From: Steve Howard
Date: 22 Feb 2002
Time: 15:12:43
Just found your site and have it bookmarked. In checking out the forum I came across this point which has really been bugging me as I know there has to be some answer, even empirical, which addresses the relative difference in confidence levels from II to III and II to I. I am currently renwewing my love-hate relationship with OC curves to try to get an answer. It appears that there has been nothing written about the use of Levels that addresses what you gain or lose in terms of risks or confidence level in any type of "numerical" format. If there is no statistical reason for the development or existence of Levels, why/how do they exist? My specific example is straight-forward, I hope. If I have a plan which gives me 95% confidence that I will reject a 1% non-conformance, and the inspection sample size is based on Level II, is there any impact on the confidence level - intuitively one would think so?!? Thanks for listening to my ranting and I hope you can help steer me in the right direction so that I can address the Level changes (and accompaniyying costs) in a way taht my Senior Management understands.