Roy Geary and William Sealy Gosset
Philip J Boland, University College Dublin, gave a talk William Sealy Gosset - An Inspiring 'Student' to the 58th World Statistical Congress held in Dublin in 2011. In his talk, which was published in the Proceedings of the Congress, Boland makes some interesting comments on the interaction between Roy Geary and William Sealy Gosset. We give an extract from the relevant section of his paper below:
[Roy Geary] got to know Gosset (the Brewer i/c Statistics) at Guinness in the 1930s. In particular they often corresponded (on business) about sales of stout and porter in Ireland. The following exchange is typical of their correspondence.
Geary wrote (22 March 1934)
Dear Gosset, I am exceedingly obliged for your graphs. The different trends in the Irish Free State sales of porter and of double stout during the last two years are extremely interesting: porter up, stout down. Does it mean that the porter-drinking class are prospering while the stout-drinking class decline: or have the stout drinkers fallen to porter? If you have no direct knowledge of this, the areal figures may furnish a clue. ....Gosset replied (10 May 1934)
Dear Geary, Somerfield has handed me the enclosed table giving the figures for April, 1934, which will enable you to bring your diagrams up to date. I do not know that there is anything very remarkable. Town and Vicinity appear to be fairly prosperous and the rest of the country going to - Connacht!The Table of April, 1934 referred to above dealt with quarterly figures on extra stout and porter showing favourable results for Town and Vicinity (Dublin town and vicinity - vicinity being within 10 miles of the GPO - the Irish General Post Office where the Easter uprising of 1916 took place).
Yours sincerely, W S Gosset.
Roy Geary seconded (with discussion) the vote of thanks on the paper The use of statistical methods in agricultural experiments read to the Statistical and Social Inquiry Society of Ireland (SISSI) by F P Hussey on 20th November, 1936 (Geary, 1936/1937). In doing so he said (wrote)
... in most statistical societies it was traditional that there should be one paper in each session completely incomprehensible to the great majority of members; and it was right that our Society (SISSI), as one of the oldest in the world (1847), should be true to this tradition. ... The method known as the "analysis of variance", which Mr Hussey has utilised, is due principally to Professor R A Fisher, who in recent years developed certain results of Mr W S Gosset, better known under the pseudonym of 'Student', who has lived and worked for the past thirty years in Dublin. Mr Gosset amuses his friends when he says he that he is "no mathematician", for his discoveries of the frequency distribution of the variance of normal samples and of the ratio of the mean to the standard deviation (the square root of the variance) are generally regarded as the most important contribution to the theory of statistics in the last half century.