h a l f b a k e r ynon-lame halfbakery tagline
add, search, annotate, link, view, overview, recent, by name, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
|
|
|
Homeopathy and bad statistics - they were made for
eachother.
There are probably at least 1000 recognised, serious
medical complaints, ranging from pancreatic cancer to
piles.
It follows that, if a large collection of people taking any
given homeopathic remedy are surveyed for these 1000
serious illnesses, at least one such illness will be found to
be significantly more frequent in the remedy-takers, as
compared to the normal population, at a confidence level
of p=0.001.
Once this statistic has been unearthed, the full weight of
regulatory power (or the tabloid press) can be brought to
bear.
Texas sharpshooter fallacy
http://en.wikipedia...harpshooter_fallacy
[xaviergisz, Aug 30 2011]
XKCD
http://xkcd.com/882/
As ususal, there is an XKCD cartoon which describes this perfectly [hippo, Aug 31 2011]
[link]
|
| |
// the full weight of regulatory power (or the tabloid press) // |
|
| |
But applying a tiny fraction of said power would be even more effective, shirley ? |
|
| |
yeah but is "gullibility" a recognized disease ? |
|
| |
Didn't we work out that there might be something to it; the body's defenses act in the same way that birds react to a silhouette of a hawk cut out of cardboard... (or mumblings to that effect) |
|
| |
Didn't understand that last annotation, didn't understand main post. Is there a fallacious correlation is causation implication? Are you a homeophobe? Are you an adherent to the spiritual system of an obscure North American Indian tribe that worships the bear? |
|
| |
//worships the bear// Does Ursula Andress count ? |
|
| |
This may surprise you but i think this is an excellent
idea. However, sometimes It's Lactose. |
|
| |
Hear, hear! Take it to'em MB. |
|
| |
MB, have you lost most of your medical encyclopedic collection with the exception of Pa - Pi? |
|
| |
// Is there a fallacious correlation is causation
implication?// Yes, and that should be good enough
for a few headlines. |
|
| |
oh how weird, [hippo] I was just looking at a bear cartoon from there. |
|
| |
[hippo]'s link depicts a sort of inverse situation,
testing many compounds against one illness, rather
than one compound against many illnesses.
However, both approaches have their merits. |
|
| |
Interesting that everyone is concentrating on the homeopathy angle. I've yet to see any statistics that weren't badly used. Statistics themselves are neither bad nor good; unless they are just made up of course, in which case they are lies rather than statistics. |
|
| |
//I've yet to see any statistics that weren't badly used// - 100% of statistics seen by [DrBob] he judges to have been "badly used". |
|
| |
See, you just wasted that statistic on me when you could have used it on somebody who cares. Somebody who would probably, even now, be waving their fist ineffectually at their monitor and muttering "Curse that damned hippo!" under their breath. But that person wouldn't be me of course. I'm too cool. And calm and composed ... composed ... yeah, that's what I am. And calm. So yet another badly used statistic. |
|
| |
100% of Borg Collectives reading [DrBob]'s last anno consider that he is neither calm nor collected, but is instead operating in a mode best described as "low-level panic", and not hiding it very well. |
|
| |
How does one avoid sampling bias in polling Borg collectives? |
|
| |
[pertinax] Simplicity itself. You only need an N of 1,
and it doesn't matter who you pick. |
|
| |
isn't at least the partial weight of regulatory power
already brought to bear, e.g. admonitions such as
"this product is not intended to cure any disease"
which routinely accompany advertising for
homeopathic products? |
|
| |
I don't think there's much new here. |
|
| |
The majority of the "regulatory power" is based on bad statistics. Therefore, much though you might like to, you'll hardly be able to make the situation worse. |
|
| |
Saying homeopathy should be subject to regulation is
tantamount to saying people shouldn't be penalized for
their gullibility. [-] |
|
| |
//"this product is not intended to cure any disease"// |
|
| |
Would cure dehydration, I'd have thought. |
|
| |
// I don't think there's much new here // |
|
| |
If you look very closely, we think you'll find that there's just a
very tiny amount of New, diluted in a large volume of Old. |
|
| |