[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Dr. Long
Dear Professor Field,
The only thing I do not understand is why you do not yet agree that the Iowa study
1, cannot claim radon as a cause of lung cancer (as in reference to it in the
American Cancer Society journal, CA) or 2, cannot support LNT.
First, Iowa women, although obvious selection in Iowa, are a 1% outlier in lung
cancer mortality association with radon in the USA. .
Only a -0.3 SD was found for Iowa but >-3.0 SD for the USA.
I am happy to read you do apply Iowa findings only to midwest women. Please inform
CA.
Second, to "adjust" for only 32% of controls smoking when 86% of cases smoked
makes me (and TARB, given Ford's writings), incredulous of dependent inferences.
Smoking's association with lung cancer is >10 x radon's. So error in memory of
smoking (ubiquitous, I find ) could make radon protection from lung cancer
(suggested by Cohen's findings) appear as cause (suggested by Iowa findings). We
value placebo studies because the control match is identical!.
Do you agree that these points do cloud inferences your study to,
1, other populations than Iowa, and
2, linear effect (harm) from home radon?
Howard Long
"Field, R. William" wrote:
> Dr. Long,
>
> I have seen you make this post on at least 7 occasions. I do not
> understand what response you are looking. Nor, do I understand your point
> about an "outlier". The reasons why Iowa was chosen as a site for a radon
> study has been presented to you on numerous occasions. The difference in
> smoking percentages have been discussed frequently before including the
> published literature (http://www.ntp.org.uk/951-TUD.pdf). If you do not
> understand the answers, I understand that and I would welcome you
> contacting me directly. If you are just be argumentative, I can likely
> provide no answer that you would find acceptable.
>
> Bill Field
>
> At 10:31 AM 01/25/2002 -0800, you wrote:
> >Don,
> >I "keep saying this" - ie, "Selecting an outlier invalidates inference to
> >the whole,"
> >because neither you nor Fields has responded!
> >Iowa women had only a -0.3 SD for lung ca mortality vs radon,
> >where there was >-3.0 SD for the whole USA.
> >
> >Nor have you supplied data that could justify substituting statistical
> >"adjustment" (extrapolation from outside studies and populations)
> >for matching smokers (32% of controls vs 86% of Iowa cases).
> >
> >Each of these problems suggests that the Iowa case control study
> >should not claim better "quality" than Cohen's epidemiologic study.
> >Do you concede this?
> >
> >Not, going, going, going - but waiting, waiting, waiting!
> >
> >Howard Long
> >
> >Rad health wrote:
> >
> > > Howard,
> > >
> > > Why do you keep saying this. What point do you hope to make. Do you
> > > believe if you say it enough someone will believe it if by chance they
> > > understand it. This is silliness. Perform your double blind studies, who
> > > is stopping you? Also, to save bandwidth, please edit your postings.
> > >
> > > Don
> > >
> > > >Mea culpa! I, too, extrapolated (estimated beyond data at hand) with "Iowa
> > > >women - 1% outlier of USA lung cancer mortality, 1/radon." What IS in
> > > >Cohen's data is that Iowa women had only 0.3 standard deviations of
> > > >inverse association - lung cancer mortality vs radon, whereas p< 0.001
> > > >chance
> > > >(many SDs) for whole USA (minus mobile CA, FL, AZ). So Iowa is different,
> > > >clouding inference to the USA.
> > > >
> > > >We need placebo studies - identical controls!
> > > >
> > > >Howard Long
> > >
> > > _________________________________________________________________
> > > Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp.
> > >
> > > ************************************************************************
> > > 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. You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/
> >
> >************************************************************************
> >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.
> >You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/
************************************************************************
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. You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/