happen.
A correlation between two things doesn’t necessarily mean there is causation between the two. So the fact that there is a relationship between ice cream sales and deaths by drowning doesn’t mean that ice cream causes drowning.
Instead, the correlation depends on a third factor: temperature. When it’s hot outside, people buy more ice cream. They’re also more likely to go swimming, which increases the number of drownings. So, ice cream sales and deaths by drowning correlate with each other—but only because they both correlate with temperature.
Whenever there’s a relationship between two things, we tend to assume that one of them caused the other. But as any good statistician will tell you, correlation does not equal causation1. And there are plenty of quite funny statistical findings that illustrate this2. For example, during the years of 2000 through 2009:
- The number of people who drowned by falling into a swimming pool correlates with the number of films Nicolas Cage appeared in.
- The per capita cheese consumption correlates with the number of people who died by becoming tangled in their bedsheets.
- The divorce rate in Maine, New England, correlates with the per capita margarine consumption.
How can these things correlate? Well, if you have a big enough pile of data, you can find plenty of variables that just happen to have a statistical correlation.
It’s a complete coincidence, but still, it’s very tempting to try to come up with an explanation for why Nicolas Cage’s movies makes people stumble into pools. It’s human nature to force causal links:
- “My friend ignores me because she’s mad at me.”
- “I failed the test because I suck at math.”
- “The team is failing because of the coach.”
Explanations like these help us bind facts together, but they’re often inaccurate. The world is a complicated place, and we overestimate our ability to understand the connections within it.
Maybe your friend is just having a bad day. Perhaps you failed the test because you’ve never had a decent math teacher. And the team might be failing because the players aren’t putting in the necessary work.
These things are very hard to know for sure, so pay attention to your tendency to presume that one thing caused another. Be skeptical of your assumptions, open to alternative explanations, and willing to change your mind.
That way, you’ll be less vulnerable to false cause reasoning.