FISHER, SIR R(ONALD) A(YLMER)

(b. Feb. 17, 1890, Londond. July 29, 1962, Adelaide, Australia), British statistician and geneticist who pioneered the application of statistical procedures to the design of scientific experiments. Fisher graduated from the University of Cambridge in 1912. In 1919 he became statistician for the Rothamsted Experimental Station near Harpenden, Hertfordshire, and did statistical work associated with the plant-breeding experiments there. At Rothamsted he developed the analysis of variance, a technique for varying different factors in an experiment and determining the probability of their causing different experimental results. His Statistical Methods for Research Workers (1925) remained in print for more than 50 years. His breeding experiments led to theories about gene dominance and fitness, published in The Genetical Theory of Natural Selection (1930). In 1933 Fisher became Galton professor of eugenics at the University of London. From 1943 to 1957 he was Balfour professor of genetics at the University of Cambridge. He investigated the linkage of genes for different traits and developed methods of multivariate analysis to deal with such questions. At Rothamsted Fisher sought ways of designing plant-breeding experiments so as to provide more amounts of useful information with less investments of time, effort, and money. One major problem he encountered in his work was that of the inadvertently biased selection of materials used in experiments, which resulted in inaccurate or misleading experimental data. To avoid such bias, Fisher introduced the principle of randomization. This principle states that before an effect in an experiment can be ascribed to a given cause or treatment independently of other causes or treatments, the experiment must be repeated on a number of control units of the material and that all units of material used in the experiments must be randomly selected samples from the whole population they are intended to represent. In this way, random, or chance, selection is used to diminish the effects of variability in experimental materials. An even more important achievement was Fisher's origination of the concept of the analysis of variance. This is a statistical procedure used to design experiments that answer several questions at once, instead of just one. Fisher's principal idea was to arrange an experiment as a set of partitioned subexperiments that differ from each other in one or several of the factors or treatments applied in them. The subexperiments are designed in such a way as to permit differences in their outcome to be attributed to the different factors or combinations of factors by means of statistical analysis. This was a notable advance over the prevailing scientific method of varying only one factor at a time in an experiment, which was a relatively inefficient procedure. It was later found that the problems of bias and multivariate analysis that Fisher had solved in his plant-breeding research are encountered in a great deal of other experimental work in biology, and indeed in many other scientific fields as well. Fisher summed up his statistical work in Statistical Methods and Scientific Inference (1956). He was knighted in 1952 and spent the last years of his life conducting research in Australia.