Key Statistical Ideas Celebrate Birthdays
Stephen Stigler speaks at Saturday conference, Monday colloquium
Corydon Ireland, Harvard News Office
Originally published in the Harvard University Gazette, October 2, 2008
His audience of 125 statistics profes- of a Google image search on each of the
sionals and students was gathered at the names—including a beautiful blond the
Radcliffe Gymnasium for Quintessential search engine mysteriously linked to the
Contributions, a daylong series of talks. The name Don Rubin.)
event, sponsored by Harvard’s Department Later on Saturday, conference-goers
of Statistics, celebrated the ‘birthdays’ of gathered at the Cambridge Queen’s Head
key statistical ideas and their inventors. in Harvard’s Memorial Hall to celebrate
All of the birthdays—except that of the modern fruits of what in the 1930s was
Gosset’s idea—recognized Harvard statisti- Gosset’s day job: head brewer for Guinness
cians who are still active in the profession. beer in London.
Donald B. Rubin, the John L. Loeb Stigler later calculated that with all the
Professor of Statistics, turned 65 this year, events to be celebrated in the history of
and his own breakthrough study, “Multiple statistics, “there’s always a good reason to
Imputations in Sample Surveys,” turned 30. have a party.”
Stigler
Worldwide, he’s one of the top-10 most- On Monday (Sept. 29), he stayed in
U
niversity of Chicago statistics pro- cited writers in mathematics. town to address about 50 students and
fessor Stephen M. Stigler, a fre- Professor of statistics Carl N. Morris professors in a crowded third-floor class-
quent visitor to Harvard, has a turned 70 this year, and his paper room in the Science Center. Stigler’s talk,
favorite movie—“Magic Town,” a black- “Parametric Empirical Bayes Inference” in professional terms, was inflammatory:
and-white flick from 1947. It stars James turned 25. He’s an expert in analytical “The Five Most Consequential Ideas in the
Stewart as a pollster who discovers a magical methods designed for public policy, health History of Statistics.” The session was one
place: a heartland town whose citizens have care, and sports. of several colloquia sponsored this fall by
a range of opinions that are a near-perfect Herman Chernoff, professor emeritus of the statistics department.
composite of the whole United States. applied mathematics and statistics, turned To qualify on this shortlist, the ideas must
In eight or nine street interviews, Stigler 85 this year—and celebrating its 35th have lasted a while, he said, and must have
said, Stewart’s character gets poll results birthday was his paper “The Uses of Faces had demonstrable consequences for statistics.
“
Basic statistical concepts, whether you put them in your top five or not, [are]
important to the way we think about things
”
.
that otherwise would require hundreds or to Represent Points in K-Dimensional The first idea was to combine observations
thousands of interrogatory encounters. Space Graphically.” He’s best known for in order to arrive at a simple mean. This “spe-
Stigler is a historian of statistics, the sci- “Chernoff faces,” a statistical tool for rep- cies of averaging,” said Stigler, found expres-
ence that uses complicated mathematics—a resenting high-dimensional data, including sion in 1635 through the work of English
world of scatter plots and curve fitting—in the multitude of subtle variables used to curate and astronomer Henry Gellibrand.
order to extract useful information from map the human face. “By combining observations, you actu-
data. It’s employed to analyze information, This year, six of 12 faculty members in ally increase the amount of information
infer probability, and estimate uncertainty. the department of statistics have birthdays you have,” said Stigler of an idea that came
[On] September 27, Stigler delivered divisible by five, said chair Xiao-Li Meng, late to science. “It may seem like ancient
a paper on the 100th anniversary of a a student of the humorously unusual. history, but it’s not.”
groundbreaking paper by W. S. “Student” (To introduce what he called “the birth- Even today, he said, there’s “deter-
Gosset, “The Probable Error of a Mean.” day boys” Saturday, he showed the results mined resistance” to the idea of combining
DECEMBER 2008 AMSTAT NEWS 7
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