I’ve seen this referenced a lot, especially with psychology, but can someone explain what exactly it means? How does correlation not imply causation? Sometimes, does correlation ever imply causation?
In: 160
I can actually highly recommend a video by VSauce called “laws and causes” which does not aim to answer this question, but provides very good insight to it regardless.
I think other people have covered a couple angles already, but here’s one slightly different PoV. Imagine we know what caused some effect. Say, we went hunting. At every 30 minutes, we counted how many deer had been killed in the last 30 minutes. And we also measure the temperature of the barrel of the gun. We know that shooting caused the gun to heat up. We also know that shooting caused the deaths of the deer.
So imagine the plot we could make with this data. On the X-axis is the temperature of the barrel and on the Y-axis is the number of deer shot. We would expect that an increase in dead deer would be accompanied by an increase in barrel temperature. This means the two factors are correlated. It may or may not mean they share a common cause. In this example, they do share a common cause. That “CO” in “CO”rrelation in this instance comes from the “CO” in “CO”mmon cause.
But we also know that the hot barrel did not cause the deaths of deer. Nor did dying deer cause the barrel to heat up. They are correlated, but neither one caused the other.
Latest Answers