Obituary
it was formally signed by Jack Wolfowitz. Emanuel Parzen. Shortly thereafter, Rupert
However, Wolfowitz was not a specialist Miller, Vernon Johns, Herbert Solomon,
Albert Hosmer Bowker
in multivariate analysis, so Ted Anderson and Herbert Scarf joined the department.
approved the thesis. These appointments were engineered by
Submitted by Ingram Olkin,
Bowker obtained the noncentral distri- Bowker. He formed an applied math and
Stanford University
bution of Hotelling’s T2 statistic using an statistics laboratory and obtained ONR
Courtesy of the Institute of invariance argument described in Section. support to sustain it. Almost everyone in
Mathematical Statistics
5.2.2. of Anderson’s book on multivariate the two departments received support from
analysis. Later, he worked with Rosedith the laboratory, and visitors from all over
In so many ways, Al
Sitgreaves on an asymptotic expansion for visited Stanford during those years.
Bowker was a man
the distribution of a classification statistic. In 1987, the idea of a National Institute
for all seasons. He
Sitgreaves was also a student at Columbia of Statistical Science (NISS) was in its
was the inaugural
and later on the faculty at Teachers infancy. If such an institute was to be
chair of the Statistics
College. She and Bowker married in 1964. founded, a working committee needed to
Department at
When Bowker was chancellor at Berkeley, be created to move it along. Furthermore,
Stanford from 1947–
Rosedith was on the faculty in the School such a committee would need to negoti-
1963 and dean of
of Education at Stanford. ate with university administrations, which
graduate studies
Bowker was a talented leader and devel- suggested it would be wise to have a senior
from 1960–1963.
Albert Hosmer
oper. At Stanford, he helped the math- statesman with name recognition as chair.
Bowker
In 1963, he became
ematics department become an eminent Bowker was an obvious choice. At the
chancellor of the
department in applicable math (a term time, he had completed his role as chan-
City University of New York, and, in 1977,
Bowker preferred to applied mathematics). cellor at both CUNY and Berkeley, and I
he returned to California as chancellor of
He worked with then Provost Fred Terman knew he was somewhat at loose ends and
the University of California, Berkeley. He
to bring the linear accelerator and hospi- would like to be involved in a project. I
was appointed the first assistant secretary
tal (then in San Francisco) to Stanford. asked him if he would be willing to serve
for postsecondary education in the newly
Bowker had the foresight to attract as chair of a committee to form an insti-
formed U.S. Department of Education
George Forsythe with the idea of starting tute of statistics.
in 1980. In 1981, he became founding
a department of computer science, which Bowker knew many of the chancellors
dean of the School of Public Affairs at the
may have been the first such department and presidents of major universities, and
University of Maryland and later became
in the country. A key feature in Bowker’s these connections helped generate interest
executive vice president. He returned to
thinking was that a statistics department in founding the institute. Janet Norwood,
the City University of New York Research
would not be large, and for it to have a formerly commissioner of the Bureau of
Foundation in 1986, where he served as
research effect in a university, it would be Labor Statistics, was the other member.
vice president for planning.
wise to have joint appointments with other Thus, we had two illustrious people, both
Bowker was born in Winchendon,
departments. Thus, over the years, the sta- committed to the furtherance of statistics
Massachusetts, on September 8, 1919, but
tistics faculty had joint appointments with and the development of an institute.
grew up in Washington, DC. His BS was
psychology, economics, education, math- NISS came into existence in 1990 and
in mathematics from MIT in 1941, after
ematics, linear accelerator, Earth sciences, was located in Research Triangle Park in
which he worked on several military proj-
electrical engineering, operations research, North Carolina. Bowker served as chair of
ects and later joined the Statistical Research
and the medical school. As a result, a rath- the board. Much needed to be done, and
Group (SRG) at Columbia. The SRG was
er small department had great influence in he guided the group with excellent coun-
a major statistical center during WWII
the university. sel. His style was characteristic of the way
and a statistical “who’s who” that consisted
When Bowker was chosen by Allen he functioned in other roles. Bowker often
of Abraham Wald, Churchill Eisenhart,
Wallis to chair the newly formed statis- bumbled along, letting everyone speak in a
Jimmie Savage, Milton Friedman, George
tics department, he was in the process of somewhat chaotic track, then at a certain
Stigler, Abe Girshick, Ken Arnold, Harold
completing his dissertation, but even at point—and only he knew when that point
Freeman, Herbert Solomon, Ed Paulson,
this young age, he recognized talent and was reached—there appeared a motion of
Millard Hastay, and Rollin Bennett.
managed to get Abe Girshick to join the exactly what he wanted. Bowker told me
Harold Hotelling was also at Columbia,
department and David Blackwell to visit. that when he went into a meeting, he knew
but moved to The University of North
Although Blackwell left shortly thereafter what he wanted to come out at the end and
Carolina at Chapel Hill in 1946 to head
for Berkeley, Bowker was able to hire a stel- somehow managed to achieve this goal.
the newly formed statistics department.
lar faculty. By 1956, the department had Stories from his days as chancellor confirm
Bowker studied multivariate analy-
a formidable faculty consisting of Kenneth this. Thus, NISS moved along to fruition,
sis with Pao-Lu Hsu when Hsu visited
Arrow (joint with economics), Herman and the profession owes him hearty thanks
Columbia, and when Hsu moved to Chapel
Chernoff, Samuel Karlin (joint with math- for his efforts.
Hill, Bowker followed. Hotelling suggested
ematics), Quinn McNemar (joint with psy- Bowker was concerned with what
a thesis topic on asymptotic distributions.
chology), Charles Stein, Gerald Lieberman we now call “diversity” and “equity.”
When Bowker completed the disserta-
(joint with engineering), Lincoln Moses This is exhibited by two examples. The
tion, which was submitted to Columbia,
(joint with the medical school), and first occurred while he was chancellor at
MARCH 2008 AMSTAT NEWS 39
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