The Amelioration of Uncertainty

Was “Statistical zealots” copied from an old letter?

Recently Jeff Leek over at Simple Statistics posted what I though was an original discussion about Statistical Zealotry. But then I saw this newly unearthed letter from an unknown European Professor to a colleague. It’s at least 300 years old, but the similarity with Leek’s post are so strong it makes one wonder if it weren’t plagiarized. It’s reproduced below for your comparison:

Yesterday while lecturing on Natural Philosophy one of the students professed this gem:

“So, while I can imagine there are good geocentrists out there predicting planetary motions with epicycles, I insist that epicycles are bogus.”

This is the extension of a long standing debate about the relative merits of geocentrism and heliocentrism methods. It is interesting that I largely only see one side of the debate being played out these days. The heliocentrism zealots have it in for the geocentrism in a big way. The university is one example, but there are more. Interestingly, even Rene Descartes is getting in the game.

I think it probably deserves a longer letter but here are my thoughts on astronomical zealotry:

(1) User effect > Philosophy effect. The person predicting a planetary path probably matters more than the philosophy. I would prefer Newton predict Mars’s position in the night sky more than a lot of astrologers. Similarly, I’d prefer that Ptolemy predict Saturn’s position than a lot of scribes.

(2) I agree with my drinking buddy that this is likely mostly a philosophy battle than a real practical applications battle. Both Epicycles and Newton’s Laws successfully predict the motions of heavenly bodies.

(3) I like Professor Longforgotton’s idea that we should move away from heliocentric vs. geocentric to pragmatism. I think most real applied astrologers have already done this, if for no other reason than being pragmatic helps you get things done.

(4) Papers like this one by Galileo that claim total victory for one side or the other all have one thing in common: they rarely use real data to verify their claims. The real world is messy and one approach never wins all the time.

My final thought on this matter is: never trust people with ideas bearing evidence.

The similarities are uncanny.

For my own part, I’ll just echo pretty much every legendary mathematician and physicist that ever lived and say that there are few things less practical in the long run than pragmatists.

November 28, 2013
9 comments »
  • November 29, 2013Juanjo Medina

    Unsavory indeed. But it wasn’t the only reason why reading it left me with a bad aftertaste. Funny enough I just read this (https://tinyurl.com/ngx9m59) immediately after when checking the daily press.

    This op-ed piece on digital vigilantism helped me to understand why (apart from the implications) I did not particularly enjoy reading the entry. As The Guardian journalist notes:
    “the fact that someone accused another of having done something wrong has never been enough to warrant an attack. At the very least, you are required to get the other side of the story”.

    So whether we agree ot not on the similarities it would have been nice for your to contact Jeff Leek first to get his side of the story. Apart from that you may want to add the full reference for the letter.

    BTW, I have no personal links with Jeff Leek.

  • November 29, 2013Joseph

    Medina,

    Leek didn’t really crib from a 300 year old letter full of historical anachronisms and modern English idioms. So I don’t think he’s crying in his cornflakes over my exposing his “source”.

  • November 29, 2013Rasmus Bååth

    I got further through the letter than I want to admit before I realized it was fake…

  • November 29, 2013Joseph

    Rasmus,

    I didn’t consider non-native English speakers, for whom it’s probably more subtle then it seems to my eyes. Especially since I’d had thought there were only the same 8 people reading this blog.

    It’s funny though that a Marine has to defend the importance of understanding the foundations of Statistics correctly from an Academic. Shouldn’t it be the other way around?

  • November 29, 2013Juanjo Medina

    Ouch. V funny. It will teach me not to believe everything I scan. And to actually read rather than scan.

  • November 29, 2013Rasmus Bååth

    Nah, I got it and enjoyed it :) (And for sure you blog has plenty of readers!)

    What I don’t like with the argument in “Statistical Zealotry” (and I’ve heard it many times, “I use what works (for me)” ) is that it conserves the frequentist status quo since “I use what works” often means “I use what I’m used to”. Since I believe that if people grokked Bayesian methods they would find them much more useful and logically coherent it is extremely irritating to find this in most PsychStats book:

    “In conclusion, none of the views of probability is completely adequate. Because
    they are all useful and they are not incompatible, they coexist amicably in the math-
    ematician’s bag of conceptual tools. The discussion that follows relies most on the
    classical and empirical views.”

    (From: http://www.amazon.com/Statistics-Introduction-Roger-E-Kirk/dp/053456478X)

    That is, they “teach the controversy” but eventually side with the less useful view of probability…

  • November 29, 2013Joseph

    Well I’m about a thousand light years away from influencing what is taught, who gets published, who gets hired, or who gets grants in the statistical sciences. I don’t think it makes much difference because most academics are just wasting everyone’s time anyway.

    But I do think all the big advances in the future are going to originate from the Bayesian line. Anyone not thinking hard about the foundations of statistics is doomed to merely make epsilon improvements to the present crap.

    Many people are happy enough to do that, but I’m not. I think being a standard issue statistician today is boring as hell and I can’t imagine what attracts people to this tedium. If I thought for a minute that was my fate, I’d get a job teaching surfing lessons and forget I’d ever heard about statistics. The only reason to care about the subject is because the Laplace-Jeffries-Jaynes line points to a much more interesting future.

  • November 29, 2013Brendon J. Brewer

    You’ve got to be the best probability-related satire writer on the web.

  • December 5, 2013Daniel Lakeland

    “It’s funny though that a Marine has to defend the importance of understanding the foundations of Statistics correctly from an Academic”

    well, the Marines are part of the Department of Defense after all. If you ever do decide to get a PhD just make sure your committee knows that you WILL be armed at the Thesis Defense ;-)

Leave a Reply or trackback