On 11/8/2010 4:24 AM, Michael Power wrote:
> David Gorski at the Science-Based Medicine blog has posted a put-down
> of Steve Simon's defence of EBM:
> http://www.sciencebasedmedicine.org/?p=8151
I wouldn't characterize this as a shouting match, and I find comments
about being naive and in denial to be amusing, and quite possibly
accurate. An extended debate is probably unproductive, but I thought
there would be some value in reviewing things once. It's hard to write
for the web without coming across as too strident in making your point
or too wishy-washy in acknowledging the good points on the other side.
So the comments by Dr. Gorski were actually appreciated by me.
Here's what I wrote:
* http://www.pmean.com/10/ScienceBasedMedicinePt2.html
This page also has links to all the previous discussions.
If I can be a bit boastful about my writing, I like the summary about
how EBM is largely self-correcting. I do believe this is one of EBM's
greatest strengths.
I'm also curious about the SBM effort to describe the conflict between
SBM and EBM to be equivalent to the conflict between Bayesian statistics
and classical statistics. I've written a bit about Bayesian methods, and
I am even a co-author on a peer-reviewed article about teaching Bayesian
statistics, but in all honesty, I'm still trying to get comfortable with
the philosophy. I have to admit that I can't see the link between SBM
and Bayesian methods. A Bayesian is no more or less prone to ignoring
scientific mechanisms as a classical statistician, at least as far as I
see it.
--
Steve Simon, Standard Disclaimer
Sign up for The Monthly Mean, the newsletter that
dares to call itself "average" at www.pmean.com/news
|