Re: Ecological Fallacy?

[mcnaught@lanl.gov (Mike McNaughton)]

>What is considered to be a
>fallacy is to asssume that all persons in such an area or population are
>having the same exposure

However, if you know the shape of the distribution (e.g., log-normal) and
the standard deviation, it is theoretically possible to develop a detailed
computer model that is not subject to the ecological fallacy. It would be
very important to include in this model detailed information on the
correlation of the variable of interest (in this case radon concentration)
with confounders such as smoking, and to have both a mean and standard
deviation for every confounder.

"The case-control fallacy" is a name we might give to the assumption that
an epidemiological study is only valid if there exists a list of the actual
names of each individual in the study.


"Shlala gashle" (Zulu greeting, meaning "Stay safe")
mike (mcnaught@LANL.GOV)