|
This page is a fragment of a dictionary of received ideas of statistics.
Many of the original entries were composed one conference evening after too much wine.
More recently it has become a commonplace book to record observations of others, see
nostrification.
It is obviously modeled after Flaubert's famous compendium
but inevitably is only the palest shadow of the work of Le Maître.
As a restorative you can find a scanned version of Flaubert's Dictionary
in English.
For the original:
en français.
Aristotle: Claimed you can fill space with regular tetrahedrons, but you can't.
Don't mention horses teeth, or any Bacon.
Arithmetic: has four branches, citing the Mock Turtle, Ambition, Distraction,
Uglification and Derision.
Bayesianism: Like Marxism, better in theory than in practice.
Don't forget to mention Matthew Prior's (!) (1664-1721) meta-satirical poem,
The hind and the panther transvers'd to the story of The country-mouse
and the city-mouse,
Bayesians: Ask: How should one compute the discounted expected utility
of one's afterlife? See Pascal's wager. With some trepidation, quote Maurice
Kendall: "I have lamented that Bayesian statisticians do not stick closely
enough to the pattern laid down by Bayes himself: if they would only do as
he did and publish posthumously we should all be saved a lot of trouble."
[On the Future of Statistics -- A Second Look, JRSS(A), (1968), 131, 182-204].
Casual Empiricism: cite Virgil, "ab uno disce omnes", from one example all
is revealed.
Causal Inference: see Casual Empiricism.
Causality: Quote Strotz and Wold: "No one has monopoly rights in defining 'causality.'"
or Betrand Russell: "The law of causality ... survives, like the monarchy, only
because it is erroneously believed to do no harm." See DiD
Chance: Ask what does "a 40 percent chance of rain" mean in Iowa? Also mention
the fabulous painting
"Allegory of Fortune" by the 16th century Ferrarese master Dosso Dossi.
Coin-flipping: the real foundation of probability, see the opening scene of
Rosencrantz and
Guildenstern Are Dead. Mention that Doob and Feller settled the question
of whether to use the term "random variable" and "chance variable" by the
flip of a coin. Consider also the grook:
A Psychological Tip
Piet Hein
Whenever you're called on to make up your mind,
and you're hampered by not having any,
the best way to solve the dilemma, you'll find,
is simply by spinning a penny.
No -- not so that chance shall decide the affair
while you're passively standing there moping;
but the moment the penny is up in the air,
you suddenly know what you're hoping.
Co-median: the median of a distribution, F, is usually defined,
in accordance with cadlag conventions,
as the infimum of the set of values, S = {x | F(x) >= 1/2}.
This is the smallest value that minimizes E |X - mu|.
When there are several minimizers of this expectation we may refer
to the other (larger) ones as co-medians. [See Stigler (1977, Fractional Order
Statistics), note added March 2013, I thought this was my joke, but it turns
out I was just recycling Stigler.]
Confidence: What science wants, and the statistician lacks.
Mention that EB Wilson (JASA, 1927) was the first to insist that random (confidence)
intervals cover the true parameter with some probability, rather than that a random
parameter lies in fixed interval with some probability. No less than Milton Friedman
seemed confused about this point, see Neyman's (1938) Lectures and Conferences on
Mathematical Statistics, p 145.
Cooking: is to Chemistry as Statistics is to Mathematics, cite Speed (1986) Questions
Answers and Statistics, but don't forget to mention that "Much depends on dinner."
Or, "Cooking is become an art, a noble science; cooks are gentleman" Titus Livius (Livy)
quoted by Knuth in the preface to Volume 3 of AoCP.
Conservative: quote Oakeshott, "To be conservative ... is to prefer the familiar to the unknown, to prefer the tried to the untried, fact to mystery, the actual to the possible, the limited to the unbounded, the near to the distant, the sufficient to the superabundant, the convenient to the perfect, present laughter to utopian bliss." In other words to disdain progress and discovery.
Correlation: isn't causation, it is a Gaussian delusional conspiracy by globalists. Or say,
its just a cosine, why all the fuss? Cosiness is what we are all searching for.
cryptography: Useless to others is the essense of
DiD: The grammar of Pearl's do-calculus (and its past tense did) is tough. Quote Colm Toibin's
novel "The Magician" channeling Thomas Mann and his wife Katia on trying to learn English
after coming to the US.
'This "did"', Thomas said, will be the end of me. You can actually
say "he did do" and then the opposite is "he didn't do". No
wonder the English are so warlike. 'What about "does"?' Katia asked.
'Should it not be "do"?' he asked. 'It's both. And then there are phrasal verbs,'
Katia said. "I have ordered a book on them."
