Smoking. The Cancer Controversy: Some Attempts to Assess the Evidence

TL;DR — R. A. Fisher’s 1959 pamphlet collecting his letters and lectures disputing that the statistical association between smoking and lung cancer proved causation.

A 1959 pamphlet published by Oliver and Boyd, reprinting in date order the letters and lectures in which Sir Ronald Fisher — one of the founders of modern statistics and experimental design — disputed the conclusion that cigarette smoking causes lung cancer. This copy is a re-typeset version of the pamphlet’s text, of the kind hosted on the University of York’s history-of-statistics pages.

Contents include his 1957 letters to the British Medical Journal on the “alleged dangers of cigarette-smoking,” “Cigarettes, Cancer and Statistics” from The Centennial Review (1958), letters to Nature, a lecture on the nature of probability and a piece on inhaling. Fisher argues that an observed association does not establish causation, raises alternative explanations such as a common genetic factor behind both smoking and cancer, and points to the finding that inhalers did not appear to have more cancer than non-inhalers. His preface calls the public health campaign “a terrifying propaganda.”

Fisher’s position has since been rejected by the scientific consensus; it is often cited as a case study in causal inference and in how an eminent expert can be wrong. Fisher was also a paid consultant to the tobacco industry.

What it is: a historical document by one of the most important statisticians of the twentieth century, on the losing side of a major scientific question. Read it as history of science, not as health guidance. The public link is a university history-of-statistics site rather than the rights-holder.

Where this came from

• A copy saved in October 2026.
• University of York history of statistics pages: https://www.york.ac.uk/depts/maths/histstat/smokingtex.htm

17 pages. A copy is archived locally against link rot; the header links the original source.