Correlation, causation and linear regression

In 1886 Francis Galton compared the heights of parents and their adult children and found that children of very tall parents were, on average, tall but less extreme than their parents, and likewise for very short ones. He called it regression towards mediocrity; we call it regression to the mean, and the word regression stuck to the whole method of fitting lines.

The line-fitting itself is older: Adrien-Marie Legendre published the method of least squares in 1805. The warning that goes with it took longer. In 1965 Austin Bradford Hill, one of the statisticians who had linked smoking to lung cancer, set out the questions to ask before reading an association as a cause.