Education: Quote Deng Xiaopeng: "Execution is an indispensible means through
which to educate the masses."
Economics: Chicago Style -- cite Harry Johnson: Science demands the submergence of
social conscience in a welter of statistical squabbles. (cited by Griliches JPE, 1979)
See intelligence. Mention Marx's complaint that no one had written so much about money
and had so little of it, and that "this economic crap" was keeping him from writing his
big book on Balzac. (Eagleton, LRB 29 June 2023.
Econometrics: Mention Stefan Valavanis's (1959) textbook characterization:
"Econometric theory is like an exquisitely balanced French recipe, spelling out precisely with how many turns to mix the sauce, how many carats of spice to add, and for how many milliseconds to bake the mixture at exactly 474 degrees of temperature. But when the statistical cook turns to raw materials, he finds that hearts of cactus fruit are unavailable, so he substitutes chunks of cantaloupe; where the recipe calls for vermicelli he uses shredded wheat; and he substitutes green garment dye for curry, ping-pong balls for turtle's eggs and, for Chalifougnac vintage 1883, a can of turpentine."
Economist: Quote Ginger Baker, "Brian [Jones] was much more of a musician
than Jagger will ever be — although Jagger’s a great economist."
Endogoneity: Ask who put the dodgy in it.
Error: Cite Pareto: "Give me fruitful error anytime full of seeds, bursting
with its own contradictions. You can keep your sterile truth for yourself."
ESP: Quote Mosteller "If there is ESP, that is exciting. However, thus far
it does not look as if it will replace the telephone." (1991 Stat. Science)
Eugenics: produced the tasteless, square tomato; mention male pattern
dumbness, or the comment by Karlin about I.J. Schoenberg who married the daughter
of the eminent mathematician Edmund Landau and thus became a true example of the
"established genetic principle" that mathematical talent is an inheritable trait
usually transmitted from father to son-in-law. [J. Approx. Theory, 1973]
Elicitation: see tuning parameter, mention Tom Sawyer's method of painting
fences -- find someone else to do your dirty work.
Evidence: Quote the Venerable Sherlock Holmes: "I see no more than you
but I have trained myself to notice what I see." Or Richard Pryor: "Who
are you going to believe, me, or your lying eyes." Or the Soviet maxim,
"He lies like an eye witness."
Finance: the alchemy of modern science.
Fun: as interuption, cite Gelman's blog entry about a 2007 talk by Sarah Igo
about her book The Averaged American, who commented that "when she speaks
to historians, they just let her speak, but we’re more fun because we interrupt
her frequently". Gelman assured her that if interruption=fun, then economists
are the most fun of all…
Gambling: mention Aldous Huxley's comment, "...the relation between craps
and Reality is a real one", letter of December 1969, cited in OED.
Or quote Samuelson: "When I go to a casino, I go not alone for the dollar
prizes but also for the pleasures of gaming -- for the soft lights and sweet music."
(Econometrica, 1952, p 671).
Gauss: mention J. L. Bernstein's advice, "it is wise to degauss the heads
prior to each recording session." Cited in the OED.
Gödel: quote Regis Debray, "Ever since Gödel showed that there does not exist a proof of the
consistency of Peano arithmetic that is formalizable within that theory (1931), political
scientists had the means for understanding why it was necessary to mummify Lenin and
display him to the ‘accidental’ comrades in a mausoleum.”
History: Statistics with small samples. Cite Mark Twain, "History doesn't
often repeat itself, but it rhymes."
Iidly: as in "drawn iidly" --drawn as independent and identically distributed,
that is somewhere between idly, and idyllically, although we shouldn't discount
the Freudian connotation "drawn by the Id." See independence.
Image Processing: Suggest the sphinx as an example of image denosing.
Index: Finding your name in the index is a shortcut to reading a new book. Quote
Jonathan Swift: "... to pretend to understand a book by scouting thro' the Index, is
as if a Traveller should go about to describe a Palace, when he had seen nothing
but the Privy."
Inequality: The toolbox of mathematics is filled with them. Quote GH Hardy:
"A science is said to be useful if its development tends to accentuate the existing
inequalities in the distribution of wealth," (A Mathematician's Apology, p 120),
but note that he later called this remark -- only an excusable rhetorical flourish
of 1915.
Independence: The great superstition of probability theory. See Kac's
Statistical Independence, and marvel at the apparent sophistication of
the Haverford undergrads in the audience. See also iidly.
Intelligence: Cite GB Shaw, "it is the mark of a truly intelligent person to be moved
by statistics," then offer an award for an explicit citation, since it seems to more
plausibly attributed to Betrand Russell. See economics.
