# [extropy-chat] calling all bayesians

Marc Geddes marc_geddes at yahoo.co.nz
Thu May 12 04:52:55 UTC 2005

```Just briefly summarizing my quick 'n dirty hackers
reasoning chain:

The information given said that you manufactured 150
droobs (so presumably the probability of a droob
failure would be the same for each droob from this 150
droob batch).

The information given then said that you tested 19
droobs from this batch and all of them were good.
What can we infer from this about the probability that
a droob from the batch is good?

Well, since we are given no other information, we can
only assume a 50% chance that all 19 tested would be
found to be good and a 50% chance that they wouldn't.

Which probability raised to the 19th power equals 50%?

.9642^19 = .5 (approx)

We have to take .9642 as the probability that a given
droob from the batch will be good.

Now we simply raise this probability to the 131st
power to find the probability that 131 droobs in a row
will be found to be good

.9642^131 = 0.0084 (approx)

Is this the result you're getting?

---

THE BRAIN is wider than the sky,
For, put them side by side,
The one the other will include
With ease, and you beside.

-Emily Dickinson

'The brain is wider than the sky'
http://www.bartleby.com/113/1126.html

---