I'm at a conference with some statisticians at this moment. One talk
today discussed a recent paper in Nature which alleged that the
Chixculub meteor had a certain origin with probablity 90%. The gist of
the talk was that the professional statistician was unable to ascribe
enough meaning to the 90% claim to refute it.
Admittedly he was a "frequentist"; I had no idea how seriously people
take this division, but as a marginally statitistically educated
person with Bayesian sympathies, he left me unable to ascribe much
meaning to it myself.
Statistical attribution was always a red herring.
Global change isn't a drug trial and we can't round up 500 planets to
give half of them CO2 and half a placebo to get a 99% refutation of
the null hypothesis. We actually have to think, not just apply
formulas.
mt
On 9/10/07, James Annan <[EMAIL PROTECTED]> wrote:
>
> William M Connolley wrote:
>
> > you can do sig tests to show that the change is not likely due to chance
> > (cue
> > JA...
>
> ...who will observe that significance tests can never answer questions
> like "was it due to chance" (or not), but only questions like "how
> likely is it that observations as extreme as these would arise in a
> hypothetical world with no forcing"?
>
> Which is not the same thing at all.
>
> Here closeth the parenthesis.
>
> :-)
>
> James
>
> >
>
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups
Global Change ("globalchange") newsgroup. Global Change is a public, moderated
venue for discussion of science, technology, economics and policy dimensions of
global environmental change.
Posts will be admitted to the list if and only if any moderator finds the
submission to be constructive and/or interesting, on topic, and not
gratuitously rude.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at
http://groups.google.com/group/globalchange
-~----------~----~----~----~------~----~------~--~---
