Understanding "Number of Distinct Categories" in Your Gage R&R Output

Recently I've been thinking about common questions that customers ask when running a Gage R&R analysis in Minitab.

For example, when you run a Gage R&R, the last result that shows up in the session window is a value for the ‘Number of Distinct Categories’.  This one metric is something that customers seem to overlook when they call to discuss their Gage studies.
This value represents the number of groups your measurement tool can distinguish from the data itself. The higher this number, the better chance the tool has in discerning one part from another.

So how do you know if your number is high enough? Fortunately, there are guidelines from the Automotive Industry Action Group (AIAG):

  • When the number of categories is less than 2, the measurement system is of no value for controlling the process, since one part cannot be distinguished from another.
  • When the number of categories is 2, the data can be divided into two groups, say high and low.
  • When the number of categories is 3, the data can be divided into 3 groups, say low, middle and high.
  • A value of 5 or more denotes an acceptable measurement system.

Let‘s say you do get a value below 5. What next? Well, there are two things you can do.

  • Analyze more distinct parts that truly represent the entire range of the process.
  • Increase the precision on your measurement tool.

I'll cover some other common questions about Gage R&R output in my next post!



Name: SURYA • Tuesday, April 10, 2012

Thanks for the explanation.Now I understood the meaning of number of distinct categories. We have to choose the components to the full length of tolerance ,so that the measuring tool measures or not accurately can be known.

Name: Jesus M • Thursday, February 21, 2013

This is a very clear explanation on this important feature of the gage R&R Thank you.

Name: Balasubramaniyan.S • Sunday, April 14, 2013

Hello, thanks for your explanation. Your explanation has made me clear of ndc.

Name: Vlad • Tuesday, April 30, 2013

Actually I have question.
I have total variation in % Tolerance column 126%.
Is it a good sign or not?

Name: Eston • Tuesday, April 30, 2013

Hi Vlad - Andy discussed %Tolerance in this post; I think it'll help you out: http://blog.minitab.com/blog/quality-data-analysis-and-statistics/how-to-interpret-gage-output-part-2

Name: Prakash • Wednesday, June 18, 2014

Thank you very much. Your explanation is super. Now my doubt is cleared.

blog comments powered by Disqus