Burnside's engagement with the ``modern theory of statistics'' (Q2271734): Difference between revisions

The celebrated algebraist William Burnside, expert in (essentially finite) group theory, later turned himself to the `modern' study of statistics. He writes Gauss's law with precision-constant \(h\). For him, {``the standard formula is arrived at by assuming (i) that the errors follow Gauss's law; (ii) that the precision-constant has the particular value which makes the probability of the observed set of values as great as possible. The alternative formula here put forward [\dots] is arrived at by making the same first assumption and replacing the second by the assumption that a priori all values of the precision-constant are equally likely.''} Yet, unable to keep up with younger competitors, Bunside insists: {``But if the critics say: Then this is not what we mean by Bayes' Theorem, I would reply: Quite so, but it is what Bayes meant by his own Theorem, and it probably fits much better the type of cases to which we are accustomed to apply it than what you mean by Bayes' Theorem.''} Referring probably to a letter addressed to Ronald A. Fisher, Burnside strongly claims: {``I absolutely object to the use of the word `underhand' in connection with anything I have done: and unless it is unequivocally withdrawn this correspondence must cease.''} The article provides well documented sharp interactions between Burnside and the best statisticians of his times.