Sir Ronald Aylmer FisherFRS (17 February 1890 – 29 July 1962) was a Britishpolymath who was active as amathematician,statistician,biologist,geneticist, and academic.[5] He has been described as "a genius who almost single-handedly created the foundations for modern statistical science"[6][7] and "the single most important figure in 20th century statistics".[8] In genetics, Fisher was the one to most comprehensively combine the ideas ofGregor Mendel andCharles Darwin,[9] as his work usedmathematics to combineMendelian genetics andnatural selection; this contributed to the revival ofDarwinism in the early 20th-century revision of the theory ofevolution known as themodern synthesis. For his contributions to biology,Richard Dawkins declared Fisher to be the greatest of Darwin's successors.[10] He is also considered one of the founding fathers ofNeo-Darwinism.[11][12] According to statisticianJeffrey T. Leek, Fisher is the most influential scientist of all time on the basis of the number of citations of his contributions.[13]
From 1919, he worked at theRothamsted Experimental Station for 14 years;[14] there, he analyzed its immense body of data from crop experiments since the 1840s, and developed theanalysis of variance (ANOVA). He established his reputation there in the following years as abiostatistician. Fisher also made fundamental contributions tomultivariate statistics.[15]
Fisher foundedquantitative genetics,[16][17] and, together withJ. B. S. Haldane andSewall Wright, is known as one of the three principal founders ofpopulation genetics.[18] Fisher outlinedFisher's principle, theFisherian runaway, thesexy son hypothesis theories ofsexual selection,parental investment, and also pioneeredlinkage analysis andgene mapping.[19][20] On the other hand, as the founder ofmodern statistics,[21][22] Fisher made countless contributions, including creating the modern method ofmaximum likelihood and deriving the properties of maximum likelihood estimators,[23]fiducial inference, the derivation of various sampling distributions, founding the principles of thedesign of experiments, and much more. Fisher's famous 1921 paper alone has been described as "arguably the most influential article" onmathematical statistics in the twentieth century, and equivalent to "Darwin onevolutionary biology,Gauss onnumber theory,Kolmogorov onprobability, andAdam Smith oneconomics",[24] and is credited with completely revolutionizing statistics.[25] For his influence and numerous fundamental contributions, he has been described as "the most original evolutionary biologist of the twentieth century" and as "the greatest statistician of all time".[26] His work is further credited with later initiating theHuman Genome Project.[27] Fisher also contributed to the understanding ofhuman blood groups.[28]
Fisher has also been praised as a pioneer of theInformation Age.[29] His work on a mathematical theory of information ran parallel to the work ofClaude Shannon andNorbert Wiener, though based on statistical theory.[30][31] A concept to have come out of his work is that ofFisher information.[32] He also had ideas aboutsocial sciences,[12] which have been described as a "foundation for evolutionary social sciences".[33]
Fisher held strong views onrace andeugenics, insisting on racial differences. Although he was clearly a eugenicist, there is some debate as to whether Fisher supportedscientific racism (see§ Views on race). He was theGalton Professor of Eugenics atUniversity College London and editor of theAnnals of Eugenics.[34]
Fisher was born inEast Finchley inLondon, England, into a middle-class household; his father, George, was a successful partner in Robinson & Fisher, auctioneers and fine art dealers.[35] He was one of twins, with the other twin being still-born[36] and grew up the youngest, with three sisters and one brother.[37] From 1896 until 1904 they lived atInverforth House in London, whereEnglish Heritage installed ablue plaque in 2002, before moving toStreatham.[38] His mother, Kate, died from acuteperitonitis when he was 14, and his father lost his business 18 months later.[35]
Lifelong poor eyesight caused his rejection by theBritish Army forWorld War I,[39] but also developed his ability to visualize problems ingeometrical terms, not in writing mathematical solutions, or proofs. He enteredHarrow School age 14 and won the school's Neeld Medal in mathematics. In 1909, he won a scholarship to studyMathematics atGonville and Caius College, Cambridge. In 1912, he gained a First inMathematics.[40] In 1915 he published a paper,The evolution of sexual preference,[41] onsexual selection andmate choice.
