RE: Cohen's Ecologic Studies

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

On Mon, 3 Jun 2002 epirad@mchsi.com wrote:



> Just for the record then, how do your treatments account

> for non-linear dependecies within and between counties,

> especially since you are using averaged data for a

> county?

>

> Please be specific.



	--I don't understand your question. Please make a specific

suggestion for a possible confounder and its

possible dependencies within and between counties.



>

> Concerning the r-squared value.  The fact remains, you

> are able to predict only a small percentage of the lung

> cancer mortality using your smoking rates regardless of

> the cause of your low r-squared value.



	--Smoking cannot explain the statistical fluctuations which

dominate thr R-squared value when the variation in smoking among counties

is small percentage-wise. Please see my paper in Health Physics

72:489-490;1997 to understand this problem.



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

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/