The discrimination ratio is the number of distinct categories discernible by the gage. A value of two, for instance, indicates the gage is useful for only attribute analysis, since it can only effectively classify the parts as being in one group or the other (for example, good or bad). AIAG recommends a value of three or more, and typically a value of eight or more is suitable for SPC analysis. The number of classes is obtained by determining the amount of part-to-part variation that is indistinguishable from measurement error. The discrimination ratio can be calculated using the formula shown here, or more easily by your SPC software or gage calibration software
.![]()
where PV is the Part Variation and R&R is the Gage Repeatability and Reproducibility error estimates.