[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Interesting paper
Many thanks for this reference.
Several of my papers give examples of how an ecological study such
as mine can give the wrong answer if confounding factors are not taken
into account. For example in my 1995 paper I show that if the width of the
distribution of smoking prevalence in U.S. counties were twice as wide as
best estimates and the coefficient of correlation between smoking
prevalence and radon levels for U.S. counties is >0.9, my data would be
explained without abandoning LNT. However I show that such a high
correlation is completely implausible. The potential importance of
confounding is why I have gone to great lengths to treat over 500
potential confounding factors, including geography which was the problem
in the Lagarde paper, and urban-rural which was the confounding factor in
the Darby et al study. All of the >500 confounding factors I have
considered in my several papers have been found not to have an effect on
my results; that is why I am offering a large monetary reward for anyone
who can suggest a confounding factor that might explain my results. They
don't have to show that it is successful - testing it is my job. My latest
offer is that they get the reward if their suggestion is accepted for
publication in Health Physics or an equivalent journal.
Note that an unrecognized confounding factor can invalidate any
epidemiological study, including case-control which Lagarde and Darby use.
These seldom treat more than 5 potential confounding, let alone 500.
I have recently submitted a paper on treatment of confounding
factors in an ecological study. If anyone is interested, I can e-mail a
copy.
Bernard L. Cohen
Physics Dept.
University of Pittsburgh
Pittsburgh, PA 15260
Tel: (412)624-9245
Fax: (412)624-9163
e-mail: blc+@pitt.edu
On Thu, 5 Jul 2001, Jim Nelson wrote:
> Dr. Cohen,
>
> Have you seen this paper that says ecological studies can not adequately
> adjust for confounders. This follows the paper of Legarde that made the
> same conclusion. They mention your ecologic study as an example. Isn't Dr.
> Doll the first person who made the link between smoking and lung cancer?
>
> Journal of the Royal Statistical Society: Series A (Statistics in Society)
>
> A parallel analysis of individual and ecological data on residential radon
> and lung cancer in south-west England
>
>
> volume 164: Issue 1
>
>
> Sarah Darby: Imperial Cancer Research Fund, Oxford, UK
> Harz Deo: Imperial Cancer Research Fund, Oxford, UK
> Richard Doll: Imperial Cancer Research Fund, Oxford, UK
> Elise Whitley: University of Bristol, UK
>
> Abstract:
>
> Parallel individual and ecological analyses of data on residential radon
> have been performed using information on cases of lung cancer and population
> controls from a recent study in south-west England. For the individual
> analysis the overall results indicated that the relative risk of lung cancer
> at 100 Bq m−3 compared with at 0 Bq m−3 was 1.12 after adjusting
> for age, sex, smoking, county of residence and social class. In the
> ecological analysis substantial bias in the estimated effect of radon was
> present for one of the two counties involved unless an additional variable,
> urban-rural status, was included in the model, although this variable was
> not an important confounder in the individual level analysis. Most of the
> methods that have been recommended for overcoming the limitations of
> ecological studies would not in practice have proved useful in identifying
> this variable as an appreciable source of bias.
>
> http://www.blackwellpublishers.co.uk/asp/journal.asp?ref=0964-1998&src=arc&vid=164&iid=1
>
> Jim Nelson
>
>
>
> _________________________________________________________________
> Get your FREE download of MSN Explorer at http://explorer.msn.com
>
>
************************************************************************
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.