Statistical Methods and Scientific Inference.

First Edition, American issue. viii, 175 pp. Original cloth. Near Fine, in near fine dust jacket. 'Although likelihood inference was proclaimed as a fundamental form of inference in all editions of [Fisher's] Statistical Methods for Research Workers, it was not developed any further for more than 30 years. Likelihood inference re-appears in Statistical Methods and Scientific Inference (1956) and the discussion there picks up from where the 1921 paper and Statistical Methods for Research Workers had left off, 'The likelihood supplies a natural order of preference among the possibilities under consideration' (chapter III, §6)' (John Aldrich, 'Likelihood and Probability in R. A. Fisher's Statistical Methods for Research Workers; www [dot] economics [dot] soton [dot] ac [dot] uk/staff/aldrich/fisherguide/prob+lik [dot] htm). 'Pearson (1920) supplied Fisher with references to the literature on Bayes' theorem. How many he read at the time is unclear. Boole and Venn, for instance, ran and ran in his writings as redoubtable critics of the 'equal distribution of ignorance' before Fisher (1956) wrote about them in detail. . . . Apart from the odd sentence and a paragraph in (Fisher 1925b, p. 700) inclining to a limiting frequency definition, he did not write on probability until 1956. . . . in Statistical Methods & Scientific Inference (1956) Fisher retold the Bayes-Laplace story in style with long quotations from their writings. The tone is more measured: Bayes is not quite the towering figure in the history of science and, instead of arraigning Laplace for 'cruelty,' (Fisher 1956, p. 15) merely notes that he 'needed a definition wide enough to be used in the vastly diverse applications of the Théorie analytique.' For Fisher the 'vast diversity' of the applications was nothing to be proud of' (Aldrich, 'R. A. Fisher on Bayes and Bayes' Theorem', Bayesian Analysis (2008) 3, Number 1, pp. 161-170).…