You take 10 parts and have three operators measure each part two times. This standard approach to a gauge (or gage, if you prefer) repeatability and reproducibility (GR&R) experiment is so common, so accepted, so ubiquitous that few people ever question whether it is effective.

Obviously one could look at whether three operators are adequate or two replicates are adequate. But in this first article in a series about “gauging gage,” I want to look at 10—just 10 parts to measure. How accurately can you assess your measurement system with 10 parts?

Assessing a measurement system with 10 parts

I’m going to use a simple scenario as an example. I’m going to simulate the results of 1,000 GR&R studies with the following underlying characteristics:
1. There are no operator-to-operator differences, and no operator*part interaction.
2. The measurement system variance and part-to-part variance used would result in a %Contribution of 5.88 percent, between the popular guidelines: <1 percent is excellent and >9  percent is poor.

 …