RE: Radon - county linear model and LNT

["Wesley" <wesvanpelt@ATT.NET>]

Bernie and Radsafers,



On reflection, I do not think that monotonic behavior is necessary. 



Stratification removes the "conduit" by which a co-variate can influence the

relation between lung cancer and radon.



Best regards,

Wes

Wesley R. Van Pelt, PhD, CIH, CHP

Wesley R. Van Pelt Associates, Inc.

Home Pagehttp://home.att.net/~wesvanpelt/Radiation.html

wesvanpelt@att.net

 



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

From: BERNARD L COHEN [mailto:blc+@pitt.edu] 

Sent: Friday, June 27, 2003 12:10 PM

To: Wesley

Cc: 'Otto G. Raabe'; epirad@mchsi.com; radsafe@list.vanderbilt.edu

Subject: RE: Radon - county linear model and LNT





On Fri, 27 Jun 2003, Wesley wrote:

>

> Dr. Cohen uses the statistical method of stratification to evaluate

> confounders (co-variates). This method stratifies the counties into 5 or

10

> groups, each with similar values for the co-variate (e.g., dietary level

of

> a specific nutrient). It is not necessary that co-variates be linear with

> lung cancer. All that is necessary is that the co-variate vary

monotonically

> with lung cancer. That is, as the co-variate increases (or decreases) lung

> cancer also increases (or decreases).



	--I don't see why this monotonic behavior is necessary. Can you

explain?







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

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/