Kernel: Ask, What is the cannonical one? In statistics, say kernel density estimation
is like making a martini: you have your gin -- that is the empirical df, then you add
noise -- that is the vermouth, finally you stir -- that is the convolution. Sip slowly
while arguing about the bandwidth -- the amount of vermouth.
Kolmogorov: Thought that every single discovery should fit in a four-page
Doklady note, since "the human brain is not capable of creating anything more
complicated at one time." quoted in http://homepages.cwi.nl/~paulv/papers/kolmogorov.pdf.
Might also mention Michael Frayn: "if your vita turns out to be reasonably longa,
as mine has, then to compensate your ars gets naturally more brevis." Observer, May 3, 2020.
Liberal: see conservative.
Literature: Statistics with falsified data.
Love: Brownian emotion.
Markov Chains: Quote le Carre, I mean childhood, at my age, is no excuse for anything.
MCMC: Mention that importance sampling was invented by Herman Kahn, the model for Dr. Strangelove
in Kubrick's movie of the same name. And don't forget that Edward Teller, another candidate
for Dr Strangelove, was a coauthor of the Metropolis paper. Both Kahn and Teller are members
of that exclusive club of people without which the world would have been a better place.
Martingale: In France mention Rabelais' socks, citing the OED.
Mathematics: What comes after arithmetic. Quote Kolmogorov: At any given moment
there is only a fine layer between the trivial and the intractable. Mathematical
discovery takes place in this layer. (diary, 14 September 1943) Should be useless
according to GH Hardy, see cryptography.
Median: is the message.
Mixtures: cite Larry Wasserman: "I have decided that mixtures, like tequila,
are inherently evil and should be avoided at all costs."
... leaving a gap in the literature filled by Kiefer and Wolfowitz (1956).
Moments: mention Tukey's "misty staircase," or say "quantiles are moments too,
of a sort." Or more in the spirit of Flaubert citing Voltaire,
Moments are like God, if they didn't exist, it would be necessary to invent them.
Pearson's method of moments should not be confused with the method of emoluments
which has emerged as the dominant mechanism of modern political economy.
Normal: Mention Stigler's comment, "a rare one-word oxymoron". see also Gauss.
Nostrification: cite Constance Reid's biography of Courant: The Gottingers had a facetious
expression for the process of making someone else's ideas one's one. They called
it "nostrification." There were many levels of the process: "conscious
nostrification" -- "unconscious nostrification" -- even "self-nostrificaiton."
This last occurred when one came up with a marvelous new idea which he later
discovered had already appeared in earlier work of his own.
Ontology: mention that the Peggy Lee song "Is that all there is?" written by Leiber and
Stoller was inspired by the Thomas Mann (1896) short story "Disillusionment."
p-value: Mention the meta-fictional treatise: Shame and the p-value. See evidence.
Paper: An obsolete technology of academic communication, replaced by vapor, as in
"I finished a vapor on X yesterday and submitted it to arXiv." When subjected to
increased pressure, may turn into a liquid.
Pascal's Wager: quote Diderot, "Any Imam could just as well reason the same way."
Poetry: is about incidental parameters, everything else is about distributions.
Poker: Quote Robert Pinsky quoting Walter Matthau (!) "Poker exemplifies the worst
aspects of capitalism that have made our county so great."
Prices: Say Kantorovich called them "expedient values" to avoid trouble with
officials at Gosplan. Boldyrev and Duppe (BJHS, 2020)
Probability: Flip a coin for DeFinetti or Kolmogorov versions, see Chance.
Quote Borel late in life: "Je vais pantoufler dans les probabilité",
and if the verb isn't
sufficiently clear quote Larousse: "Pour un fonctionnaire, en particulier pour
un ancien élève des grandes écoles, quitter le service de
l'État pour celui d'une entreprise privé."
Or quote Morris DeGroot commenting on IJ Good's theory of (hierarchical)
"woolly probabilities: "I suppose that Poisson probabilities are woolly
because their mean is lambda." [Trabajos de estadística y de investigación
operativa, 1980]
Professor: Quote Auden: Someone who talks in someone else's sleep.
Proof: Some day soon they will all be checked by machine, useful as an aide memoire
for what is claimed by the theorem. Mention Larry Shepp, who when confronted with
an earlier version of one of his results responded, "yes, but when I proved it,
it stayed proved." see Nostrification.
Publish: or perish. If possible, follow the advice of Gian-Carlo Rota
"Publish the same result several times: ...
Riesz would publish the first rough version of the idea in some obscure Hungarian journal.
