羅納德·費雪

His 1924 article "On a distribution yielding the error functions of several well known statistics" presented Karl Pearson's chi-squared and Student's t in the same framework as the Gaussian distribution, and his own "analysis of variance" distribution z (more commonly used today in the form of the F distribution). These contributions easily made him a major figure in 20th century statistics.

In defending the use of the z distribution when the data were not Gaussian, Fisher introduced the "randomization test". According to biographers Yates and Mather, "Fisher introduced the randomization test, comparing the value of t or z actually obtained with the distribution of the t or z values when all possible random arrangements were imposed on the experimental data."^[9]

However, Fisher wrote that randomization tests were "in no sense put forward to supersede the common and expeditious tests based on the Gaussian theory of errors." Fisher thus effectively began the field of non-parametric statistics, even though he didn't believe it was a necessary move.

His work on the theory of population genetics also made him one of the three great figures of that field, together with Sewall Wright and J. B. S. Haldane, and as such was one of the founders of the neo-Darwinian modern evolutionary synthesis. In addition to founding modern quantitative genetics with his 1918 paper, he was the first to use diffusion equations to attempt to calculate the distribution of gene frequencies among populations. He pioneered the estimation of genetic linkage and gene frequencies by maximum likelihood methods, and wrote early papers on the wave of advance of advantageous genes and on clines of gene frequency. His 1950 paper on gene frequency clines is notable as first application of computers to biology.

Fisher introduced the concept of Fisher information in 1925, some years before Shannon's notions of information and entropy. Fisher information has been the subject of renewed interest in the last few years, both due to the growth of Bayesian inference in artificial intelligence, and due to B. Roy Frieden's book Physics from Fisher Information, which attempts to derive the laws of physics from a Fisherian starting point.

[编辑] Genetical Theory of Natural Selection

Fisher was an ardent promoter of eugenics, which also stimulated and guided much of his work in genetics of man. His book The Genetical Theory of Natural Selection was started in 1928 and published in 1930. It contained a summary of what was already known to the literature. He developed ideas on sexual selection, mimicry and the evolution of dominance. He famously showed that chance of a mutation increasing the fitness of an organism decreases with the magnitude of the mutation. He also proved that larger populations carry more variation so that they have a larger chance of survival. He set forth the foundations of what was to become known as population genetics.

About a third of the book concerned the applications of these ideas to man, and presented what data there was available at the time. He presented a theory that attributed the decline and fall of civilizations to its arrival of a state where the fertility of the upper classes is forced down. Using the census data of 1911 for Britain, he showed that there was an inverse relationship between fertility and social class. This was partly due, he believed, to the rise in social status of families who were not capable of producing many children but who rose because of the financial advantage of having a small number of children. Therefore he proposed the abolishment of the economic advantage of small families by instituting subsidies (he called them allowances) to families with larger numbers of children, with the allowances proportional to the earnings of the father. He himself had two sons and six daughters. 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."

The book was reviewed, among others, by physicist Charles Galton Darwin, a grandson of Charles Darwin's, and following publication of his review, C. G. Darwin sent Fisher his copy of the book, with notes in the margin. The marginal notes became the food for a correspondence running at least three years.^[10]

Between 1929 and 1934 the Eugenics Society also campaigned hard for a law permitting sterilization on eugenic grounds. They believed that it should be entirely voluntary, and a right, not a punishment. They published a draft of a proposed bill, and it was submitted to Parliament. Although it was defeated by a 2:1 ratio, this was viewed as progress, and the campaign continued. Fisher played a major role in this movement, and served in several official committees to promote it.

In 1934, Fisher moved to increase the power of scientists within the Eugenics Society, but was ultimately thwarted by members with an environmentalist point of view, and he, along with many other scientists, resigned.

