Some Memories of Bill Hunter

Article by George Box on Bill Hunter

I met Bill Hunter in the Fall semester of 1975 when I transferred into his course Statistics 424 at the University of Wisconsin-Madison. It was "Statistics for Experimenters," taught from mimeographed notes by Box, Hunter, and Hunter, that students could purchase from Mary Arthur in the Statistics Department office. The book would ultimately be published in 1978; we students who continued in the Department over the years had the privilege of seeing the book take final form - including the evolution of all the half-normal plots that were in the manuscript when we took the course, into full normal plots when the book was published.

Bill later told the story that he himself had learned from similar notes two decades before, when he got permission from George Box to attend George's graduate seminar on experimental design at Princeton. Bill was the only undergraduate so honored. They were dittoed notes in that case, but had the same + and - signs "marching down the page," as Bill described them. He said that little did he know then, as a student, that he was learning from a book of which he was to become one of the authors. And upon publication in 1978, he said, he broke into doggerel:

The three wrote the book page by page
So that statistics would become all the rage.
But when it came back from the binding,
They made a great finding:
At birth, it had reached voting age!

In 1975 I was a first-semester grad student in the Statistics Department with no prior background in statistics. It was a giant leap. I was grateful to have Statistics 424 as a course that made sense in an otherwise impenetrable semester, especially grateful for Bill's approachability and gift for clarity in teaching. In the first weeks of class Bill talked about his two young sons who had sat in the back of the room during a prior semester, who said afterward that they had really enjoyed the class. When asked what it was that they liked, they said "the pirate hats" - the floating reference distributions that Bill would draw on the blackboard to illustrate sample means that were not significantly different.

Bill and his family spent the following year in Nigeria and would write of their experiences to George Box, who would quote some of them in his class on Time Series in the Fall semester of 1976. One quote was directly related to time series: Bill told how, in order to purchase a bottled drink, one had to bring an empty bottle to trade for a filled one. The hard part was how to get started – where did one get the first bottle to trade?

A handful of us students were treated to a slide show of Nigeria after Bill's return to Madison, the final slide of which was a shot of their home on Vilas Avenue. "Madison is a pretty good place," Bill said.

I continued in the Statistics Department and subsequently took Statistics 824 from Bill, "Advanced Statistical Experimental Design for Engineers." It was such an informative class that I wrote out all the notes again, by hand in those days, and had them bound in a volume that even decades later sits in my office only an arm's reach away. For that course, Bill insisted on productive scientific collaboration and on-target communication of results. Statistics students were paired with "real" science and engineering students to work on actual experiments and data analysis, and present our results as if our lives depended on it. Bill was very demanding when it came to statistical communication, and I imagine some of our ears may still ring today. Bill's explanation of his grading system was as follows: "Imagine, on the last day of the semester, that I am seeing you off at the airport as you depart on your first consulting trip. Your grade will be how I feel as the plane takes off."

I was absent from Madison for three years during a brief career at DuPont in Delaware, in fact being a consultant in the style that Bill had taught us by example. Just as I was returning to Madison, Bill asked me to take over instruction of the statistics short course he had always taught for AIChE, the American Institute of Chemical Engineers. It was an extraordinary gift of trust.

Bill's inspiration and leadership in the quality movement in the next two years is widely known. It gave new life to statistics. Privately, as Bill faced more important challenges and no longer had time for the office routine, his friends and family drew closer with many weekend get-togethers and weekday lunches at Lulu's, Ovens of Brittany, the Fess Hotel, and L'Etoile - and one really big party worthy of a symposium. Bill wrote moving cards to each of us, telling us of his memories of our early acquaintance and growing friendship, of things about us that made him feel good.

And then we lost Bill. The diversity of friends at his service was proof of his connectedness and joy in everyone. He was the intersection of groups that would not otherwise have met, with lasting impact in each. We continue to quote him when we want to make a point in the best possible way. In my own teaching I still assign the full version of his article, "101 Ways to Design an Experiment."

"Bill, we miss you. It was a privilege to be in your circle, and it's an enduring joy to be uplifted by your writings and by memories of our conversations and friendship."

Conrad Fung
September 2009