Mar 4, 2013 11:20 AM
| Last Modified: Jun 26, 2017 6:36 AM
J. Stuart (“Stu”) Hunter is the statistician we are celebrating in the month of March in this International Year of Statistics. He is considered by many people to be one of the most important and influential statisticians of the last half century, especially with regard to applying statistics to problems in industry.
Hunter was born in Holyoke, Massachusetts, in 1923. He turned south for his higher education. He received a bachelor’s degree in electrical engineering in 1947, a master’s degree in engineering mathematics in 1949, and a doctorate in experimental statistics in 1954 -- all from North Carolina State University, the birthplace of SAS. His doctoral thesis supported the emerging response surface methodology and the properties of the central composite design, in particular.
Contributions to Education
Before teaching, Hunter worked on statistical problems at the American Cyanamid Company as a staff statistician. Then he became a member of Mathematics Research Center at the University of Wisconsin – Madison. Finally, he took a position in 1961 as an associate professor of civil engineering at Princeton University, from which he retired in 2009 to become Professor Emeritus. In addition to his university classes, he taught many classes about design of experiments in industry as well as for professional organizations such as the American Society for Quality and the American Statistical Association.
Hunter has always stressed the importance of clear ideas and definitions. It isn’t that he believes that statistics is inherently confusing, but rather it is a complex and profound subject, and it abounds with nuances that we might otherwise confuse without these clear distinctions. For example, students often struggle with the distinction between parameters (model) and statistics (estimation). We had a long discussion once in which he suggested that we should use separate terms for parameters and their associated statistic, like mean (parameter) and average (estimate) or standard deviation (parameter) and scedastic (estimate).
For many people, Hunter is best known as an author of one of the most successful textbooks in statistics, Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building, which he wrote with Bill Hunter and George Box. The first edition was published in 1978. The 25th anniversary edition was a bit late; it was published in 2005 and the subtitle changed to Design, Innovation, and Discovery. This second edition was completely rewritten to incorporate many new ideas and methods, such as optimal design of experiments and Bayesian analysis. He also published Introductory Engineering Statistics in 1982 with Irwin Guttman and S. S. Wilks.
Hunter has always taken advantage of the latest ideas about education and educational technology. He produced a boxed set of books, Design of Experiments, and recorded a set of lectures in 1961 at the dawn of black and white television. Long before CGI effects, he used many innovative props and devices for interactive demonstrations of the concepts he taught. Who else would think of using a golf cart in a statistics lecture? See for yourself! The video recordings are now available on YouTube as Stu Hunter Teaches Statistics as a courtesy of JMP. And if you'd like to see Hunter talk statistics with David Salsburg, author of The Lady Tasting Tea, more recently, watch this video.
Hunter has many interests, but two interests that he has promoted are Evolutionary Operation (EVOP) and EWMA for automated process control. He also promotes the teachings and methods of quality management by W. Edward Deming. Of course, in the time of Big Data, he is now investigating developments in data mining and machine learning.
Hunter served as the president of the ASA in 1992. He was a founding member of the Environometrics Society.
He also oversaw the launch of Technometrics as its founding editor in 1959. This quarterly journal is published jointly by ASQ and ASA and is a vital source of papers about research in applied statistics for industry. Recent papers include Multivariate Geostatistics, A Robust Standard Deviation Control Chart, and Bayesian Computation Using Design of Experiments-Based Interpolation Technique, just to name a few.
Hunter has been recognized internationally throughout his career for his accomplishments as a teacher and a researcher in statistics and quality methods. He became a fellow of the Royal Statistical Society, the American Association for the Advancement of Science, the ASQ, and the ASA. He received the Brumbaugh Award twice (1959, 1985), the Shewhart Medal (1970), the Ellis Ott Award (1978), and the Deming Medal (1986) from the ASQ. He became an Honorary member of ASQ in 1998. He was honored by the U. S. Army with their Wilks Medal in 1987. The ASA presented him with their Founders Award in 1994. He was elected to the National Academy of Engineering in 2005.
Hunter is especially fond of the format used by the Gordon Research Conferences, in which there is much time given to each topic (two hours) and discussion is strongly encouraged. There is ample time for participants to continue discussions outside of presentations, too. This format leads to deeper exchange of knowledge and deeper working relationships, and is in contrast to the large conference format that requires very brief presentations with little time for discussion.
(Photo Courtesy of Emil M Friedman)
He has lobbied for a new conference about applied statistics that adopted the GRC format. He recently got his wish. The inaugural meeting of the Stu Hunter Research Conference will take place in March. It is simultaneously a celebration of statistics and his 90th birthdaylater this year. Let’s wish him a happy birthday, and many happy returns of the day!
It is difficult, if not impossible, to describe someone as important and accomplished as Hunter with a single word, so I will use two words: enthusiasm and inspiration. You sense his enthusiasm as soon as you begin talking with him. It is infectious. Moreover, you leave feeling inspired to act on whatever you discussed with him. Those are the characteristics of a very special person, and statistics is lucky to have had such a person for so long.
Current and former students and colleagues are invited to share their news and stories about Stu in the comments below.