[编辑] Method and personality

The interest in eugenics, and his experiences working on the Canadian farm, made Fisher interested in starting a farm of his own. In these plans he was encouraged by Gudruna, the wife of a college friend, and this led to him meeting Ruth Eileen Gratton Guinness, Gudruna's younger sister. Ruth Eileen and Gudruna's father, Dr Henry Gratton Guinness, had died when they were young and Ruth Eileen, only sixteen years of age, knew that her mother would not approve of her marrying so young. As a result Fisher married Ruth Eileen at a secret wedding ceremony without her mother's knowledge, on 26 April 1917, only days after Ruth Eileen's 17th birthday. They had two sons and seven daughters, one of whom died in infancy.

As an adult, Fisher was noted for his loyalty to his friends. Once he had formed a favorable opinion of any man, he was loyal to a fault. A similar sense of loyalty bound him to his culture. He was a patriot, a member of the Church of England, politically conservative, and a scientific rationalist. Much sought after as a brilliant conversationalist and dinner companion, he very early on developed a reputation for carelessness in his dress and, sometimes, his manners. In later years he was the archetype of the absent-minded professor.

Having been brought up in the Church of England, he knew the scriptures well, but was not dogmatic in his religious beliefs. In a 1955 broadcast on Science and Christianity, he said, "The custom of making abstract dogmatic assertions is not, certainly, derived from the teaching of Jesus, 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.'

[编辑] Later years

It was Fisher who referred to the growth rate r (used in equations such as the logistic function) as the Malthusian parameter, as a criticism of the writings of Thomas Robert Malthus. Fisher referred to "...a relic of creationist philosophy..." in observing the fecundity of nature and deducing (as Darwin did) that this therefore drove natural selection.

He received the recognition of his peers in 1929 when he was inducted into the Royal Society. His fame grew and he began to travel more and lecture to wider circles. In 1931 he spent six weeks at the Statistical Laboratory at Iowa State College in Ames, Iowa. He gave three lectures a week on his work, and met many of the active American statisticians, including George W. Snedecor. He returned again for another visit in 1936.

In 1933 he left Rothamsted to become a Professor of Eugenics at University College London. In 1937 he visited the Indian Statistical Institute (in Calcutta), which at the time consisted of one part-time employee, Professor P. C. Mahalanobis. He revisited there often in later years, encouraging its development. He was the guest of honor at its 25th anniversary in 1957 when it had grown to 2000 employees^{[來源請求]}. In 1939, when World War II broke out, the University tried to dissolve the eugenics department, and ordered all of the animals destroyed. Fisher fought back, but he was then exiled back to Rothamsted with a much reduced staff and resources. He was unable to find any suitable war work, and though he kept very busy with various small projects, he became discouraged of any real progress. His marriage disintegrated. His oldest son, an (airplane?) pilot, was killed in the war.

In 1943 he was offered the Balfour Chair of Genetics at Cambridge University, his alma mater. During the war, this department was also pretty much destroyed, but the University promised him that he would be charged with rebuilding it after the war. He accepted the offer, but the promises were largely unfilled, and the department grew very slowly. A notable exception was the recruitment in 1948 of the Italian researcher Cavalli-Sforza, who established a one man unit of bacterial genetics. A renewal of Fisher's appointment at Cambridge was not offered by the University in the summer of 1950, much to Fisher's dismay. He now realized he could expect little in the way of support, but he continued his work on mouse chromosome mapping and other projects. They culminated in the publication in 1949 of the idiosyncratic (?) The Theory of Inbreeding. In 1947 he co-founded with Cyril Darlington the journal Heredity: An International Journal of Genetics.

He eventually received many awards for his work and was dubbed a Knight Bachelor by Queen Elizabeth II in 1952.

Fisher was opposed to the conclusions of Richard Doll that smoking caused lung cancer. To quote Yates and Mather again, "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 labors, 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."

After retiring from Cambridge University in 1957 he spent some time as a senior research fellow at the CSIRO in Adelaide, Australia. He died of colon cancer there in 1962.

Fisher's important contributions to both genetics and statistics are emphasized by the remark of L.J. Savage, "I occasionally meet geneticists who ask me whether it is true that the great geneticist R.A. Fisher was also an important statistician" (Annals of Statistics, 1976).

He had an Erdos number of two.