|
Gage R&R Study (Expanded)ANOVA Table |
The results displayed in this ANOVA (analysis of variance) tells you if different levels of the factors result in different average values of a response variable.
You want to see if the p-value associated with each source of variation is less than the chosen level of significance. This would indicate that the source contributes significantly to measurement variability.
The ANOVA table lists the following sources of variability:
The results displayed in this ANOVA table will be used to compute the Gage R&R.
Example Output |
ANOVA Table with All Terms
Source DF Seq SS Adj SS Adj MS F P Part 21 1071.303 1071.303 51.014 6.46 0.000 Operator 2 32.178 32.178 16.089 3.27 0.164 x Station 1 11.247 11.247 11.247 3.50 0.202 Part*Operator 42 331.809 331.809 7.900 1.27 0.189 Operator*Station 2 6.433 6.433 3.217 0.52 0.598 Repeatability 63 390.527 390.527 6.199 Total 131 1843.497
x Not an exact F-test.
α to remove interaction term = 0.05
ANOVA Table with Terms Used for Gage R&R Calculations
Source DF Seq SS Adj SS Adj MS F P Part 21 1071.303 1071.303 51.014 7.49 0.000 Operator 2 32.178 32.178 16.089 2.36 0.099 Station 1 11.247 11.247 11.247 1.65 0.202 Repeatability 107 728.769 728.769 6.811 Total 131 1843.497 |
Interpretation |
When the p-value for an interaction is > 0.05, Minitab omits this interaction from the model. For the refraction data, the Part*Operator p-value is 0.189 and the Operator*Station p-value is 0.598 in the top ANOVA Table. Therefore, both of these interactions are omitted from the final model.
The second ANOVA table contains the terms used in the final Gage R&R calculations. Part (0.000) is a significant source of measurement variation at the a = 0.05 level of significance. However, Operator ( 0.099), and Station (0.202) are probably not significant sources of measurement variation.