[ RadSafe ] Ecological fallacy fallacy

[Dale Boyce]

Hi all,

I keep seeing the phrase ecological fallacy invoked.  The more correct term 
is ecological interference, and statistical methods have been devised to 
circumvent it. See for example:

http://gking.harvard.edu/eicamera/kinroot.html

I believe this was published around 1997.  The presence of confounding 
factors does not preclude finding statistically significant trends.  While 
this particular paper/book was developed to study voting trends and not 
epidemiological studies, its conclusions apply.

I can't say whether or not anyone has used this or similar data treatments 
in background radiation studies. If not someone should.   Automatically 
invoking the ecological fallacy argument without examining the underlying 
statistical treatment is insufficient to discount epidemiological studies.

Just my $0.02

Dale



----- Original Message ----- 
From: <Rainer.Facius at dlr.de>
To: <crispy_bird at yahoo.com>; <jimm at WPI.EDU>; <maurysis at ev1.net>
Cc: <cdn-nucl-l at mailman1.cis.mcmaster.ca>; <mbrexchange at list.ans.org>; 
<radsafe at radlab.nl>
Sent: Thursday, August 11, 2005 1:43 AM
Subject: AW: AW: [ RadSafe ] Re: "Science" reports on background 
radiationandhealth


John:



Before we continue this futile exchange I suggest you start studying at 
least some of the more than 3 dozen references I offered upon your request. 
Afterwards we might continue to discuss the evidence provided there on the 
health status as a function of background radiation these populations are 
exposed to. By then you might also understand why I referred to the 
ecological fallacy argument.



Regards, Rainer



________________________________

Von: John Jacobus [mailto:crispy_bird at yahoo.com]
Gesendet: Mi 10.08.2005 23:30
An: Facius, Rainer; jimm at WPI.EDU; maurysis at ev1.net
Cc: cdn-nucl-l at mailman1.cis.mcmaster.ca; mbrexchange at list.ans.org; 
radsafe at radlab.nl
Betreff: Re: AW: [ RadSafe ] Re: "Science" reports on background radiation 
andhealth



Rainer,
I think you have fallen prey to the problem of wishful
thinking.  As a scientist, I expected more for you.

This has nothing to do with the LNT or ecological
studies.  It is what science is about.  Studies
performed and evidence presented.  Do you know of any
that support the idea that people who live in high
background areas are healthier and live longer?

--- Rainer.Facius at dlr.de wrote:

> "Can you cite any epidemiological studies..."
>
>
>
> John:
>
>
>
> Apparently you have fallen prey to the fairy tale
> perpetuated by linear philosophers that ecological
> epidemiological studies yield no valid conclusion
> whatsoever. Particularly in case of linear
> stimulus-risk relations, BL Cohen has conclusively
> refuted that myth. Otherwise it might indeed be
> impossible to extract risk coefficients from
> ecological studies. But who actually cares about
> risk coefficients if the complete (of course
> non-linear) risk function representing essentially
> the whole population is known. Obviously again only
> linear minds would care. Otherwise you might wish to
> study some of the results demonstrated in the papers
> of the incomplete list below (BTW, not all report
> ecological studies).
>
>
>
> Kind regards, Rainer
>
>  . . .


+++++++++++++++++++
"Every now and then a man's mind is stretched by a new idea and never 
shrinks back to its original proportion." -- Oliver Wendell Holmes, Jr.

-- John
John Jacobus, MS
Certified Health Physicist
e-mail:  crispy_bird at yahoo.com



____________________________________________________
Start your day with Yahoo! - make it your home page
http://www.yahoo.com/r/hs




_______________________________________________
You are currently subscribed to the RadSafe mailing list

Before posting a message to RadSafe be sure to have read and understood the 
RadSafe rules. These can be found at: 
http://radlab.nl/radsafe/radsaferules.html

For information on how to subscribe or unsubscribe and other settings visit: 
http://radlab.nl/radsafe/