Re: Confounders and Coincidences

["Jerry Cohen" <jjcohen@PRODIGY.NET>]

Otto,

    As I recall, there was a British study several years ago that included a

multiple regression analysis on cancer etiology. One surprising result was

that  there appeared to be a strong negative correlation between cancer

incidence and the consumption of fried foods. Of course, this result was

considered absurd and dismissed as anomalous. It was  assumed that

confounding factors were the cause of this apparent relationship, although

no serious effort was made to identify those factors. Apparently KFC

took no position on the matter.

    I know it is not the same thing, but I hope that Bernie's radon findings

do not meet the same fate.  I fear that NCRP  investigating the matter is

like assigning a fox to guard the chickens.  When you think about it, isn't

much of their status and prestige vested in acceptance of LNT. It seems that

it would take an awful amount of courage for them to recant a position that

they have held for decades, not to mention all the money and effort that may

needlessly have been expended pursuant to LNT.

    In any case, as was discussed in previous messages on radsafe, all

epidemiologic studies up to and including those relating smoking to

lung cancer could be discounted on the basis of possible unknown

confounding factors or just plain coincidence. Even extreme improbabilities

are not impossibilities, so that absolute certainty is seldom, if ever,

attained

in epidemiology. Since there is always some doubt, credibility becomes

the issue. I believe that's where Bernie's reference to religious conviction

is appropriate. Whether you consider it religion, faith, belief, prejudice,

or whatever, it isn't science. IMHO, convincing the NCRP that LNT is not an

appropriate basis for radiation standards could be like persuading the

leaders

of any religion that their fundamental faith is unfounded.



----- Original Message -----

From: Otto G. Raabe <ograabe@UCDAVIS.EDU>

To: BERNARD L COHEN <blc+@PITT.EDU>

Cc: internet RADSAFE <radsafe@list.vanderbilt.edu>

Sent: Friday, May 02, 2003 3:32 PM

Subject: Re: NCRP bias?





> At 09:25 AM 5/2/03 -0400, BERNARD L COHEN wrote:

> >

> >I recognize that to many

> >epidemiologists it is a religious conviction that an ecological study

> >cannot be used to test a theory, but the NCRP committee includes

> >physicists who should not be influenced by that religious conviction.

> **************************************************

> May 2, 2003

>

> A few years ago Bernie Cohen and I were invited to attend a committee

> hearing on LNT at the NCRP headquarters in Bethesda. At that meeting, we

> watched as Jay Lubin derived on the board the mathematical relationships

> associated with possible slope observations in an ecological study such as

> Bernie's and showed convincingly that unrecognized and possibly

> undetectable cross-interactions between the variables could result in a

> completely meaningless "observed" regression slope irrespective of the

> underlying true relationship. Hence, it is a mathematical truth (not a

> religious conviction) that the "observed" slope in Bernie's study of the

> possible relationship for radon-induced lung cancer could be totally

> spurious. On the other hand, this is not a proof that it is necessarily

wrong.

>

> It seems to me that all Bernie has been asking for is a plausible

> suggestion as to what conceivable or even far-fetched cross interaction is

> yielding his robust results.

>

> Otto

> **********************************************

> Prof. Otto G. Raabe, Ph.D., CHP

> Center for Health & the Environment

> (Street Address: Bldg. 3792, Old Davis Road)

> University of California, Davis, CA 95616

> E-Mail: ograabe@ucdavis.edu

> Phone: (530) 752-7754   FAX: (530) 758-6140

> ***********************************************

> ************************************************************************

> 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/





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

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/