Re: Medical Research-Evidence
- From: hrubin@xxxxxxxxxxxxxxxxxxxx (Herman Rubin)
- Date: 16 May 2006 15:41:03 -0400
In article <uY9ag.974595$xm3.857567@attbi_s21>,
Skeptic <bcs002b@xxxxxxxxx> wrote:
"George Conklin" <georgeconklin1@xxxxxxxxxxxxx> wrote in message
news:R07ag.2622$x4.2264@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
[Lots of back and forth deleted.]
....................
Even if the results get no better than they are now, their is a
signficant
difference, clincally and statistically.
What Herman was trying to tell you is that this is not so.
Herman is not a a doctor and a physician is in a better situation to
determine what is CLINICALLY significant.
A doctor is in a better position to provide the medical
information, which should be used by the patient to
assess the risks and benefits of the various alternatives.
As to what is clinically significant, this is a very
difficult problem. In a certain sense, everything is
clinically significant, as it provides a change in the
probabilities, however slight. Because of limitations,
this cannot be done in practice.
You remind me of the Catholic church when it came up with a marriage
questionnaire. It could not be looked at statistically because it was a
holy document.
Clinically as used by your is a mystification technique. It is
meaningless. The only issue is whether a treatment works.
What does that mean? If someone is cured of a disease, and
dies the next day, the treatment has "worked", but what good
is it? There is also the matter of quality of life; people
who have had heart bypass operations may not live longer, but
their quality of life is greatly improved.
What Herman was trying to tell you is that in decision theory he would
rather trust a treatment which cured 3 out of 3 than 2% more of a large
group of people. Why? Well, too many variables not controlled for. What
if
they go back now and find that those who were 'cured' were only those who
did NOT have the newly-discovered gene? Or did have? Or what? Very
small
differences in cancer survival rates over very long periods of time may be
significant at the .05 level, but relatively meaningless at the individual
level. When effectiveness is unexplained, then Herman brings up a valid
point.
Yes, his comments on statistics are valid. On a separate note, the study
showed a small but clear survival advantage with surgery vs. watchful
waiting. We will see what further studies show.
significant.Very small
differences must be evaluated carefully even if statistically
The original authors state differences are small. Why dispute them?
I'm not disputing them. I support them. You just don't seem tounderstand
that a relatively small difference can be a very important one...
especially if you're amonge the extra 20 lives saved in that study.
The problem is that when you rerun the study, with low levels of
significance you might just as well find the opposite, as the HRT studies
showed or seemed to show.
you're living in hypotheticals now. Fact - the study showed a survival
advantage for surgery vs. watchful waiting. It's the best study we have
right on that topic.
I have commented on that in another posting, and looked
at the arithmetic carefully.
--
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
.
- Follow-Ups:
- Re: Medical Research-Evidence
- From: George Conklin
- Re: Medical Research-Evidence
- References:
- Breast Cancer Research
- From: george conklin
- Re: Medical Research-Evidence
- From: Skeptic
- Re: Medical Research-Evidence
- From: Skeptic
- Breast Cancer Research
- Prev by Date: Re: Medical Research
- Next by Date: Re: Medical Research
- Previous by thread: Re: Medical Research-Evidence
- Next by thread: Re: Medical Research-Evidence
- Index(es):
Relevant Pages
|
