Cohen's ecological data: a test of LNT?

[Ken Mossman <Ken.Mossman@asu.edu>]

Cohen states  that "LNT is a special case of a causal relationship." I do
not understand this statement. There is no "special case." LNT IS
unconditionally a causal relationship. It is no more or no less a causal
relationship than a curvilinear dose-response, or threshold dose-response,
etc. 

Whether one is referring to a dose-response for individuals or a dose
response for a group of individuals has no bearing on the fact that LNT is a
causal relationship. 
 
My logic is quite simple and straight forward:

1.	LNT is a causal relationship.
2.	Cohen's data does not test for a causal relationship (in order to
avoid the ecological fallacy).
3.	Therefore, Cohen's data does not test LNT. 

Kenneth L. Mossman
Professor of Health Physics
Director, Office of Radiation Safety
Arizona State University
Tempe, AZ 85287-3501
************************************************************************
The RADSAFE Frequently Asked Questions list, archives and subscription
information can be accessed at http://www.ehs.uiuc.edu/~rad/radsafe.html