During 1913–1919, Fisher worked as a statistician in the City of London and taughtphysics and maths at a sequence ofpublic schools, at theThames Nautical Training College, and atBradfield College. There he settled with his new bride, Eileen Guinness, with whom he had two sons and six daughters.[42]
In 1918 he published "The Correlation Between Relatives on the Supposition of Mendelian Inheritance", in which he introduced the termvariance and proposed its formal analysis.[43] He put forward agenetics conceptual model showing thatcontinuous variation amongstphenotypic traits measured by biostatisticians could be produced by the combined action of many discrete genes and thus be the result ofMendelian inheritance. This was the first step towards establishingpopulation genetics andquantitative genetics, which demonstrated thatnatural selection could changeallele frequencies in a population, reconciling its discontinuous nature with gradualevolution.[44] Joan Box, Fisher's biographer and daughter, says that Fisher had resolved this problem already in 1911.[45] Today, Fisher's additive model is still regularly used ingenome-wide association studies.[46]
In 1919, he began working at theRothamsted Experimental Station in Hertfordshire, where he would remain for 14 years.[14] He had been offered a position at theGalton Laboratory inUniversity College London led byKarl Pearson, but instead accepted a temporary role at Rothamsted to investigate the possibility of analysing the vast amount of crop data accumulated since 1842 from the "Classical Field Experiments". He analysed the data recorded over many years, and in 1921 publishedStudies in Crop Variation I, his first application of theanalysis of variance (ANOVA).[47]Studies in Crop Variation II written with his first assistant,Winifred Mackenzie, became the model for later ANOVA work.[48] Later assistants who mastered and propagated Fisher's methods wereJoseph Oscar Irwin,John Wishart andFrank Yates. Between 1912 and 1922 Fisher recommended, analysed (with heuristicproofs) and vastly popularized themaximum likelihood estimation method.[49]
Fisher's 1924 articleOn a distribution yielding the error functions of several well known statistics presentedPearson's chi-squared test andWilliam Gosset'sStudent's t-distribution in the same framework as theGaussian distribution, and is where he developedFisher's z-distribution, a new statistical method commonly used decades later as theF-distribution. He pioneered the principles of thedesign of experiments and the statistics of small samples and the analysis of real data.[22]
In 1925 he publishedStatistical Methods for Research Workers, one of the 20th century's most influential books on statistical methods.[50]Fisher's method[51][52] is a technique fordata fusion or "meta-analysis" (analysis of analyses). Fisher formalized and popularized use of thep-value in statistics, which plays a central role in his approach. Fisher proposes the level p=0.05, or a 1 in 20 chance of being exceeded by chance, as a limit for statistical significance, and applies this to a normal distribution (as a two-tailed test), yielding the rule of two standard deviations (on a normal distribution) for statistical significance.[53] The significance of1.96, the approximate value of the 97.5 percentile point of the normal distribution used in probability and statistics, also originated in this book.
"The value for which P = 0.05, or 1 in 20, is 1.96 or nearly 2; it is convenient to take this point as a limit in judging whether a deviation is to be considered significant or not."[54]
In Table 1 of the work, he gave the more precise value 1.959964.[55]
In 1928, Fisher was the first to usediffusion equations to attempt to calculate the distribution ofallele frequencies and the estimation ofgenetic linkage by maximum likelihood methods among populations.[56]
In 1930,The Genetical Theory of Natural Selection was first published byClarendon Press and is dedicated toLeonard Darwin. A core work of the neo-Darwinianmodern evolutionary synthesis,[57] it helped definepopulation genetics, which Fisher founded alongsideSewall Wright andJ. B. S. Haldane, and revived Darwin's neglected idea ofsexual selection.[58]
One of Fisher's favourite aphorisms was "Natural selection is a mechanism for generating an exceedingly high degree of improbability."[59]
Fisher's fame grew, and he began to travel and lecture widely. In 1931, he spent six weeks at the Statistical Laboratory atIowa State College where he gave three lectures per week, and met many American statisticians, includingGeorge W. Snedecor. He returned there again in 1936.[60]
In 1933, Fisher became the head of the Department ofEugenics atUniversity College London.[61] In 1934, he become editor of theAnnals of Eugenics (now calledAnnals of Human Genetics).
