The Difference Between Correlation and Causation: Why You Shouldn't Assume One Causes the Other
TLDR The confusion between correlation and causation is a common logical and statistical error that many people make. Strong correlations can exist between unrelated variables, and understanding the differences between correlation and causation is important when interpreting scientific findings.
Timestamped Summary
00:00
The confusion between correlation and causation is a common logical and statistical error that many people make, where they assume that just because two things are correlated, one must cause the other.
01:51
Strong correlations can exist between unrelated variables, such as the number of doctorates awarded in civil engineering and the per capita consumption of mozzarella cheese, the divorce rate in Maine and the per capita consumption of margarine, and the number of people who drown in swimming pools and the number of new movies released starring Nicholas Cage.
03:35
In the 20th century, cases of lung cancer exploded and researchers found a strong correlation between people who smoke cigarettes and people with lung cancer, although correlation doesn't imply causation.
05:21
Confounding variables are a big problem in research, especially in nutritional science, where observational studies often produce correlations that are reported as causation.
07:05
P-hacking is a problem in research where variables are tested against each other multiple times, increasing the chance of finding a statistically significant result by chance.
08:52
Attending college does not necessarily cause higher lifetime earnings; it may be that people who are destined to make more money are more likely to go to college.
10:38
Understanding the differences between correlation and causation is important, as causal relationships will show a correlation, so it's important to be skeptical and consider confounding variables when interpreting scientific findings.