Re: Radon and Smoking (individual vs aggregate)

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

On Thu, 21 Feb 2002, Otto G. Raabe wrote:



> February 21, 2002

>

> Dr. Field says that the joint distribution between radon levels and smoking

> characteristics in each County is what is causing the inverse slope in Dr.

> Cohen's ecological studies of radon and lung cancer. Dr. Cohen says he has

> been looking for a relationship that could explains his results. Dr. Field

> says that it is too late, since those unknown County relationships are

> inherently part of the observed results and cannot be removed or corrected.



	--It can't be too late. He can assume any  relationships he

likes, and leave it to me to prove that they can't explain my results



>

> Well, if the unknown relationships of smoking characteristics and radon

> levels by County are totally random among the 116 Counties in Cohen's

> study,



	--My study involves 1601 counties, not 116. It can also be treated

as 14 independent studies of 116 counties, with the distribution of

counties among these 14 independent studies chosenosen any way anyone

likes.

	--There is no need to assume they are random. Assume anything you

like about the smoking relationships and it is up to me to show that this

does not explain my results, or that the assumptions are very highly

implausible. I have done this in my papers.



 wouldn't that randomness wash out the effect of individual County

> radon versus smoking relationships? Dr. Field's objection would be correct

> only if a few Counties where under study. It seems to me that with 116

> Counties the only way those individual County relationships could have such

> a strong and consistent effect on Dr. Cohen's study is for there to be an

> underlying relationship the permeates most of the 116 Counties. Isn't that

> what Dr. Cohen is trying to find, a plausible relationship that can explain

> his results?

>

> I can't imagine that random and unrelated within-County relationships

> between radon levels and smoking characteristics could produce such a

> consistent and robust result.

>

> Otto

>

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

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

> 	Center for Health & the Environment (CHE)

> 	(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/