Re: Cohen's Observation

[BERNARD L COHEN <blc+@PITT.EDU>]

	Let me explain again why I need concrete hypothetical examples of

what can be wrong with my treatments. My papers contain many examples of

what could possibly explain my results. For example, according to Table 2

of Item #7 on my web site, the existence of an unrecognized confounding

factor which has a correlation of 0.75 with both radon levels and lung

cancer rates, would do the job. But in the accompanying discussion, I show

that such high correlations are extremely implausible. Plausibility of

correlations is a very important aspect of my reasoning.

	It is impossible to address the issue of plausibility without a

concrete example. That is why I need a concrete example. It can be made

up (i.e. hypothetical), and there is no need to show that it is valid. It

is then up to me to evaluate its plausibility, and it is that evaluation

that I would like to see judged by an arbitrator.

	It is this need for a concrete hypothetical example that prompted

me to offer an award for one that I could not show to be implausible in

the judgment of an impartial arbitrator. For an arbitrator on my

procedures, without a concrete hypothetical example, I would require a

theoretical physicist; but for an arbitrator over a concrete example, I

would accept any scientist willing to engage in a few back-and-forth

exchanges with me.



Bernard L. Cohen

Physics Dept.

University of Pittsburgh

Pittsburgh, PA 15260

Tel: (412)624-9245

Fax: (412)624-9163

e-mail: blc@pitt.edu

web site: http://www.phyast.pitt.edu/~blc



On Fri, 20 Jun 2003 epirad@mchsi.com wrote:



> > >  My argument with you is that such a blunt instrument as

> > > an ecologic study should not be used to test the validity of the LNT.

> >

> > 	--If it is a blunt instrument, why can't you make up a concrete

> > hypothetical example of how that bluntness can explain my results?

> >

> I have answered this question many times including in the papers and letters we

> wrote in Health Physics regarding your work.

>

>

>

>



************************************************************************

You are currently subscribed to the Radsafe mailing list. To unsubscribe,

send an e-mail to Majordomo@list.vanderbilt.edu  Put the text "unsubscribe

radsafe" (no quote marks) in the body of the e-mail, with no subject line.

You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/