In 1935, he publishedThe Design of Experiments, which was "also fundamental, [and promoted] statistical technique and application... The mathematical justification of the methods was not stressed and proofs were often barely sketched or omitted altogether .... [This] ledH.B. Mann to fill the gaps with a rigorous mathematical treatment".[50][62] In this book Fisher also outlined theLady tasting tea, now a famousdesign of a statisticalrandomized experiment which usesFisher's exact test and is the original exposition of Fisher's notion of anull hypothesis.[63][64]
The same year he also published a paper onfiducial inference[65][66] and applied it to theBehrens–Fisher problem, the solution to which, proposed first byWalter Behrens and a few years later by Fisher, is theBehrens–Fisher distribution.
In 1936, he introduced theIris flower data set as an example ofdiscriminant analysis.[67]
In his 1937 paperThe wave of advance of advantageous genes he proposedFisher's equation in the context ofpopulation dynamics to describe the spatial spread of an advantageousallele, and explored its travelling wave solutions.[68] Out of this also came theFisher–Kolmogorov equation.[60]In 1937, he visited theIndian Statistical Institute in Calcutta, and its one part-time employee,P. C. Mahalanobis, often returning to encourage its development. He was the guest of honour at its 25th anniversary in 1957, when it had 2000 employees.[69]
In 1938, Fisher andFrank Yates described theFisher–Yates shuffle in their bookStatistical tables for biological, agricultural and medical research.[70] Their description of the algorithm used pencil and paper; a table of random numbers provided the randomness.
In 1943, along withA. S. Corbet andC. B. Williams he published a paper onrelative species abundance where he developed thelog series distribution (sometimes called the logarithmic distribution) to fit two different abundance data sets.[71][72][73] In the same year he took theBalfour Chair of Genetics where the Italian researcherLuigi Luca Cavalli-Sforza was recruited in 1948, establishing a one-man unit of bacterial genetics.
In 1936, Fisher used aPearson's chi-squared test to analyze Mendel's data and concluded that Mendel's results were far too perfect, suggesting that adjustments (intentional or unconscious) had been made to the data to make the observations fit the hypothesis.[74] Later authors have claimed Fisher's analysis was flawed, proposing various statistical and botanical explanations for Mendel's numbers.[75][76] In 1947, Fisher co-founded the journalHeredity withCyril Darlington and in 1949 he publishedThe Theory of Inbreeding.
In 1950, he published "Gene Frequencies in a Cline Determined by Selection and Diffusion".[77] He developed computationalalgorithms for analyzing data from his balanced experimental designs,[78] with various editions and translations, becoming a standard reference work for scientists in many disciplines. Inecological genetics he andE. B. Ford showed that the force of natural selection was much stronger than had been assumed, with many ecogenetic situations (such aspolymorphism) being maintained by the force of selection.
During this time he also worked on mouse chromosome mapping, breeding the mice in laboratories in his own house.[79]
Fisher publicly spoke out against the 1950 study showing that smokingtobacco causeslung cancer, arguing thatcorrelation does not imply causation.[80][81][82][83][84][85] To quote his biographers Yates and Mather, "It has been suggested that the fact that Fisher was employed as consultant by the tobacco firms in this controversy casts doubt on the value of his arguments. This is to misjudge the man. He was not above accepting financial reward for his labours, but the reason for his interest was undoubtedly his dislike and mistrust of puritanical tendencies of all kinds; and perhaps also the personal solace he had always found in tobacco."[86] Others have suggested that his analysis was biased by professional conflicts and his own love of smoking;[87] he was a heavy pipe smoker.[88]
He gave the 1953Croonian lecture on population genetics.[89]
In the winter of 1954–1955 Fisher metDebabrata Basu, the Indian statistician who wrote in 1988, "With his reference set argument, Sir Ronald was trying to find avia media between the two poles of Statistics – Berkeley andBayes.[90] My efforts to understand this Fisher compromise led me to thelikelihood principle".[91]
In 1957, a retired Fisher immigrated to Australia, where he spent time as a senior research fellow at the AustralianCommonwealth Scientific and Industrial Research Organisation (CSIRO) inAdelaide,South Australia.[92] During this time, he continued in his denial of tobacco harm, and enlisted German eugenicistOtmar von Verschuer to his cause.[88]
Following surgery forcolon cancer, he died of post-operative complications inQueen Elizabeth Hospital in Adelaide on 29 July 1962.[92][88] His remains are interred inSt Peter's Cathedral, Adelaide.[92]
