During World War II, Tukey worked at the Fire Control Research Office and collaborated with Samuel Wilks and William Cochran. He is claimed to have helped design the U-2 spy plane. After the war, he returned to Princeton, dividing his time between the university and AT&T Bell Laboratories. He became a full professor at 35 and founding chairman of the Princeton statistics department in 1965.
From 1960 to 1980, Tukey helped design the NBC television network polls used to predict and analyze elections. He was also a consultant to the Educational Testing Service, the Xerox Corporation and Merck & Company.
Though he believed in the utility of separating the two types of analysis, he pointed out that sometimes, especially in natural science, this was problematic and termed such situations uncomfortable science.
A. D. Gordon offered the following summary of Tukey's principles for statistical practice:
... the usefulness and limitation of mathematical statistics; the importance of having methods of statistical analysis that are robust to violations of the assumptions underlying their use; the need to amass experience of the behaviour of specific methods of analysis in order to provide guidance on their use; the importance of allowing the possibility of data's influencing the choice of method by which they are analysed; the need for statisticians to reject the role of "guardian of proven truth", and to resist attempts to provide once-for-all solutions and tidy over-unifications of the subject; the iterative nature of data analysis; implications of the increasing power, availability, and cheapness of computing facilities; the training of statisticians.
Tukey coined many statistical terms that have become part of common usage, but the two most famous coinages attributed to him were related to computer science.
While working with John von Neumann on early computer designs, Tukey introduced the word "bit" as a contraction of "binary digit". The term "bit" was first used in an article by Claude Shannon in 1948.
In 2000, Fred Shapiro, a librarian at the Yale Law School, published a letter revealing that Tukey's 1958 paper "The Teaching of Concrete Mathematics" contained the earliest known usage of the term "software" found in a search of JSTOR's electronic archives, predating the OED's citation by two years. This led many to credit Tukey with coining the term, particularly in obituaries published that same year, although Tukey never claimed credit for any such coinage. In 1995, Paul Niquette claimed he had originally coined the term in October 1953, although he could not find any documents supporting his claim. The earliest known publication of the term "software" in an engineering context was in August 1953 by Richard R. Carhart, in a Rand Corporation research memorandum.
^Carhart, Richard (1953). A survey of the current status of the electronic reliability problem(PDF). Santa Monica, CA: Rand Corporation. p. 69. […] It will be recalled from Sec. 1.6 that the term personnel was defined to include people who come into direct contact with the hardware, from production to field use, i.e., people who assemble, inspect, pack, ship, handle, install, operate, and maintain electronic equipment. In any of these phases personnel failures may result in unoperational gear. As with the hardware factors, there is almost no quantitative data concerning these software or human factors in reliability: How many faults are caused by personnel, why they occur, and what can be done to remove the errors. […]