Re: quality control

"Frank" <deps_bear@xxxxxxxxx> wrote in news:1163379604.737594.310650
@b28g2000cwb.googlegroups.com:

If I know a product fails .01% of the time and I have 1500 items I'm
running through a process. How many items do I need to check with,
say, 99% confidence that all the items are built correctly.

Think about it in simple terms. What would be the failure rate if only 1
out of 1500 failed. Once you look at that failure rate, you should should
ask youself whether there is any chance in Hades that you will ever be 99%
confident with any sample.

I'm thinking either Poison or Geometic distribution is applicable, but
what would the formula be. Also, what key words should I be searching
for. I know I've come across this problem many years ago but stuck on
finding where.

Its a binomial problem and the Poisson would be a good approximation, but
if that is really the problem, then it won't matter whether you use a
Poisson or a binomial. You will never get to power of 0.99 with anything
less that 100% sample.

--
David Winsemius

.

Loading