the contact
of reason
with nature
henry margenau
.
ambiguity of language is
philosophy's main source of
problems. that is why it is of
the utmost importance to examine
attentively the very words we use
giuseppe peano 1858-1932
.
i see no greater impediment to scientific progress
than the prevailing practice of focusing all of our mathematical
resources on probabilistic and statistical inferences
while leaving causal considerations to
the mercy of intuition and
good judgment
judea pearl / causality 2000
.
. .
it would be tempting
to investigate only absolute
measurable spaces contained in the
real line, which has been extensively done
this would be fine if one is interested only in
say, measure theoretic or set theoretic properties
of absolute measure spaces, but clearly inadequate
if one is interested in topological
or geometric structures
togo nishiura / absolute measurable spaces 2008
. .
.
in the 1860s
a small group
of young english
intellectuals formed
what they called the x club
the mathematical symbol for the unknown
and the plan was to meet for dinner once a month and let
the conversation take them where chance would have it
the group included darwinian biologist thomas huxley
and the social philosopher herbert spencer. one evening
about 1870 they met for dinner at the athenaeum club
in london, and that evening included one exchange
that so struck those present that it was repeated
on several occasions. statistician francis galton
was not present at the dinner, but he heard
separate accounts from three men who
were and he recorded it in his own
memoirs. as galton reported it,
during a pause in the conversation,
spencer said "you would little think
of it but i once wrote a tragedy"
huxley answered promptly
"i know the catastrophe"
spencer declared
it was impossible for
he had never spoken about
it before then. huxley insisted
spencer asked what it was
huxley replied
"a beautiful theory
killed by a nasty, ugly little fact"
sm stigler "the epic story of maximum likelyhood" stat sci 9.2007
.
. .
.
precise and accurate
[unbiased and low variance]
precise but inaccurate
[biased but low variance]
imprecise and inaccurate
[biased and high variance]
imprecise but accurate
[unbiased but high variance]
since we're already here, bimodal distribution
["a mixture of 2 gaussians already invalidates expectation maximization" - v vapnik]
how to wound fisher, nyeman, pearson and wald with one quiver
[uncorrelated but high mutual information]
all graphics programmed with mathematica 6
.
. .
.
i come
to bury sigma
not to praise it
sam l savage / the flaw of averages, 2009
.
. .
a rigorous
definition of the
components of the information
specifying their number, level and length
must precede any graphic construction
jacques bertin / "semiology of graphics: diagrams, networks, maps" 1983
.
a graphic is not "drawn" once and for all
it is "constructed" and reconstructed
until it reveals all the relationships
constituted by the interplay of
data. it is never an end in
itself; it is a moment
in the process of
decision-making
j bertin /Êgraphics and graphic information processing, 1981