Re: Medical Research-Evidence
- From: hrubin@xxxxxxxxxxxxxxxxxxxx (Herman Rubin)
- Date: 30 May 2006 13:27:21 -0400
In article <neJeg.8600$1i1.1583@attbi_s72>, Skeptic <bcs002b@xxxxxxxxx> wrote:
"George Conklin" <georgeconklin1@xxxxxxxxxxxxx> wrote in message
Here is a comment from UK:
Prostate therapy benefits doubted
There are always supporters and doubters.
Many men diagnosed with low-grade prostate cancer do not benefit from
radical treatment, research suggests.
Agreed. The study did not state nor imply every man benefited from surgery.
In fact, it shows that operating on all men with prostate cancer results in
overtreatment... which we already new. The problem is, we don't know
*which* patients will benefit. That's why you check everyone's blood
pressure... to pick up the hypertensive patients. There's no way to guess
which one will have high blood pressure and as of now, there's no way to
tell which man will get a survival benefit from surgery. All that we now
*know* is that some men do. The rest of your posts confirms exactly this
and is therefore snipped.
In this case, get all the information you can, and analyze
it VERY CAREFULLY to decide what additional tests are
needed to whittle down the evidence. Statistics is not
infinitely powerful, and the sample sizes, while they may
seem large to you, are not that large that one can do more
without strong prior assumptions.
You may have some prior information, from guesses or
biological reasoning, and these might be able to get at
some of the results more quickly. I am now at the point
of having to discuss the problem in detail with the
experimenter to make more concrete suggestions.
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@xxxxxxxxxxxxxxx Phone: (765)494-6054 FAX: (765)494-0558
- Prev by Date: Re: Medical Research-Evidence
- Next by Date: Re: Medical Research-Evidence
- Previous by thread: Re: Medical Research-Evidence
- Next by thread: Re: Medical Research-Evidence