[ | Next | Previous | Up ]

Re: Cpk and Sample Size/frequency determination

From: Stan Hilliard
Date: 22 Jan 2001
Time: 21:22:50

Comments

I think that your goal can be met. I would divide the issue into two parts:

1) What procedures will reduce the sample size from a lot or sub-lot as the Cpk increases, and vice versa? A requirement: that the protection against erroneous decisions that is offered by the plan's operating characteristic curve not be sacrificed for those lots with smaller samples.

2) What procedures will increase the interval between samples as data accumulates to demonstrate that the process is stable, and vice versa?

Am I interpreting your goals correctly? If so, are we talking about an existing process or general methods?

If a particular process, please post some more information about it. For example, is the process a continuous stream of items, or are they grouped into natural lots or sub-lots? What is the throughput rate? What are the items?

Sincerely, Stan Hilliard


Last changed: November 20, 2007