Darren New <dne### [at] sanrrcom> wrote:
> Grassblade wrote:
> > Ah, the magic of statistics. :-D If it's statistically proven, then you can be
> > confident it isn't proven.
>
> Define "proven" then.
"Statistically proven" is the result of the usual hypothesis testing, with
rejection or acceptance of the null hypothesis.
"Proven" has been defined somewhere in this thread, and you didn't raise any
objection to its definition.
This was also meant to be a pun for statisticians. Never mind.
>
> I'm pretty sure we've proven the sun comes up reliably every day, and
> that the phases of the moon repeat about once every 4 weeks. If God gave
> proof at that level, I don't think I'd question his existence.
Who was that guy who bet the sun would rise again the next day? British, around
XVIIIth century, I seem to recall...?
<snip>
> > In statistics you give up certainty to
> > get (possibly) greater insight through inference. It makes no sense to claim
> > that you can prove a negative with statistics.
>
> Sure it does. If you can "prove" a positive statement with statistics,
> you can prove a negative statement in the same way.
>
> "This drug cures cancer."
> "This drug does *not* fail to cure cancer."
To prove a positive I only need to find one item with the required property.
"Some grass is green". Easy as pie to prove. To prove a negative I need to sort
through the whole population: "There exists no grass that isn't green". If I use
statistics to make the proof, I'll be using a subsample. That's the whole point
of using statistics. Consequently no statistical proof of a negative is
possible, in general ("in general" in the mathematical sense).
>
> These aren't quite the same statement statistically speaking, I know,
> but it makes the point.
>
> >>> and it's that faith in the impossible not happening
> >>> that provides them with the comfort of their beliefs.
>
> >> I have a great deal of faith that the impossible won't happen.
>
> > I guess that begs the question: define "impossible".
>
> Define "proof" first. Or God. Or Faith. Why am I the first person who
> has to nail down exactly what I mean by everyday words?
Tsk, I asked first. ;-) Impossible is an interesting word. If I base myself on
everyday experience, I would say that being in two places at the same time is
impossible, or that what comes before causes what comes after. Yet in quantum
physics that isn't true.
Besides, it ties in with the proof-of-negative, since I suppose you prove
"impossible" by negation of what is "possible". Since you claim you can prove
it, be my guest.
>
> --
>    Darren New / San Diego, CA, USA (PST)
>      It's not feature creep if you put it
>      at the end and adjust the release date.

Post a reply to this message