Concept

Correlation does not imply causation

Overview

The phrase "correlation does not imply causation" refers to the inability to legitimately deduce a cause-and-effect relationship between two events or variables solely on the basis of an observed association or correlation between them. The idea that "correlation implies causation" is an example of a questionable-cause logical fallacy, in which two events occurring together are taken to have established a cause-and-effect relationship.

This fallacy is also known by the Latin phrase cum hoc ergo propter hoc ('with this, therefore because of this'). This differs from the fallacy known as post hoc ergo propter hoc ('after this, therefore because of this'), in which an event following another is seen as a necessary consequence of the former event, and from conflation, the errant merging of two events, ideas, databases, etc., into one.

As with any logical fallacy, identifying that the reasoning behind an argument is flawed does not necessarily imply that the resulting conclusion is false. Statistical methods have been proposed that use correlation as the basis for hypothesis tests for causality, including the Granger causality test and convergent cross mapping. The Bradford Hill criteria, also known as Hill's criteria for causation, are a group of nine principles that can be useful in considering the epidemiologic evidence of a causal relationship. Ultimately, assumptions are always required to draw causal conclusions, and modern causal inference frameworks focus on interrogating the strength of these assumptions.

Overview adapted from Wikipedia (CC BY-SA 4.0; see the article history for authors).

Possible passages

Found by search and not yet checked by a person; they may only mention the idea in passing.

Simplicity and objectivity do not have to be secured through elaborate and labored metaphysical construction. The data are simple and the hypothesis objective in so far as they accomplish the work where unto they are called--the removal of conflict, ambiguity, and inhibition in conduct and affection. In the experimental conception of inference it is clear that the principles of formal logic must play their role…
John Dewey, Creative Intelligence
States what Correlation does not imply causation is.
Read the chapter · Open in the reader
This is a question which we can not be exempted from answering: but the consideration of it belongs to what is called the Theory of Probability, which will form the subject of a chapter hereafter. It is seen, however, at once, that the conclusion does amount to a practical certainty after a sufficient number of instances, and that the method, therefore, is not radically vitiated by the characteristic imperfection…
John Stuart Mill, A System of Logic, Ratiocinative and Inductive
States what Correlation does not imply causation is.
Read the chapter · Open in the reader
There are not a law and an exception to that law, the law acting in ninety-nine cases, and the exception in one. There are two laws, each possibly acting in the whole hundred cases, and bringing about a common effect by their conjunct operation. If the force which, being the less conspicuous of the two, is called the _disturbing_ force, prevails sufficiently over the other force in some one case, to constitute that…
John Stuart Mill, A System of Logic
States what Correlation does not imply causation is.
Read the chapter · Open in the reader

Related ideas

Place in the tradition

Part of Philosophy of science.

Explore Correlation does not imply causation in the interactive graph →