Accuracy Criteria - Published material related to acceptable accuracy criteria

I was wondering if anyone knew of any published material related to acceptable accuracy criteria, or methods of determining, for measuring equipment. I have found information on R&R studies (0-10 acceptable, 10-20 marginal, etc.), but is there any way to determine acceptance criteria through statistical methods by somehow relating results to product tolerance, criticality, process spread, etc.? Any help would be greatly appreciated.

I recommend you check out the subject of measurement uncertainty; start at: http://physics.nist.gov/cuu/Uncertainty/index.html

Send me an email if you have further questions.

NOTE: This message was edited to HotLink the url.

[This message has been edited by Marc Smith (edited 22 May 1999).]

[Marc]

Thanks for the link!

My company is a wholesale electrical distributor and we just went through our preassessment. Things went well until we came across the subject of calibration. We have a counter that measures wire we sell. As long as this counter doesn't short the customer its accuracy doesn't have to be that precise. The assessor mentioned that we have to be able measure a standard with a device whose accuracy can be traced back to a national standard. This seems like quite a bit of over kill for us. As long as we are only over/under a foot per thousand that is acceptable to our customer. Is there any way around this?

[Don Winton]

The assessor mentioned that we have to be able measure a standard with a device whose accuracy can be traced back to a national standard.

The assessor is not precisely correct. Reference paragraph 4.11.2(b), which states, in part "Where no such standards exist, the basis used for calibration shall be documented."

As long as we are only over/under a foot per thousand that is acceptable to our customer.

That may be true, but you must have objective evidence that the measurement device meets this criteria, assuming the criteria is a documented one.

Now, the details. What does the manufacturer's manual state in terms of accuracy? Is there a statement in the manual that reads 'this counter is accurate for x number of uses or years' or something to that effect?

Check with the manufacturer. They may be able to help further. For example, the manual for one measurement device I use reads '…guarantees gage accuracy as long as the dial needle remains within the zero indicator when not in use.' A statement of this type should be acceptable objective evidence. In this case, the basis used for calibration is documented by the manufacturer's statement.

Regards,
Don

------------------
Just the ramblings of an Old Wizard Warrior.

Check Out dWizard's Lair:
www.ficom.net/members/donwinton/home.html

Thanks for the Help.