Attribute Gage R&R - MSA 3rd Edition - 'Hypothesis Test Analysis - Cross Tab Method'

Y

YKT

With the new MSA 3rd Edition, the changes included 'new method for analysis of Attribute measurement system', which is stated in Chapter III - Section C, page 125.

My question is that, do we really need to follow the new attribute GRR, as to show proof (to the auditors) that we are following the 'Hypothesis Test Analyses - Cross Tab Method', calculation of kappa, calculation of the effectiveness, miss rate and false alarm rate, and use the table of acceptance on page 132 ?

The old method, if I'm not mistaken is merely comparing any discrepancies in the attribute reading by two or more appraisers.


So, do I have to upgrade the methodology ?
 
A

Atul Khandekar

Here is an excerpt from AIAG's MSA FAQ:

Q15. Why are the short and long form attribute methods that were in MSA2 not in the new MSA3 manual?

In MSA3, look at Figure 29 on p. 126, or the graphic in the left margin of p. 125. For an attribute gage study to be beneficial, this gray zone must be defined. In order to do that, some parts from the gray zone must be present in the study and one must use valid statistical methods that define that zone. The previous short and long form had shortcomings. The procedure surrounding those methods did not allow for "indecision" -- results were required to show 100% agreement; a bad part must be called "bad" all the time and a good part must be called "good". There was no room for disagreement in the results. However, using a "perfect" check fixture, a part that is exactly on the specification limit will be called "good" 50% of the time and "bad" 50% of the time. In reality, this "exactly on specification limit" is the gray zone (wider than the specification limit) and it should be understood and defined in a successful measurement systems analysis. Doing an attribute study successfully also requires a relatively large number of parts and test-opportunities to make a decision. The previous short form did not really accomplish this. Keep in mind that if the short and/or long form methods are still acceptable to your customer, they may still be used.


Hope this helps.
 
Y

YKT

atul,

Thanks. However, does that mean I do not have to follow the 'Kappa' or calculate the effectiveness, miss rate, false alarm rate etc , as long as I can show that the attirbute method is acceptable by customer ?

Recently i heard a lot of nonconformances being issues to companies subscribing to QS9000 or ISO/TS 16949, for failing to comform with the new MSA 3rd EDition requirements. Thus, I'm afraid that the attribute GRR will be one of the issues the auditors will raise.
 
A

Atul Khandekar

YKT,
Its a question of having confidence in your measurement system as a whole, not just the gages. That is why you should try to characterize the measurement system and evaluate the risk (to you and to your customer) of having a possibly faulty measurement system. This applies to variable as well as attribute measurements. After all measurement is the basis for everything.

The FAQ says that the old method is inadequate. The bottom line of course, is to check with your customer and find out how much risk is acceptable to him.

As regards what is accepted by auditors, someone who has more experience than me in these matters should be able to tell us.
 
N

NISHANT

Regarding Cross Tab Method

Hi MR Kahndekar,
Sir I am trying very hard to understand the cross tabulation method but i can't get that. So please would you explain me the method.
& Secondly please explain the term uncertainty & method to calculate it.
 
A

Atul Khandekar

NISHANT said:
Hi MR Kahndekar,
Sir I am trying very hard to understand the cross tabulation method but i can't get that. So please would you explain me the method.
& Secondly please explain the term uncertainty & method to calculate it.
Nishant,

Difficult to answer these two rather broad questions in a post so I'll give you a few pointers:

For crosstab nethod, use the forums search with terms like: kappa, expected score, miss rate, false alarm etc. You'll also find an excel spreadsheet or two.

Start with these threads:
Go - No Go (Attribute) Gage R&R (Repeatibility and Reproducibility)
TS 16949 - AIAG's MSA Manual - Thread Inspection Gage - Attribute Gage R&R
Attribute MSA-CrossTab Study Example in MSA Manual:How to compute the Expected Count?
Miss rate & False Alarm Rate - What are they and how are they calculated?
Calculating the upper and lower confidence interval bounds

The topic of uncertainty has been extensively discussed in varipous threads in the 17025 forum: ISO 17025 - Calibration and Test Laboratories, Measurement and Gages

Also see: http://physics.nist.gov/cuu/Uncertainty/
and download an Uncertainty Calculator from:
http://metrologyforum.tm.agilent.com/download3.shtml

Hope this helps.

PS: Welcome to the Cove! I see that you are in Pune. :bigwave: You are welcome to call me if you like. My telephone numbers are in the profile.
 
Last edited by a moderator:
J

Jackiechan

Re: Attribute Gage R&R - MSA 3rd Edition - 'Hypothesis Test Analysis - Cross Tab Meth

Hello,
How do you find the gray area for the go/no-go gauge ?
In MSA MANUAL, on page 127, table no-12, where do you get these ref. values?
Thanks in advance
 
D

David DeLong

Re: Attribute Gage R&R - MSA 3rd Edition - 'Hypothesis Test Analysis - Cross Tab Meth

Hello,
How do you find the gray area for the go/no-go gauge ?
In MSA MANUAL, on page 127, table no-12, where do you get these ref. values?
Thanks in advance

In that table, the reference values are the actual measured values. One can reflect a measured value this since we have an attribute study on a go/no-go gauge. We simply measure the holes with a suitable measuring devise.

If we use this attribute study on an attribute characteristic such as a "crack", the reference value is the pre-determined assessment that the product does or does not have a crack.

By the way, the MSA 3rd edition does not describe in detail how to arrive at the counts in cross tabulation but I know there are some good excel files on line here that will do that for you.

Hope this helps.
 
Top Bottom