Validation sampling plan

This topic has 1 reply, 2 voices, and was last updated 10 years, 3 months ago by Kotval.

Viewing 2 posts - 1 through 2 (of 2 total)

Author

Posts
July 7, 2011 at 5:59 pm #53840

Avila
★ 10 Years ★
Participant

@Ifsergioa Include @Ifsergioa in your post and this person will
be notified via email.

Hi everibody!

i want to know how can i implement a sampling plan ti validate a process.

I know, it musst be more strict than the one for the lot, but i want an advice over how to implement it.

If there is any methodology

Thanks a lot

Sergio Avila

0

July 13, 2011 at 8:59 pm #191634

Kotval
★ 10 Years ★
Participant

@ckotval Include @ckotval in your post and this person will
be notified via email.

Selecting sample size is always a challenging issue. A rule of thumb for variable data sampling is 30 or more. For attribute data it should be 60 or more. If one has conducted an FMEA and the risk severity levels are known for the parameters being measured, the higher the severity level the higher the sample size should be.

If you are conducting a comparative study, such as comparing an existing process to a new one, a formula can be used to determine desired sample size. It is dependant on selecting a desired confidence level which is determined by the alpha level (Type I error), the historical standard deviation (Sigma) and a detectable difference in the sample means. I am attaching the formula to this response.

Hopefully this will help.

0
Author

Posts

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.