Obituary
I. J. Good
R
enowned statistician Irving John and the more sophisticated Colossus
“Jack” Good died of natural computer. But the significance of the
causes on April 5 at the age of early computers was overshadowed at
92. He was an emeritus university dis- the time by the critical role the scientists
tinguished professor in the statistics at Bletchley Park played in securing the
department at Virginia Tech. victory over Germany.
Jack was born in London in 1916 and The code-breaking work also led
given the name Isidore Jacob Gudak. Jack to the serious study of Bayesian sta-
(His father changed the surname, and tistics, for which he is most famous. In
Jack altered the rest later—he claimed conjunction with Turing, he developed
a popular play titled “The Virtuous the concept of “weight of evidence”
Isidore” opened the door to too many and an early version of the hierarchical
poor jokes.) Jack was a prodigy and model as tools for cryptographers. This
became proficient in mental arithmetic was operationalized as “banburismus”
by the age of nine. Lying in bed with (named for Banbury, the town that
diphtheria, he turned over in his mind printed the special paper on which the
GoodGood
his sister’s lesson on square roots. On calculations were made), an arithmetic
his own, he realized the irrationality process for decryption that reduced the
of the square root of two and solved apparently impossible to merely a very Jack always pointed out that his work
Pell’s equation. The impressive feat of difficult puzzle. was preceded by a binary version of the
independently developing these results After the war, Jack joined Turing at FFT, invented by Frank Yates in the
as a child is not diminished by their the University of Manchester. While context of experimental design.)
prior discovery. there, he posited the idea of “machine After leaving SIS, Jack pursued
Jack distinguished himself in math- building,” an early version of what we research at Cambridge and Oxford,
ematics in secondary school and excelled now know as microprogramming. It was earning ScD and DSc degrees. It was
at Cambridge University (Jesus College), during this time that he published his during this time that he had sub-
where he earned his PhD in mathemat- first book, Probability and the Weighing of stantial interaction with the growing
ics in 1941 with G. H. Hardy and A. S. Evidence, expanding upon Turing’s ideas circle of Bayesians, especially Harold
Besicovitch (J. E. Littlewood also served about measuring the smallest weight of Jeffreys, Dennis Lindley, and Leonard
on his committee). He won Cambridge’s evidence possible. It has become a slim, Jimmie Savage. He made many dura-
Smith Prize for a mathematical essay by but elegant, classic in the field. ble contributions to the philosophy of
a graduate student and devoted much of In 1948, Jack was recruited back Bayesian statistics and did significant
his time to chess. into the British Secret Intelligence work on the Bayesian analysis of con-
During World War II, Jack served Service (SIS). Until 1959, he worked tingency tables and the mathematics
the British government as a cryptanalyst at the Government Communications of distribution theory (especially in
in Bletchley Park, working to break the Headquarters, doing signals intelligence. terms of the combinatorial properties
Enigma and Fish ciphers. This entailed During this period, he did a great deal of moments; combinatorics was a great
extensive collaboration with mathema- of fundamental work in statistics, some enthusiasm of his).
ticians Alan Turing and Max Newman, of which is still classified and some of In 1967, Jack moved to the United
in addition to Donald Michie, a linguist which was published then or later. In States, where he was Virginia Polytechnic
who became an eminent computer sci- particular, he developed a discrete Fast Institute’s university distinguished pro-
entist and longtime friend. Their mutual Fourier Transform that inspired the sub- fessor until he retired in 1994. An avid
efforts ultimately led to the creation of sequent and more general work of J. W. student of coincidence and the occur-
the Heath Robinson, an early computer Cooley and John Tukey. (With his hall- rence of numbers, he became more phil-
named for the British Rube Goldberg, mark penchant for accurate attribution, osophical in the later part of his career.
46 AMSTAT NEWS MAY 2009
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84