Comments on: Jacoby #1: A "Few Good" Series

By: La blogosfera limpia la muy sucia “ciencia del cambio climático”. « PlazaMoyua.com

Sat, 09 Jun 2012 05:37:53 +0000

[...] McIntyre [-->] [...]

By: La llaman ciencia, pero no es replicable – ni verdad. « PlazaMoyua.com

Thu, 07 Jun 2012 20:43:14 +0000

[...] reconocidos torpes en estadística. Unos ejemplos de la descripción del problema por: McIntyre [-->] Stockwell [-->] Stockwell [-->] Jeff Id [-->] Jeff Id [-->] Motl [-->] Lucia [...]

By: Myles Allen Calls For “Name and Shame” « Climate Audit

Myles Allen Calls For “Name and Shame” « Climate Audit — Fri, 01 Jun 2012 02:11:16 +0000

[...] discussed the screening fallacy (not by that name) in early CA posts e.g. here, as a criticism of Jacoby’s selection of the 10 “most temperature sensitive” [...]

By: Schmidt’s “Conspiracy Theory” « Climate Audit

Schmidt’s “Conspiracy Theory” « Climate Audit — Wed, 16 May 2012 22:06:33 +0000

[...] sites. Jacoby refused in a truly remarkable letter, reported on in one of the very first CA posts here. The following is a lengthy excerpt, see the link for the full letter): The inquiry is not asking [...]

By: TCO

TCO — Sun, 11 Sep 2005 20:46:14 +0000

The jarhead’s paper should not have been accepted. The reviewers should have asked the obvious question you are asking. (Doesn’t take reworking the problem).

But really the answer is to resample. And don’t give me any crap about not knowing his locations. Sample new trees. This is not just about exposing individual’s dissembling, but about showing that the as-reported science is incorrect.

By: TCO

TCO — Tue, 09 Aug 2005 15:12:26 +0000

If you really want to resample, pick your own site. Have a person in the field (presumably the one who will do the sampling) advise on relevant conditions (to make it meaningful). If your results differ, you won’t be able to determine what mistake was made in the earlier work. But you will be able to show that a seperate (good) study came up with a different answer.

By: Steve McIntyre

Steve McIntyre — Tue, 09 Aug 2005 14:57:26 +0000

The only reason that has been provided is whether the data has an upward 20th century trend. But if you have highly autocorrelated data, a certain percentage will have trends just from the statistics. The issue become statistical and you need to see all the data – just as mining promoters have to report bad drill holes and drug companies have to report cases where the drug didn’t work. There is NO justification for Jacoby’s behavior and the acquiescence of all levels of climate scientists (journals, NSF and peers) is a disgrace. He’s refused to even identify the location of the Gaspe site, when I wanted to arrange for re-sampling.

By: TCO

TCO — Tue, 09 Aug 2005 14:47:10 +0000

A few good men is a rational policy if the reasons for data exclusion make sense. If you exclusde data because you can prove a confounding factor, then that is reasonable (although including it and doing multiple regression might still be superior). However, if you exclude the data because they don’t fit the story, then that is not reasonable. Of course if that is happening, one may never see it (for instance if there is not throwarw comment about the 36 sites looked at). In this case, the only way to go after it is to replicate experrimental work.

By: fFreddy

fFreddy — Sat, 02 Jul 2005 15:30:13 +0000

Sorry, that referes to the “Hockey Team” link at the top.

By: fFreddy

fFreddy — Sat, 02 Jul 2005 15:24:53 +0000

You have to wonder what he perceived as his mission. The strong implication was that it was to achieve the hockey-stick result. His colonel should explain to him that a scientist’s task is to find the truth, whatever it may be.
As of 2 July, the link is not working again.