People who are published in newspapers who don’t make proper use of published data


“Pundits are regularly outpredicted by people you’ve never heard of. Here’s how to change that.”
is a very interesting article at the monkey cage by Sam Winter-Levy and Jacob Trefethen.
(h/t @MarkThoma)

They note a study of people you’ve never heard of vs intelligence analysts (not pundits) and write

accountability. While many pundits may not see themselves as being in the business of making forecasts, implicit predictions underpin much of what they write. It seems strange then that we know more about the accuracy of the predictions of Bill Flack, a superforecaster and retired irrigation specialist from Nebraska, than we do about the predictions of Paul Krugman or Bret Stephens.

I don’t know who Bret Stephens is, but note that Winter-Levy and Jacob Trefethen decided to type “Paul Krugman” without mentioning any forecast made by Paul Krugman. They don’t discuss evaluation of the accuracy of Paul Krugman’s forecasts. I assert with great confidencethat they didn’t google Paul Krugman forecast accuracy. I am also sure that they didn’t google Paul Krubman forecast accuracy (as I did — I don’t type so good)

My comment

It may be true that we know more about the accuracy of Bill Flack’s forecasts than of Krugman’s but Krugman’s ability to forecast has been graded. The sample was small, forecasts made on TV, but Krugman didn’t make any incorrect forecasts.

This is publicly available information. google Krugman forecast accuracy and find
https://www.hamilton.edu/documents/Analysis-of-Forcast-Accuracy-in-the-Political-Media.pdf
or if you don’t want to bother with a pdf the second hit
http://www.poynter.org/news/mediawire/130485/claim-krugman-is-top-prognosticator-cal-thomas-is-the-worst/

I think that you really must note this scrap of data in an article about evaluating forecast accuracy in which you chose to name Krugman. Are you aware of the study ? If so, why didn’t you mention it. If not what does that tell us about your ability to handle publicly available data ?

I think your article shows us something about the ability to deal with publicly available data of people who are published in newspapers (including yourselves) and people no one has heard of (including me).

I mean really, would it have been too hard to google ?

Interestingly, this isn’t yesterday’s only post at The Monkey Cage which includes the words Paul and Krugman. Nor is it one which suggests the most ignorance.

I think the staff of The Monkey Cage (including the editor equivalent if there is one) have to have a talk about the proper use of the word “Krugman” which includes two principles

1) watch out for Brad DeLong and his friends (or in other words Krugman’s acolytes and his acolytes’ acolytes)
&
2) Paul Krugman is right surprisingly often.

I am not joking at all.