A few years later he would send a series of notes to the French Academy's Comptes Rendus
in which the material was further elaborated. A few more years would pass, and he would
publish the definitive paper, either in French or in English." [Indiscrete Thoughts],
advice only available to the multi-lingual. See nostrification. On what to publish
cite Halmos (AMM, 1975): "A striking criterion for how to decide not to publish something
was offered by my colleague John Conway. Suppose that you have just finished typing a paper.
Suppose now that I come to you, horns, cloven hooves, forked tail and all,
and ask: if I gave you $1000.00, would you tear the paper up and forget it?
If you hesitate, your paper is lost - do not publish it. That's part of a more
general rule: when in doubt, let the answer be no." Don't forget to update the cash allowance
to current dollars.
Quantiles: Are moments too, of a sort.
R: what comes after Q. Quote Virginia Woolf (To the Lighthouse):
"It was a splendid mind. For if thought is like the keyboard of a piano,
divided into so many notes, or like the alphabet is ranged in twenty-six
letters all in order, then his splendid mind had no sort of difficulty in
running over those letters one by one, firmly and accurately, until it had
reached the letter Q. He reached Q. Very few people in the whole of England
reach the letter Q.... But after Q? What comes next?... Still, if he could
reach R it would be something. Here at least was Q. He dug his heels in at
Q. Q he was sure of. Q he could demonstrate. If Q then is Q--R--.... "Then
R..." He braced himself. He clenched himself....
"...In that flash of darkness he heard people saying--he was a failure--that
R was beyond him. He would never reach R. On to R, once more. R---....
"...He had not genius; he had no claim to that: but he had, or he might have
had, the power to repeat every letter of the alphabet from A to Z accurately
in order. Meanwhile, he stuck at Q. On then, on to R."
Random Numbers: Mention von Neumann's comment: "Any one who considers arithmetical
methods of producing random digits is, of course, in a state of sin." as quoted by
Knuth, ACP:V2.
Refereeing: Mention that Dante, who missed out on the experience of
peer review failed to anticipate the overcrowding of purgatory while St Peter
tried to work through his backlog of "refereeing of souls."
Regression: is demeaning.
Robustness: Burned with such intensity that, like Marxism-Leninism,
only the ashes of the most pure remain.
Simulation: What makes statistics an experimental science. See Random Numbers.
Description of the results of simulation experiments is called dissimulation.
Ask: Have you read Francis Bacon's essay "Simulation and Dissimulation?"
Smoking: Say R.A. Fisher found it healthy and became wealthy.
Statistics: The (futile) attempt to offer certainty about uncertainty.
Cite Kafka, "I have reached the stage that I no longer desire certainty."
Structural estimation: see strictural estimation.
Strictural estimation: estimation subject to one or more strictures,
cite OED -- " There is no strictural obstruction to the progress of the
faeces." J.M. Duncan (1886).
tenure: say Thorstein Veblen is the patron saint of the untenured, having
been forced to resign at booth University of Chicago and Stanford, and resigning
voluntarily from the University of Missouri without having tenure. One could
also nominate C.S. Peirce who after finally getting a lecturer position at
Hopkins was, like Veblen, force to resign for traveling with a woman who was
not his wife.
Test: Quote "Joe" the CIA's chief "expert" on Iraq's aluminum
tubes and their potential role for WMD, testifying in Congress on
why he didn't consult Energy Department experts on the subject:
"Because we funded it. It was our testing. We were trying to prove some
things that we wanted to prove with the testing." (NYTimes, Oct 3, 2004).
Mention that in sequential analysis this is called testing to a
foregone conclusion.
Tukey: "never estimate intercepts, always estimate centercepts!"
Quote von Neumann's comment: "There is this very bright
graduate student, and the remarkable thing is that he does it all on
milk." (Brillinger's (2002) obituary in the AMS Notices.)
Tukey on Friedman: Milton was well acquainted with the statistical side
and very sharp. Probably easier to cut yourself on him than anybody else in
the Biometric Society or the Institute [of Advanced Study.]
Tuning parameter: What the Bayesian call the "degree of belief in the prior",
say neither frequentists or Bayesians know how to select them.
Truth: see error. Ask: is it true that Somerset Maugham coined the
the phrase "Nothing is too rum to be true"? Corde says, "I heard it
years ago on a Channel train from an old English gentleman. He was
a lifelong atheist, but maybe God did exist, he said." Saul Bellow,
Dean's December.
University: The soft underbelly of capitalism, or cite Veblen's The
Higher Learning in America, originally subtitled "A Study in Total Depravity,"
or say, "higher education -- the highest form of money laundering."
Writing: mention Geoff Dyer: "a way of postponing the day when I won't do it
any more, the day when I will sink into a depression so profound it will be
indistinguishable from perfect bliss."
|
