Re: [Phys-l] Poisson stat.

[John Denker <jsd@av8n.com>]

On 04/16/2009 10:49 PM, Bernard Cleyet wrote:
> I've for some time assumed the simulation w/ student groups throwing  
> initially 100 dice, and removing those w/, say, one up. successively.  
> was a model for decay w/ Poisson stat.  Wrong, right?
>
> The ten groups would add their data successively showing the  
> progressive smoothing.
>
> P. requires N >> 100 and remain so?
>
> bc has lotsa dice, and not very bright?

The per-die process is a Bernoulli process (subject to the
usual mild assumptions, e.g. that the dice are not damaged
by the throws).

The overall experiment is a good model of radioactive decay.
Quite a direct model.

Why mention Poisson at all?  You could make it "approach"
Poisson in various ways, but it wouldn't make the model any
better.

====================

Writing complete, grammatical English sentences makes messages
easier to understand.  When there are hundreds of people reading
each message, it is worth your time to polish the writing before
sending.