Sampling using summay data

["Harry Hinks" <harryhinks@hotmail.com>]

Yes, Ted,

It is in the math.  I didn't realize Prof. Cohen performed statistical 
sampling when choosing which house to test in a given area?  I thought the 
data set came from individuals who wanted to test for radon becasue of 
health concerns or thought they may be living in a high radon area. I wonder 
if people who have increased concern about their health would have lower 
cancer rates?

You can add large numbers and get very small error bars, but how do you know 
the data is representative.  Are the summary samplings a statistically valid 
sampling and can it be used in a realistic fashion for risk analysis?  It 
can be compared to the EPA sampling, but even the EPA's almost nationwide 
sampling was never intended for risk analysis.


You also say,

To collect the individual data would take a national level government
>funded mandatory program.  And very few of us would want to pay the
>taxes that would cost nor tolerate that level of intrusion into out
>private lives.  I wouldn't!  Maybe in a more totalitarian state this
>could be done.

It has been done in studies already performed by Darby, Wichman, Fields, 
Alavanja, and others.


Harry

harryhinks@hotmail.com

_________________________________________________________________
Get your FREE download of MSN Explorer at http://explorer.msn.com

************************************************************************
The RADSAFE Frequently Asked Questions list, archives and subscription
information can be accessed at http://www.ehs.uiuc.edu/~rad/radsafe.html