Factors | Sum of squares | Degrees of freedom | Mean square | F-value | P-value | |
|---|
Model | 18368.05 | 5 | 3673.61 | 13.97 | 0.0016 | significant |
X
1
| 740.37 | 1 | 740.37 | 2.82 | 0.1373 | |
X
2
| 4796.85 | 1 | 4796.85 | 18.24 | 0.0037 | |
X
1
X
2
| 150.06 | 1 | 150.06 | 0.57 | 0.4747 | |
X
1
2
| 4654.76 | 1 | 4654.76 | 17.70 | 0.0040 | |
X
2
2
| 3230.99 | 1 | 3230.99 | 12.29 | 0.0099 | |
Residual | 1840.87 | 7 | 262.98 | | | |
Lack of fit | 1656.83 | 3 | 552.28 | 12.00 | 0.0181 | significant |
Pure error | 184.04 | 4 | 46.01 | | | |
Cor total | 20208.92 | 12 | | | | |
- aCoefficient of determination (R2) = 0.9089. A model with an F-value of 13.97 implies that the model is significant. There is only a 0.16% chance that a model F-value this large could occur due to noise. Values of “Prob>F” less than 0.0500 indicate that model terms are significant. In this case B, A2, B2 are significant model terms. The “Lack of fit F-value” of 12.00 implies that the lack of fit is significant. There is only a 1.81% chance that a lack of fit F-value this large could occur due to noise. The “Pred R-Squared” of 0.3684 is not as close to the “Adj R-Squared” of 0.8438 as one might normally expect. This may indicate a large block effect or a possible problem with a model and/or data. Things to consider are model reduction, response transformation, and outliers, among others. “Adeq Precision” measures the signal-to-noise ratio. A ratio greater than 4 is desirable. A ratio of 10.962 indicates an adequate signal. This model can be used to navigate the design space.