Fisher's doctoral students includedWalter Bodmer,[2]D. J. Finney,Ebenezer Laing,[3][2]Mary F. Lyon[4] andC. R. Rao.[2] Although a prominent opponent ofBayesian statistics, Fisher was the first to use the term "Bayesian", in 1950.[93] The 1930The Genetical Theory of Natural Selection is commonly cited in biology books, and outlines many important concepts, such as:
Fisher is also known for:
Fisher married Eileen Guinness, with whom he had two sons and six daughters.[42]His marriage disintegrated duringWorld War II, and his older son George, anaviator, was killed in combat.[111] His daughter Joan, who wrote a biography of her father, married the statisticianGeorge E. P. Box.[112]
According to Yates and Mather, "His large family, in particular, reared in conditions of great financial stringency, was a personal expression of his genetic and evolutionary convictions."[86] Fisher was noted for being loyal, and was seen as a patriot, a member of theChurch of England, politicallyconservative, as well as a scientific rationalist. He developed a reputation for carelessness in his dress and was the archetype of the absent-minded professor.H. Allen Orr describes him in theBoston Review as a "deeply devoutAnglican who, between founding modern statistics and population genetics, penned articles for church magazines".[113] In a 1955 broadcast on Science and Christianity,[86] he said:
The custom of making abstract dogmatic assertions is not, certainly, derived from the teaching ofJesus, but has been a widespread weakness among religious teachers in subsequent centuries. I do not think that the word for the Christian virtue of faith should be prostituted to mean the credulous acceptance of all such piously intended assertions. Much self-deception in the young believer is needed to convince himself that he knows that of which in reality he knows himself to be ignorant. That surely is hypocrisy, against which we have been most conspicuously warned.
Fisher was involved with theSociety for Psychical Research.[114][115]
Between 1950 and 1951, Fisher, along with other leading geneticists and anthropologists of his time, was asked to comment on a statement thatUNESCO was preparing on the nature of race and racial differences, which was published in 1950 as the UNESCOStatement on Race. The statement, along with the comments and criticisms of a large number of scientists including Fisher, is published in "The Race Concept: Results of an Inquiry" (1952).[116]
Fisher was one of four scientists who opposed the statement. In his own words, Fisher's opposition is based on "one fundamental objection to the Statement", which "destroys the very spirit of the whole document." He believes that human groups differ profoundly "in their innate capacity for intellectual and emotional development" and concludes from this that the "practical international problem is that of learning to share the resources of this planet amicably with persons of materially different nature, and that this problem is being obscured by entirely well-intentioned efforts to minimize the real differences that exist."[117][118][119]
Fisher's opinions are clarified by his more detailed comments on Section 5 of the statement, which are concerned with psychological and mental differences between the races. Section 5 concludes as follows:
Scientifically, however, we realized that any common psychological attribute is more likely to be due to a common historical and social background, and that such attributes may obscure the fact that, within different populations consisting of many human types, one will find approximately the same range of temperament and intelligence.[116]: 14
Of the entire statement, Section 5 recorded the most dissenting viewpoints. It was recorded that "Fisher's attitude … is the same asMuller's andSturtevant's".[116]: 56 Muller's criticism was recorded in more detail and was noted to "represent an important trend of ideas":
I quite agree with the chief intention of the article as a whole, which, I take it, is to bring out the relative unimportance of such genetic mental differences between races as may exist, in contrast to the importance of the mental differences (between individuals as well as between nations) caused by tradition, training and other aspects of the environment. However, in view of the admitted existence of some physically expressed hereditary differences of a conspicuous nature, between the averages or the medians of the races, it would be strange if there were not also some hereditary differences affecting the mental characteristics which develop in a given environment, between these averages or medians. At the same time, these mental differences might usually be unimportant in comparison with those between individuals of the same race…. To the great majority of geneticists it seems absurd to suppose that psychological characteristics are subject to entirely different laws of heredity or development than other biological characteristics. Even though the former characteristics are far more influenced than the latter by environment, in the form of past experiences, they must have a highly complex genetic basis.[116]: 52
