Another common question with Gage Crossed is what table to look at when assessing your measurement system. By default, Minitab gives a %Contribution table and %Study Variation table. Which one should you use when assessing where the variation is mostly coming from? Well, you could use either of them.

The %Contribution table can be convenient because all sources of variability add up nicely to 100%. Example:

The %Study Variation table doesn’t have the advantage of having all sources add up nicely to 100%, but it has other positive attributes. Because standard deviation is expressed in the same units as the process data, it can be used to form other metrics, such as Study Variation (6*standard deviation), %Tolerance (if you enter in specification limits for your process), and %Process (if you enter in an historical standard deviation). Of course, there are guidelines for levels of acceptability from AIAG as well:

If the Total Gage R&R contribution in the %Study Var column (% Tolerance, %Process) is:

- Less than 10% - the measurement system is acceptable.
- Between 10% and 30% - the measurement system is acceptable depending on the application, the cost of the measuring device, cost of repair, or other factors.
- Greater than 30% - the measurement system is unacceptable and should be improved.

If you are looking at the %Contribution column, the corresponding standards are:

- Less than 1% - the measurement system is acceptable.
- Between 1% and 9% - the measurement system is acceptable depending on the application, the cost of the measuring device, cost of repair, or other factors.
- Greater than 9% - the measurement system is unacceptable and should be improved.

We field a lot of questions about %Tolerance as well. %Tolerance is just comparing estimates of variation (part-to-part, and total gage) to the spread of the tolerance.

When you enter a tolerance, the output from your gage study will be exactly the same as if you hadn't entered a tolerance, with the exception that your output will now contain a %Tolerance column. Your results will still be accurate if you don't put in a tolerance range; however, including the tolerance will provide you more information.

For example, you could have a high percentage in %Study Var for part-to-part, and a high number of distinct categories. However, when you compare the variation to your tolerance, it might show that in reference to your spec limits, the variation due to gage is high. The %Tolerance column may be more important to you than the %Study Var column, since the %Tolerance is more specific to your product and its spec limits.

Think of it this way: Your total variation comprises part-to-part and the gage (Reproducibility and Repeatability). After adding a tolerance, we get to see what percentage of variation really dominates within the tolerance bounds specified. If the ratio between the Total Gage R&R and the tolerance is high (%Tolerance>30%), that provides insight about the types of parts being selected. It’s telling us that the measurement tool cannot effectively decipher if the part is good or bad, because too much measurement system variation is showing up between specifications.

I hope the answers to these common questions help you next time you’re doing Gage R&R in Minitab!

Time: Thursday, May 31, 2012

Had a quick quastion, how is the total gage R&R Std Dev calculated?

Time: Wednesday, June 13, 2012

i need to know why is part to part variation is too high?

>90%

Time: Wednesday, June 13, 2012

hi jefre - we're happy to help, but there's not really any way to answer your question without a little bit more information about your data, etc. If you're in the U.S., you can call our customer support line at 814-231-2682, if not check www.minitab.com/company/contact-us/default.aspx to find out how to get support in your country.

Time: Thursday, June 14, 2012

Regarding the %Study Var related for Part-to-Part, Is there any number or thershold that could help me determine I did a poor sample selection process? (say, like: Part-to-Part being equal to 80% means that a lousy sample selection process was executed)

Time: Friday, June 15, 2012

Luis, there is no threshold that I'm aware of because the sample selection could go wrong in either direction - sampling from a range of parts that's narrower than the typical process OR sampling parts that fall outside the typical range. If you select Gage R&R Study (Crossed) > Options and enter a 'Historical standard deviation', Minitab will provide %Process, which you can use to avoid the sample selection issue.

Time: Sunday, June 17, 2012

What is the purpose of entering the Study Variation in the Options dialog box. How is it different if I enter 1.0 versus 6.0 or 5.15 ? What does 1.0 or 5.15 or 6.0 practically mean ?

Time: Monday, June 18, 2012

AIAG manual version 4 answers most of your questions, but its not free. NIST online handbook is free, but answers are complex, as this subject is NOT about those magic % numbers but really about the graphs you can make that show you what to FIX to get better use of your gage.

http://www.itl.nist.gov/div898/handbook/mpc/mpc.htm

Don Wheeler has attacked the AIAG methods in many ways, and his Evaluation of the Measurement Process (EMP) methods as well as the AIAG methods are explained and supported in JMP v. 10 now. MInitab should perhaps do the same.

Measurement Systems Analysis is trivialized by focus on the AIAG %GRR numbers, as AIAG admits in its new manual. Bias, Linearity, Stability, are key issues. And the PURPOSE of using a gage is important. Is it for SPC or for Scrap decisions? The "rating" systems are not same for those very different applications. I fuzzy gage often work OK for SPC, but not for scrap decisions (which use spec limits rather than control limits).

Time: Tuesday, September 4, 2012

hi.

below is my question :

if the GR&R result is : %R&R=100(R&R/TV) = 17.88%;

: %R&R=100(R&R/Tol) = 9.53%,

which is the correct result to determine the GR&R study?;

and why?

Time: Thursday, September 6, 2012

You're asking about using %Contribution vs. %Tolerance. The answer is it depends. If the measurement system is used for process improvement (reducing part-to-part variation), %Contribution is a better estimate of measurement precision. If the measurement system is used to evaluate parts relative to spec limits, %Tolerance is a more appropriate metric. Or as the Assistant puts it, use this statistic if you want to use the measurement system “to accurately accept or reject parts”. Hope this helps! You can always contact our support team for assistance, too!

Time: Wednesday, September 19, 2012

I'm trying to understand % Contribution (of VarComp) and % Tolerance( SV/Toler) on MiniTab. I ran a GR&R Crossed to determine the Reproducibility and Repeatability of our CMM by using two people, measuring 10 parts from different dates and cavity number three times. In each of the three runs set up was broken down and set up again in the same way to determine the Reproducibility. These are my results when I input the rawndata on Minitab using the GR&R Crossed.

Gage R&R %Contribution

Source VarComp (of VarComp)

Total Gage R&R 0.0000000 1.20

Repeatability 0.0000000 1.20

Reproducibility 0.0000000 0.00

INSPECTOR 0.0000000 0.00

Part-to-Part 0.0000013 98.80

Total Variation 0.0000013 100.00

Process tolerance = 0.008

Study Var %Study Var %Tolerance

Source StdDev(SD) (6* SD ) (%SV) (SV/Toler)

TotalGR&R 0.0001263 0.0007577 10.95 9.47

Repeatability 0.0001263 0.0007577 10.95 9.47

Reproducibility 0.0000000 0.0000000 0.00 0.00

INSPECTOR 0.0000000 0.0000000 0.00 0.00

Part-to-Part 0.0011467 0.0068801 99.40 86.00

Total Variation 0.0011536 0.0069217 100.00 86.52

Number of Distinct Categories =12

Need to know what percentage I'm I suppose to use to determine weather my GRR Crossed is acceptable?

Time: Wednesday, July 24, 2013

How is the total gauge R&R std Dev calculated?

Time: Wednesday, July 24, 2013

How do you calculate the stDev of the total gauge?