In Remembrance.
 

In Remembrance

Ron Carne
Lila Gosch
Jessica Holland
Jim Saxe
Larry Thatcher
 

Charles M. Stein

1920–2017
by Taylor Kubota

Charles M. Stein, professor emeritus of statistics, was one of the world's premier mathematical statisticians. Outwardly, he very much fit that part: slim, bearded and bespectacled, thoughtful and spare with his words. But his was a singular mind, inspiring awe at his genius and reverence for his strong morals

Family, friends and colleagues describe him as a broadly knowledgeable, truly individual person who was uncompromising in his expectations for himself and his belief in basic human rights. Stein passed away in his sleep on November 24 at the age of 96.

From Brooklyn to Stanford

Born in Brooklyn, New York in 1920, Stein had a natural talent for math from an early age. Bradley Efron, professor of statistics and biomedical data science at Stanford, knew Stein since 1960 and recalled speaking with him once about his childhood. Stein shared that his father had been a steamboat captain on the Hudson River and, with uncharacteristic excitement, told Efron, Once, when I was 10, he let me steer the boat. You had to take into account at least three derivatives!

Stein earned his bachelor's degree in mathematics at the University of Chicago in 1940, then worked for the U.S. Air Force during World War II. Alongside Kenneth Arrow, George Forsythe and Gil Hunt, he worked to verify weather broadcasts, critical for understanding how weather might affect wartime activities. Of his weather service work, Stein said in a 2003 interview published by Imprints, Our participation in World War II was necessary in the fight against fascism … He spoke out against all United States involvement in wars since WWII and was often involved in anti-war protests.

After he was discharged from the Air Force in 1946, Stein completed his doctorate at Columbia University in 1947 and worked at the University of California, Berkeley, for the next two years, leaving because he refused to sign a loyalty oath, which resulted from McCarthy-era politics. This decision eventually brought him to Stanford, which, as a private university, required no such oath.

Stein was hired as an associate professor in 1953 but became a full professor just three years later, a speed that Susan Holmes, professor of statistics at Stanford, said was just what she would expect from Stein. People underestimated him because he didn't show off, said Holmes, but his talents became clear very quickly.

Although he retired in the late eighties, Stein continued to live close to Stanford for most of the rest of his life and stayed interested in his field. Partially motivated by a dream to use his namesake method (Stein's method) to prove the prime number theorem (a mathematical statement about the distribution of prime numbers), he went to the library every day for an hour to read all the new math books.

An exceptional body of work

Papers written by Stein were notoriously rare. In a 1986 interview published in Statistical Science, he blamed this on a mix of perfectionism and laziness—which Holmes said was the same word he used to describe his daily math text readings. Having seen hundreds of notebooks filled with Stein's drafts of papers, she said that he would rewrite a paper from the beginning if he thought it was flawed but that everything he wrote was packed with brilliance. Some of his most profound results only appeared due to write-ups by friends and students, said Efron.

Even with relatively few written works and his tendency for self-deprecation, Stein was a strong influence on his peers, The ideas he had, many of the people in our department have lived off those ideas, said Holmes. He was just a genius. He thought outside the box. He didn't accept things for what they were. This is a defining feature of Stein's career, during which he gained a reputation for finding counterexamples to long-held statistical beliefs.

Stein's method, Stein's lemma and Stein's paradox are all named for him. Efron, along with his then-PhD student Carl Morris, wrote the 1977 Scientific American article that named Stein's paradox, which came out of the James-Stein theorem (developed with Stein's graduate student Willard James).

A basic summary of the paradox offered by Efron was that there is unexpected information available if one has several independent estimates. In the Scientific American article, Efron explained the paradox with a baseball example: while most people would think the best prediction for the end-of-season batting averages of 10 players would be obtained by looking at each player's early average, the James-Stein theorem showed that including other players' averages leads to a better result. This is a paradox because players' individual performances shouldn't influence each other.

Emmanuel Jean Candès, current chair of math and statistics, called the paradox, the most provocative result in our field of mathematical statistics in our field in the last 60 years. In addition to being highly practical and widely applicable, Candès said the paradox reminds statisticians, and scientists in general, that research is not only about validating your instincts, that there is a responsibility to do hard, trailblazing work as well.

Beyond academia

Stein was renowned for his passionate social activism. He was opposed to war and refused to take military funding for his research. On October 11, 1985, he was the first Stanford faculty arrested in apartheid protests, as reported by the Stanford Daily. His son, Charles Stein Jr., said that his father felt it was his responsibility to stand up for these causes. As a tenured professor, Stein Sr. believed he could use the privilege that came along with the security of his job to give voice to people who would suffer consequences for the same acts of protest.


He had some basic respect for people's individuality and personal freedom, said Stein Jr. He didn't compromise on that. This, added Stein Jr., extended to his parenting as well. Leaving his wife, Margaret, to handle much of the discipline, Stein Jr. said he never heard a stronger admonition from his father than, I wouldn't advise that.

As a PhD student, Candès recalled Stein discussing his activism, even holding informational meetings about his causes in his home. I was really young at the time and was impressed that someone of his stature would come to me and talk passionately about his views, he said It testifies to the kind of person he was, extremely respectful of everyone and every opinion.

Up until the last few years, Stein lived on campus. In addition to his daily library time, he came to seminars whenever possible. He hiked the Stanford hills every day and always led the way when out with the Loma Prieta chapter of the Sierra Club.

Stein Jr. said his father was extraordinary learned in a broad sense. He was well read and spoke five languages, largely self-taught, but never showed off.

Stein was a giant in his field who rarely published and a fervent activist whose disturbances of the peace were almost always in the name of that very ideal, a man of few words but whose words were each incredibly thoughtful and thought-provoking. He was unique, said Stein Jr. of his father. Everyone's unique but he was more unique than others.

Stein was preceded in death by his wife, Margaret. He is survived by two daughters: Sara Stein, her husband, Gua-su Cui, and their son, Max Cui-Stein, of Arlington, Massachusetts; and Anne Stein and her husband, Ezequiel Pagan, of Peekskill, NY; and son Charles Stein Jr. and his wife, Laura Stoker, of Fremont, California.

References

Charles M. Stein, extraordinary statistician and anti-war activist, dies at 96, Stanford News, December 1, 2016. Link.

A Special Program in Honor of Charles Stein; and Charles Stein: The Invariant, the Direct and the "Pretentios", an interview with Charles Stein by Y.K. Leong, Imprints, December 2003, published by Institute for Mathematical Sciences. Link.

A Tribute to Charles Stein, Statistical Science, 2012, Vol. 27, No.1, 1–2; Project Euclid: Mathematics and Statistics Online. Link

A Conversation with Charles Stein, interviewed by Morris H. DeGroot, Statistical Science, 1986, Vol. 1, No. 4, 454–462; Project Euclid: Mathematics and Statistics Online. Link

In Memory Of Charles M. Stein: Extraordinary Stanford Statistician, Anti-War Activist, by Susan C. Schena, Palo Ato Patch, December 1, 2016. Link

A Glimpse at Stein’s Method, in Memory of Charles Stein, posted by Greg Valiant online in Theory Dish: Stanford's CS Theory Research Blog. Link