Fisher's own words were quoted as follows:
As you ask for remarks and suggestions, there is one that occurs to me, unfortunately of a somewhat fundamental nature, namely that the Statement as it stands appears to draw a distinction between the body and mind of men, which must, I think, prove untenable. It appears to me unmistakable that gene differences which influence the growth or physiological development of an organism will ordinarilypari passu influence the congenital inclinations and capacities of the mind. In fact, I should say that, to vary conclusion (2) on page 5, 'Available scientific knowledge provides a firm basis for believing that the groups of mankind differ in their innate capacity for intellectual and emotional development,' seeing that such groups do differ undoubtedly in a very large number of their genes.[116]: 56
Fisher also ended a 1954 letter toReginald Ruggles Gates, a Canadian-born geneticist who argued that different racial groups were different species, with the words:
I am sorry that there should be propaganda in favour ofmiscegenation in North America as I am sure it can do nothing but harm. Is it beyond human endeavour to give and justly administer equal rights to all citizens without fooling ourselves that these are equivalent items?[120]
Fisher's writings nearly all discuss human populations or humanity as a whole without reference to race or specific racial groups, and none of his work explicitly supports the idea of racial superiority or white supremacy.[120] Fisher had a close personal relationship with Indian statisticianP.C. Mahalanobis, and significantly contributed to the development of theIndian Statistical Institute; and Fisher's graduate students includedWalter Bodmer, a child of Jewish-German parents who fled from Nazi Germany while he was young, andEbenezer Laing, an African geneticist from Ghana.[120]Daniel Kevles, an Americanhistorian of science, described Fisher as an "anti-racist conservative".[120] However, British historian Richard J. Evans, writing inThe New Statesman, argued that Fisher's views on eugenics and his opposition to UNESCO's statement about genetic racial differences were indicative of racism.[121]
In 1911, Fisher became founding Chairman of the University of Cambridge Eugenics Society, whose other founding members includedJohn Maynard Keynes,R. C. Punnett, andHorace Darwin. After members of the Cambridge Society – including Fisher – stewarded the First International Eugenics Congress in London in summer 1912, a link was forged with theEugenics Society (UK).[122] He saweugenics as addressing pressing social and scientific issues that encompassed and drove his interest in both genetics and statistics. During World War I Fisher started writing book reviews forThe Eugenics Review and volunteered to undertake all such reviews for the journal, being hired for a part-time position.
The last third ofThe Genetical Theory of Natural Selection focused on eugenics, attributing the fall ofcivilizations to the fertility of their upper classes being diminished, and used British 1911 census data to show an inverse relationship between fertility and social class, which was partly due, he claimed, to the lower financial costs and hence increasing social status of families with fewer children. He proposed the abolition of extra allowances to large families, with the allowances proportional to the earnings of the father.[123][124][125] He served in several official committees to promote eugenics, including the Committee for Legalizing Eugenic Sterilization which drafted legislation aiming to limit the fertility of "feeble minded high-grade defectives ... comprising a tenth of the total population". It was proposed that this policy would allow for voluntary sterilisation. Fisher was against the idea of forced sterilisation.[126][127]
Beginning in 1934, Fisher became disillusioned with the Eugenics Society over concerns that its activities were increasingly aimed in a political rather than scientific direction; he formally dissociated with the Society in 1941.[120]
Fisher wrote a testimony on behalf of the eugenicistOtmar Freiherr von Verschuer. He wrote that, although the Nazis used Verschuer's work to give scientific support for their ideology, it was "[Verschuer's] misfortune rather than his fault that racial theory was a part of the Nazi ideology."[120][128] He conducted extensive correspondence with von Verschuer over decades, which is held at theUniversity of Adelaide.[88]
Fisher was elected to theRoyal Society in 1929, theAmerican Academy of Arts and Sciences in 1934,[129] theAmerican Philosophical Society in 1941,[130] and the United StatesNational Academy of Sciences in 1948.[131] He was made aKnight Bachelor by QueenElizabeth II in 1952 and awarded theLinnean Society of LondonDarwin–Wallace Medal in 1958.
