From ‘Student’ to Student:
Reflecting on 100 Years of History
… in One Saturday
Yves Chretien, Kari Lock, and Andrew C. Thomas, Harvard University
years earlier. The original problem inspired
Rubin’s multiple imputation approach,
which has been widely used since.
We of the personal computer generation
have witnessed an ever-increasing quantity
and complexity of data available in vari-
ous fields, but we’ve also been spoiled with
computers that can handle it, often with a
minimum of direction. It was illuminating
to see Andrew Gelman examine how Carl
Morris’ work on parametric empirical Bayes
helped a previous generation of statisticians
deal with multilevel data (by showing the
value of shrinkage estimation for inference
about a set of unknown quantities) and
still incorporate important and fresh ideas
for thinking about multilevel modeling. In
particular, the comparison of parametric
From left: Speakers and honorees include Stephen Stigler, Fritz Scheuren, Steve Wang, Herman
empirical Bayes methods with fully Bayesian
Chernoff, Don Rubin, Carl Morris, Andrew Gelman, and Xiao-Li Meng. Rubin, Morris, and Meng are
methods highlighted the advantages of mul-
wearing their newly acquired Bayes ties, a gift from presenter Stigler. Meng is wearing a Singapore-
tilevel modeling, as Gelman offered his own
made “celebration shirt,” a gift from a department alumnus.
insights on how and when to pool data,
based in part on Morris’ ideas.
With the advent of cheap computing,
I
t was a birthday party like no other: It underlying message that while their work
graphics have greatly reduced in price and
celebrated the living, the dead, and the was clearly important to them, it was not
increased in ease of creation, which has
immortal. On September 27, we in the enough. A picture of Carl Morris holding
spurred a quest to generate more mean-
Harvard Statistics Department marked the his two then-infant daughters was enough
ingful forms of visualization. Herman
quinquennial anniversaries of the births of to show that to the whole room.
Chernoff, however, had insights ahead of
three senior faculty members—Don Rubin A striking demonstration of how statisti-
his time, as he published the visualization
(65), Carl Morris (70), and Herman cal techniques can be used to help people—
Chernoff (85)—as well as a key paper each when well developed and used in an open
of them wrote some number of half-decades
and transparent manner—was put forth by
ago. This dovetailed nicely with the 100th
Fritz Scheuren. In his tribute to Don Rubin
anniversary of William Gosset’s most cele-
and his work on multiple imputation,
brated paper as the pseudonymous Student,
Scheuren demonstrated a recent and highly
giving us another reason to celebrate, not to
relevant example: estimating an amount of
mention an irresistible theme for jokes
collected money held in trust for Native
and puns.
Americans since 1887. Scheuren illustrated
No one was better equipped to seize this
the difficulties involved in putting together
theme than department chair Xiao-Li Meng,
a reliable estimate of past accountings when
who laid out the agenda with a personal
there was a substantial amount of missing
photo tribute to each of the honorees and
data to be reckoned with. Measuring the
presenters. What struck us most was the
uncertainty when imputing for missing data
personal vulnerability the honorees were
was the problem Scheuren asked Rubin to
willing to expose in order to share the
tackle, admittedly in another context 30
NOVEMBER 2008 AMSTAT NEWS 5
AMSTAT November 08.indd 5 10/24/08 2:27:36 PM
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