Re: Wing: Descriptive Epidemiology by Any Other Name...

[Bob Flood <bflood@SLAC.Stanford.EDU>]

At 04:39 PM 2/26/97 -0600, you wrote:
>If you are upset by Wing yet celebrate Cohen, I ask that you examine why 
>descriptive studies are compelling in one case and not in the other.  To 
>me, the bottom line is that neither have data for individuals, neither 
>has meaningful control for confounders and biases, and no amount of 
>statistical analysis will change that.  Both fail to meet many of the 
>criteria presented by leading risk analysts.


A point well made - the methodology cannot be acceptable in one case and
inappropriate for the other.

However, it is important to note that the description given cited the
descriptive study as suitable for developing a hypothesis. Well, LNTH mean
Linear No Threshold HYPOTHESIS, and the Cohen data point directly to a
contradictory hypothesis. Until proven, one hypothesis with data to support
postulating the hypothesis is as good as any other hypothesis with data to
support postulating that hypothesis.

But, I think it hasn't been said frequently enough - we are debating the
existence of a trivially small risk in a world filled with tremendously
larger risks needing more immediate attention and a larger shared of our
always limited resources.


Bob Flood
Stanford Linear Accelerator Center
(415) 926-3793     bflood@slac.stanford.edu
Unless otherwise noted, all opinions are mine alone.