He won theCopley Medal and the Royal Medal. He was an Invited Speaker of theICM in 1924 in Toronto and in 1928 in Bologna.[132]
In 1950,Maurice Wilkes andDavid Wheeler used theElectronic Delay Storage Automatic Calculator to solve adifferential equation relating to gene frequencies in a paper by Ronald Fisher.[77] This represents the first use of a computer for a problem in the field of biology. TheKent distribution (also known as the Fisher–Bingham distribution) was named after him andChristopher Bingham in 1982, while theFisher kernel was named after Fisher in 1998.[133]
TheR. A. Fisher Lectureship was a North AmericanCommittee of Presidents of Statistical Societies (COPSS) annual lecture prize, established in 1963, until the name was changed to COPSS Distinguished Achievement Award and Lectureship in 2020. On 28 April 1998 a minor planet,21451 Fisher, was named after him.[134]
In 2010, the R.A. Fisher Chair in Statistical Genetics was established in University College London to recognise Fisher's extraordinary contributions to both statistics and genetics.
Anders Hald called Fisher "a genius who almost single-handedly created the foundations for modern statistical science",[6] whileRichard Dawkins named him "the greatest biologist sinceDarwin":
Not only was he the most original and constructive of the architects of the neo-Darwinian synthesis, Fisher also was the father of modern statistics and experimental design. He therefore could be said to have provided researchers in biology and medicine with their most important research tools, as well as with the modern version of biology's central theorem.[135]
Geoffrey Miller said of him:
To biologists, he was an architect of the "modern synthesis" that used mathematical models to integrate Mendelian genetics with Darwin's selection theories. To psychologists, Fisher was the inventor of various statistical tests that are still supposed to be used whenever possible in psychology journals. To farmers, Fisher was the founder of experimental agricultural research, saving millions from starvation through rational crop breeding programs.[136]
Fisher and Sewall Wright both contributed to the development ofpopulation genetics, which became part of themodern synthesis. The interpretation of the mathematical theories of population genetics became a bone of contention between Fisher and Wright by the mid-1920s, and the issue became acrimonious. Dispute persisted for the rest of Fisher's life.[137] A 2021 paper, authored by trustees of the "Fisher Memorial Trust", commented that recent criticism of Fisher could mostly be characterised as "reconsideration of the honour given to individuals from preceding times who are felt to have contributed to social injustice in the past, or to have held views that are felt to have promoted social injustice."[120]
In June 2020, during theinternational protests caused by themurder of George Floyd,Gonville and Caius College announced thata 1989 stained-glass window commemorating Fisher's work would be removed because of his connection with eugenics.[138] An accommodation building, built in 2018 and previously named after him, was subsequently renamed too.[139]University College London also decided to remove his name from its Centre for Computational Biology.[140]
Fisher rejected the notion of smoking cigarettes being dangerous, calling it "propaganda".[141]
{{cite book}}:ISBN / Date incompatibility (help){{cite book}}:ISBN / Date incompatibility (help),Table 1The targets (one-figure numbers and letters of the alphabet) were pasted on the backs of visiting cards, which were put into random order either by shuffling or by the use of random number tables loaned us by Professor Sir Ronald Fisher.
{{cite book}}: CS1 maint: location missing publisher (link)Fisher worked as he didbecause he was an ardent eugenist. (original italics) ... Careful study of Fisher's writings, moreover, enables one to establish strong connections between the problems that Fisher facedqua eugenist and the work in genetics outlined above.
Amemorandum was accordingly circulated to the Council signed by Dr. R.A. Fisher, Professor Huxley, Dr. J.A. Ryle, Mr. E.J. Lidbetter, and myself, asking for authorization to form a sub-committee, the aim of which would be to secure the legalization of eugenics sterilization. The memorandum was unanimously approved by the Council, and in this way the nucleus of the existing Committee for Legalizing Eugenic Sterilization was formed.
Who is the greatest biologist since Darwin? That's far less obvious, and no doubt many good candidates will be put forward. My own nominee would be Ronald Fisher. Not only was he the most original and constructive of the architects of the neo-Darwinian synthesis. Fisher also was the father of modern statistics and experimental design. He therefore could be said to have provided researchers in biology and medicine with their most important research tools, as well as with the modern version of biology's central theorem.
Media from Commons
Quotations from Wikiquote
Data from Wikidata| Academic offices | ||
|---|---|---|
| Preceded by | Presidents of theRoyal Statistical Society 1952–1954 | Succeeded by |
| Scientific method | |
|---|---|
| Treatment andblocking | |
| Models andinference | |
| Designs Completely randomized | |
| International | |
|---|---|
| National | |
| Academics | |
| People | |
| Other | |
