Comments on: Did I See this Item in a New York Times Headline?

By: When amoxicillin works for acne.

When amoxicillin works for acne. — Thu, 13 Aug 2009 14:51:52 +0000

Amoxicillin….

Amoxicillin. Amoxicillin clavulanic acid suspension. Infant amoxicillin reactions….

By: Hammer

Hammer — Mon, 29 Sep 2008 09:52:04 +0000

Jay: That is a very good point, and a somewhat surprisingly common issue in many fields of study. Not just with statistics, but rather the borrowing of concepts and ideas from other fields and applying them without understanding them is common across all fields it seems.
I just got done spending a weekend with a buddy of mine who is a PhD candidate in English analytics (or something along those lines.) We spent a good bit of time talking about how his professors use economic ideas to define models for the exchange of ideas, using Marx as a base. Needless to say, the economics part of their theories was WAY off base, though I can't speak to the rest.
Amusingly, I am reading Origins of Wealth which describes as the first part how economists borrowed a lot of ideas from physics to come up with the supply/demand model of equilibrium, but did so at a time just before entropy was well understood. The result was that economics labored under a really awkward and inaccurate model set for a long time, as dynamic systems were outside their reach.

I suppose the take home message here is "don't try and wing it yourself; actually get a professional in the field you are working in to help your project." One would think that with all the different proffessors at universities this wouldn't be an issue...

By: Jay

Jay — Fri, 26 Sep 2008 22:12:53 +0000

Taleb:

Are we using models of uncertainty to produce certainties?

This masquerade does not seem to come from statisticians—but from the commoditized, "me-too" users of the products. Professional statisticians can be remarkably introspective and self-critical. Recently, the American Statistical Association had a special panel session on the "black swan" concept at the annual Joint Statistical Meeting in Denver last August. They insistently made a distinction between the "statisticians" (those who deal with the subject itself and design the tools and methods) and those in other fields who pick up statistical tools from textbooks without really understanding them. For them it is a problem with statistical education and half-baked expertise.

By: Rudy

Rudy — Fri, 26 Sep 2008 13:05:03 +0000

Come on guys, the government is in a time of massive bailouts. The temperature has to be cooling off now in order for more money to go that cause!!

By: gappy

gappy — Fri, 26 Sep 2008 12:00:15 +0000

The same point has been made in a recent review of Friedman's "Hot, Flat and Crowded" by Bjorn Lomborg on WSJ. I think that Lomborg's Copenhagen Consensus is a good initiative and, since there are disagreements, the most reputed climatologists and economists of a different persuasion should be brought in (but no Quiggins or post-autistic economists, please) to allay any objections about partisanship.

I have a question for Don. I think that the problem is best analyzed from a cost-benefit analysis viewpoint. Does he agree? I am asking because his colleague and intellectual mentor J Buchanan is against this approach.