BtZ42 Section 9 (pp 53-60): the sieve of chance

[Monte Davis]

Not at odds: it's entirely correct to expect that *eventually* the law of
large numbers will be borne out. What turns that into the Monte Carlo
fallacy is to imagine that with each black, some kind of force or pressure
towards red is growing -- which leads to wild overestimation of how *soon*
the law of large numbers will be borne out.


On Fri, May 13, 2016 at 9:43 AM, David Morris <fqmorris at gmail.com> wrote:

> It does seem that the Monte Carlo Fallacy is at odds wit the Large Number
> Theory.  I don't know anything about statistics, but I'm sure this isn't
> the first time this question has been asked.
>
> David Morris
>
> On Fri, May 13, 2016 at 8:32 AM, Thomas Eckhardt <
> thomas.eckhardt at uni-bonn.de> wrote:
>
>>  Monte Davis <montedavis49 at gmail.com> wrote:
>>
>>> P. 56:
>>>
>>> “But squares that have already* had* several hits, I mean—”
>>>
>>> “I’m sorry. That’s the Monte Carlo Fallacy..."
>>>
>>
>> I look at it like this: It is highly unlikely that the roulette ball
>> settles on black for 26 times in a row. But once it *has* settled on black
>> for 26 times in a row, the probability for it to do so again with the next
>> spin of the wheel is the same as before (48.6 per cent, that is).
>>
>> At least that's how I explain it to the kids...
>>
>> Where the bettors went wrong was that 26 spins of a roulette wheel simply
>>> isn't that large a number.
>>>
>>
>> Hmmm. It would have been the same probability even if the ball at that
>> point had settled on black for a few million times in a row, no?
>> -
>> Pynchon-l / http://www.waste.org/mail/?list=pynchon-l
>>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://waste.org/pipermail/pynchon-l/attachments/20160513/0310faee/attachment.html>