Edward H. Simpson

Edward Hugh Simpson CB (born 10 December 1922)[1] is a retired British civil servant and former statistician best known for describing Simpson's paradox along with Udny Yule.

Edward Simpson was introduced to the thinking of mathematical statistics as a cryptanalyst at Bletchley Park (1942–45).[2] He wrote the paper The Interpretation of Interaction in Contingency Tables while a postgraduate student at the University of Cambridge in 1946 with Maurice Bartlett as his tutor; and published it in the Journal of the Royal Statistical Society in 1951 at Bartlett's request because Bartlett wanted to refer to it.[3]

The paradox is used in mathematical statistics teaching to illustrate the care statisticians need to take when interpreting data. It figured in a 2009 episode of the US television crime-solving series Numb3rs.

Simpson entered the civil service administrative class in the UK Ministry of Education in 1947 and subsequently worked also in the Treasury, the Commonwealth Education Liaison Unit, as Private Secretary to Lord Hailsham as Lord President of the Council and Lord Privy Seal, and in the Civil Service Department. He was a Commonwealth Fund (Harkness) Fellow in the USA (1956–57). At one point a useful observation of his on the aggregate behaviour of teachers' pay was labelled "Simpson's Drift". He retired from the Department of Education and Science as a Deputy Secretary and Companion of the Order of the Bath in 1982 and now lives in Oxfordshire.

References

  1. ↑ SIMPSON, Edward Hugh, Who's Who 2014, A & C Black, 2014; online edn, Oxford University Press, 2014
  2. ↑ Simpson, Edward (June 2010). "Edward Simpson: Bayes at Bletchley Park". Significance. 7 (2). doi:10.1111/j.1740-9713.2010.00424.x. Retrieved 17 March 2013.
  3. ↑ Simpson, E. H. (1951). "The Interpretation of Interaction in Contingency Tables". Journal of the Royal Statistical Society, Series B. 13: 238–241.


This article is issued from Wikipedia - version of the 3/1/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.