Any time you measure the results of a process you will see some variation. This variation comes from two sources: one, there are always differences between parts made by any process, and two, any method of taking measurements is imperfect - thus, measuring the same part repeatedly does not result in identical measurements.

Use Gage R&R to determine what portion of the variability in measurements may be due to the measurement system. Measurement system variability includes both variation due to the gage and operator-to-operator variability.

This method is suitable for non-destructive testing. It can also be used for destructive tests when the following assumptions have been met:

·    All parts within a single batch are similar enough to claim they are the same part

·    All operators measure from each batch

An ANOVA method and an and R method are available for the crossed Gage R&R study. The calculations used in the and R method are simpler, however the ANOVA method is more accurate.

In a Gage R&R study, it is important that the measurements are done in a random order and that the parts selected provide a representative sample across the possible range of responses.

Ten parts representing the expected range of the process variation were selected. Three operators measured the thickness of each of the ten parts, two times per part, in a random order.

Data: Thickness.MTW (available in the Sample Data folder).