Gage R&R Study (Crossed)

ANOVA Method
Gage R&R - Variability

  

The Gage R&R output shows how the total variability is divided up among the following sources:

·    Total Gage R&R, which can be broken into

-    Repeatability, which is the variability in measurements obtained when the same part is measured multiple times by the same operator.

-    Reproducibility, (which can be divided further into Operator and Operator*Part components), which is the variability in measurements obtained when the same part is measured by different operators.

·    Part-To-Part, which is the variability in measurements across different parts.

Ideally, very little of the variability should be due to repeatability and reproducibility; instead, differences between parts (Part-to-Part) should account for most of the variability. This would be shown by:

·    A small %Contribution for the sources Repeatability and Reproducibility.

·    A large %Contribution for the source Part-to-Part.

The most important information is found in the %Contribution, %Study Var, %Tolerance, and %Process columns. These columns show the sources of variation. Typically, the Total Gage R&R should equal less than 30% of the study variation, and less than 10% would be ideal.

If you entered a process tolerance, an upper or lower specification limit, or a historical standard deviation, then either the %Tolerance or the %Process column may be more important than %Study Var.

Example Output

                              %Contribution

Source             VarComp     (of VarComp)

Total Gage R&R     0.0044375          10.67

  Repeatability    0.0012917           3.10

  Reproducibility  0.0031458           7.56

    Operator       0.0009120           2.19

    Operator*Part  0.0022338           5.37

Part-To-Part       0.0371644          89.33

Total Variation    0.0416019         100.00

 

 

Process tolerance = 1

Historical standard deviation = 0.174757

 

 

                                Study Var  %Study Var  %Tolerance   %Process

Source              StdDev(SD)   (6 × SD)       (%SV)  (SV/Toler)  (SV/Proc)

Total Gage R&R        0.066615    0.39969       32.66       39.97      38.12

  Repeatability       0.035940    0.21564       17.62       21.56      20.57

  Reproducibility     0.056088    0.33653       27.50       33.65      32.09

    Operator          0.030200    0.18120       14.81       18.12      17.28

    Operator*Part     0.047263    0.28358       23.17       28.36      27.04

Part-To-Part          0.192781    1.15668       94.52      115.67     110.31

Total Variation       0.203965    1.22379      100.00      122.38     116.71

Interpretation

For the parts data, the Total Gage R&R equals 32.66% of the study variation. It appears as if some corrective action should be taken. This action may include training of operators or acquiring better gages.