Harold Jeffreys - Collected Quotes

"A prior probability used to express ignorance is merely the formal statement of that ignorance." (Harold Jeffreys, "Theory of Probability", 1939)

"An hypothesis that may be true may be rejected because it has not predicted observable results that have not occurred." (Harold Jeffreys, "Theory of Probability", 1939)

"An observation, strictly, is only a sensation. Nobody means that we should reject everything but sensations. But as soon as we go beyond sensations we are making inferences." (Harold Jeffreys, "Theory of Probability", 1939)

"The theory of probability makes it possible to respect the great men on whose shoulders we stand." (Harold Jeffreys, "Theory of Probability", 1939)

"If we have no information relevant to the actual value of the parameter, the probability must be chosen so as to express the fact that we have none." (Harold Jeffreys, "Theory of Probability", 1939)

"It is essential to the possibility of induction that we shall be prepared for occasional wrong decisions." (Harold Jeffreys, "Theory of Probability", 1939)

"The best way of testing differences from a systematic rule is always to arrange our work so as to ask and answer one question at a time." (Harold Jeffreys, "Theory of Probability", 1939)

"The difference made by any ordinary change of the prior probability is comparable with the effect of one extra observation." (Harold Jeffreys, "Theory of Probability", 1939)

"The posterior probabilities of the hypotheses are proportional to the products of the prior probabilities and the likelihoods." (Harold Jeffreys, "Theory of Probability", 1939)

"The whole of the information contained in the observations that is relevant to the posterior probabilities of different hypotheses is summed up in the values that they give to the likelihood." (Harold Jeffreys, "Theory of Probability", 1939)

"What the use of P [the significance level] implies, therefore, is that a hypothesis that may be true may be rejected because it has not predicted observable results that have not occurred." (Harold Jeffreys, "Theory of Probability", 1939)

“Nature does not consist entirely, or even largely, of problems designed by a Grand Examiner to come out neatly in finite terms, and whatever subject we tackle the first need is to overcome timidity about approximating.” (Harold Jeffreys & Bertha S Jeffreys, “Methods of Mathematical Physics”, 1946)