Ronald A Fisher - Collected Quotes

"The postulate of randomness thus resolves itself into the question, ‘of what population is this a random sample?’ which must frequently be asked by every practical statistician." (Ronald  A Fisher, "On the Mathematical Foundation of Theoretical Statistics", Philosophical Transactions of the Royal Society of London Vol. A222, 1922)

"Equal areas on the [frequency] diagram represent equal frequency; if the data be such that the ranges into which the individuals are subdivided are not equal, care should be taken to make the areas correspond to the observed frequencies, so that the area standing upon any interval of the base line shall represent the actual frequency observed in that interval." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"Grouping in effect replaces the actual data by fictitious data placed arbitrarily at the central values of the groups; evidently a very coarse grouping might be very misleading. It has been shown that as regards obtaining estimates of the parameters of a normal population, the loss of information caused by grouping is less than 1 percent, provided the group interval does not exceed one-quarter of the standard deviation [...] With suitable group intervals, however, little is lost by grouping, and much labour is saved."(Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"If we know exactly how the original population was distributed it is theoretically possible, though often a matter of great mathematical difficulty, to calculate how any statistic derived from a sample of given size will be distributed. The utility of any particular statistic, and the nature of its distribution, both depend on the original distribution, and appropriate and exact methods have been worked out for only a few cases." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925) 

"It may often happen that an inefficient statistic is accurate enough to answer the particular questions at issue. There is however, one limitation to the legitimate use of inefficient statistics which should be noted in advance. If we are to make accurate tests of goodness of fit, the methods pf fitting employed must not introduce errors of fitting comparable to the errors of random sampling; when this requirement is investigated, it appears that when tests of goodness of fit are required, the statistics employed in fitting must be not only consistent, but must be of 100 percent efficiency. This is a very serious limitation to the use of inefficient statistics, since in the examination of any body of data it is desirable to be able at any time to test the validity of one or more of the provisional assumptions which have been made." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"Little experience is sufficient to show that the traditional machinery of statistical processes is wholly unsuited to the needs of practical research. Not only does it take a cannon to shoot a sparrow, but it misses the sparrow! The elaborate mechanism built on the theory of infinitely large samples is not accurate enough for simple laboratory data. Only by systematically tackling small sample problems on their metrics does it seem possible to apply accurate tests to practical data." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"No human mind is capable of grasping in its entirety the meaning of any considerable quantity of numerical data." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"Statistics may be regarded as (i) the study of populations, (ii) as the study of variation, and (iii) as the study of methods of the reduction of data." (Ronald A Fisher, "Statistical Methods for Research Worker", 1925)

"The conception of statistics as the study of variation is the natural outcome of viewing the subject as the study of populations; for a population of individuals in all respects identical is completely described by a description of anyone individual, together with the number in the group. The populations which are the object of statistical study always display variations in one or more respects. To speak of statistics as the study of variation also serves to emphasise the contrast between the aims of modern statisticians and those of their predecessors." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"The correlation table is useful for three distinct purposes. It affords a valuable visual -representation of the whole of the observations, which with a little experience is as easy to comprehend as a dot diagram; it serves as a compact record of extensive data, which, as far as the two variates are concerned, is complete. […] the data so presented form a convenient basis for the immediate application of methods of statistical reduction. The most important statistics which the data provide, means, variances, and covariance, can be most readily calculated from the correlation table." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"The preliminary examination of most data is facilitated by the use of diagrams. Diagrams prove nothing, but bring outstanding features readily to the eye; they are therefore no substitutes for such critical tests as may be applied to the data, but are valuable in suggesting such tests, and in explaining the conclusions founded upon them." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925) 

"The problems which arise in the reduction of data may thus conveniently be divided into three types: (i) Problems of Specification, which arise in the choice of the mathematical form of the population. (ii) When a specification has been obtained, problems of Estimation arise. These involve the choice among the methods of calculating, from our sample, statistics fit to estimate the unknow n parameters of the population. (iii) Problems of Distribution include the mathematical deduction of the exact nature of the distributions in random samples of our estimates of the parameters, and of other statistics designed to test the validity of our specification (tests of Goodness of Fit)." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

"The statistical examination of a body of data is thus logically similar to the general alternation of inductive and deductive methods throughout the sciences. A hypothesis is conceived and defined with all necessary exactitude; its logical consequences are ascertained by a deductive argument; these consequences are compared with the available observations; if these are completely in, accord with the deductions, the hypothesis is justified at least until fresh and more stringent observations are available." (Ronald A Fisher, "Statistical Methods for Research Workers", 1925)

An observation is judged significant, if it would rarely have been produced, in the absence of a real cause of the kind we are seeking. It is a common practice to judge a result significant, if it is of such a magnitude that it would have been produced by chance not more frequently than once in twenty trials. This is an arbitrary, but convenient, level of significance for the practical investigator, but it does not mean that he allows himself to be deceived once in every twenty experiments. The test of significance only tells him what to ignore, namely all experiments in which significant results are not obtained. He should only claim that a phenomenon is experimentally demonstrable when he knows how to design an experiment so that it will rarely fail to give a significant result. Consequently, isolated significant results which he does not know how to reproduce are left in suspense pending further investigation." (Ronald A Fisher, "The Statistical Method in Psychical Research", Proceedings of the Society for Psychical Research 39, 1929)

"Professor Eddington has recently remarked that 'The law that entropy always increases—the second law of thermodynamics - holds, I think, the supreme position among the laws of nature'. It is not a little instructive that so similar a law should hold the supreme position among the biological sciences. While it is possible that both may ultimately be absorbed by some more general principle, for the present we should note that the laws as they stand present profound differences - (1) The systems considered in thermodynamics are permanent; species on the contrary are liable to extinction, although biological improvement must be expected to occur up to the end of their existence. (2) Fitness, although measured by a uniform method, is qualitatively different for every different organism, whereas entropy, like temperature, is taken to have the same meaning for all physical systems. (3) Fitness may be increased or decreased by changes in the environment, without reacting quantitatively upon that environment. (4) Entropy changes are exceptional in the physical world in being irreversible, while irreversible evolutionary changes form no exception among biological phenomena. Finally, (5) entropy changes lead to a progressive disorganization of the physical world, at least from the human standpoint of the utilization of energy, while evolutionary changes are generally recognized as producing progressively higher organization in the organic world." (Ronald A Fisher, "The Genetical Theory of Natural Selection", 1930)

"In scientific subjects, the natural remedy for dogmatism has been found in research. By temperament and training, the research worker is the antithesis of the pundit. What he is actively and constantly aware of is his ignorance, not his knowledge; the insufficiency of his concepts, of the terms and phrases in which he tries to excogitate his problems: not their final and exhaustive sufficiency. He is, therefore, usually only a good teacher for the few who wish to use their mind as a workshop, rather than to store it as a warehouse." (Ronald A Fisher, "Eugenics, Academic and Practical Eugenics" Review Vol. 27, 1935)

"The statistician cannot evade the responsibility for understanding the process he applies or recommends." (Ronald A Fisher, "The Design of Experiments", 1935)

"To consult the statistician after an experiment is finished is often merely to ask him to conduct a post mortem examination. He can perhaps say what the experiment died of." (Ronald A Fisher, [presidential address] 1938)

"The effects of chance are the most accurately calculable, and therefore the least doubtful of all the factors of an evolutionary situation." (Ronald A Fisher, "Croonian Lecture: Population Genetics", Proceedings of the Royal Society of London Vol. 141, 1955)

"The precise specification of our knowledge is, however, the same as the precise specification of our ignorance." (Ronald A Fisher, Statistical Methods and Scientific Inference, 1959)

"In relation to any experiment we may speak of this hypothesis as the 'null hypothesis', and it should be noted that the null hypothesis is never proved or established, but is possibly disproved, in the course of experimentation. Every experiment may be said to exist only in order to give the facts a chance of disproving the null hypothesis." (Sir Ronald A Fisher, "The Design of Experiments", 1971)

"Inductive inference is the only process known to us by which essential new knowledge comes into the world." (Sir Ronald A Fisher, "The Design of Experiments", 1971)

"[…] no isolated experiment, however significant in itself, can suffice for the experimental demonstration of any natural phenomenon; for the ‘one chance in a million’ will undoubtedly occur, with no less and no more than its appropriate frequency, however surprised we may be that it should occur to us." (Sir Ronald A Fisher, "The Design of Experiments", 1971)

"Statistical procedure and experimental design are only two different aspects of the same whole, and that whole is the logical requirements of the complete process of adding to natural knowledge by experimentation." (Sir Ronald A Fisher, "The Design of Experiments", 1971)

"The statistician cannot excuse himself from the duty of getting his head clear on the principles of scientific inference, but equally no other thinking man can avoid a like obligation." (Sir Ronald A Fisher, "The Design of Experiments", 1971)

"Sometimes the only thing you can do with a poorly designed experiment is to try to find out what it died of." (Ronald A Fisher)

"The best time to plan an experiment is after you’ve done it." (Ronald A Fisher)