Fit Summary

Response 4: angle

Source Sequential p-value Lack of Fit p-value Adjusted R² Predicted R²

Linear 0.1614 0.0050 0.1006 -0.4185
2FI 0.0102 0.0184 0.4308 -0.8457
Quadratic 0.0094 0.0835 0.6750 -0.7359 Suggested
Cubic 0.0965 0.1755 0.8172 Aliased

Sequential Model Sum of Squares [Type I]

Response 4: angle

Source Sum of Squares df Mean Square F-value p-value

Mean vs Total 3.826E+05 1 3.826E+05
Block vs Mean 2.16 1 2.16
Linear vs Block 119.59 3 39.86 1.89 0.1614
2FI vs Linear 202.13 3 67.38 5.06 0.0102
Quadratic vs 2FI 125.62 3 41.87 5.51 0.0094 Suggested
Cubic vs Quadratic 79.83 7 11.40 2.67 0.0965 Aliased
Residual 34.21 8 4.28
Total 3.832E+05 26 14737.23

Select the highest order polynomial where the additional terms are significant and the model
is not aliased.

Model Summary Statistics

Source Std. Dev. R² Adjusted R² Predicted R² PRESS

Linear 4.59 0.2130 0.1006 -0.4185 796.31
2FI 3.65 0.5731 0.4308 -0.8457 1036.16
Quadratic 2.76 0.7969 0.6750 -0.7359 974.48 Suggested
Cubic 2.07 0.9391 0.8172 * Aliased

 Case(s) with leverage of 1.0000: PRESS statistic not defined.

Focus on the model maximizing the Adjusted R² and the Predicted R².
Lack of Fit Tests

Source Sum of Squares df Mean Square F-value p-value

Linear 415.96 14 29.71 8.05 0.0050
2FI 213.83 11 19.44 5.27 0.0184
Quadratic 88.21 8 11.03 2.99 0.0835 Suggested
Cubic 8.38 1 8.38 2.27 0.1755 Aliased
Pure Error 25.83 7 3.69

The selected model should have insignificant lack-of-fit.

ANOVA for Quadratic model

Response 4: angle

Source Sum of Squares df Mean Square F-value p-value

Block 2.16 1 2.16
Model 447.34 9 49.70 6.54 0.0008 significant
A-Current 51.43 1 51.43 6.77 0.0201
B-Volatage 108.84 1 108.84 14.32 0.0018
C-Gas flow 1.09 1 1.09 0.1432 0.7104
AB 91.64 1 91.64 12.05 0.0034
AC 0.1430 1 0.1430 0.0188 0.8927
BC 78.39 1 78.39 10.31 0.0058
A² 16.87 1 16.87 2.22 0.1571
B² 71.14 1 71.14 9.36 0.0080
C² 0.8114 1 0.8114 0.1067 0.7484
Residual 114.04 15 7.60
Lack of Fit 88.21 8 11.03 2.99 0.0835 not significant
Pure Error 25.83 7 3.69
Cor Total 563.54 25

Factor coding is Coded.

Sum of squares is Type III - Partial

The Model F-value of 6.54 implies the model is significant. There is only a 0.08% chance
that an F-value this large could occur due to noise.

P-values less than 0.0500 indicate model terms are significant. In this case A, B, AB, BC, B²
are significant model terms. Values greater than 0.1000 indicate the model terms are not
significant. If there are many insignificant model terms (not counting those required to
support hierarchy), model reduction may improve your model.
The Lack of Fit F-value of 2.99 implies there is a 8.35% chance that a Lack of Fit F-value
this large could occur due to noise. Lack of fit is bad -- we want the model to fit. This
relatively low probability (<10%) is troubling.

Fit Statistics

Std. Dev. 2.76 R² 0.7969

Mean 121.31 Adjusted R² 0.6750
C.V. % 2.27 Predicted R² -0.7359
Adeq Precision 12.3775

A negative Predicted R² implies that the overall mean may be a better predictor of your
response than the current model. In some cases, a higher order model may also predict better.

Adeq Precision measures the signal to noise ratio. A ratio greater than 4 is desirable. Your
ratio of 12.378 indicates an adequate signal. This model can be used to navigate the design
space.

Model Comparison Statistics

PRESS 974.48
-2 Log Likelihood 112.22
BIC 148.06
AICc 153.08

Coefficients in Terms of Coded Factors

Factor Coefficient Estimate df Standard Error 95% CI Low 95% CI High VIF
Intercept 122.03 1 1.01 119.88 124.18
Block 1 1.12 1
Block 2 -1.12
A-Current -2.78 1 1.07 -5.07 -0.5026 4.42
B-Volatage -4.35 1 1.15 -6.80 -1.90 1.56
C-Gas flow 0.4017 1 1.06 -1.86 2.66 1.80
AB -4.47 1 1.29 -7.22 -1.73 1.65
AC 0.1671 1 1.22 -2.43 2.76 1.89
BC 3.25 1 1.01 1.09 5.40 1.11
A² 0.8467 1 0.5684 -0.3649 2.06 3.04
B² -5.03 1 1.64 -8.53 -1.52 2.09
C² -0.5428 1 1.66 -4.08 3.00 2.22
The coefficient estimate represents the expected change in response per unit change in factor
value when all remaining factors are held constant. The intercept in an orthogonal design is
the overall average response of all the runs. The coefficients are adjustments around that
average based on the factor settings. When the factors are orthogonal the VIFs are 1; VIFs
greater than 1 indicate multi-colinearity, the higher the VIF the more severe the correlation of
factors. As a rough rule, VIFs less than 10 are tolerable.

Final Equation in Terms of Coded Factors

angle =
+122.03
-2.78 A
-4.35 B
+0.4017 C
-4.47 AB
+0.1671 AC
+3.25 BC
+0.8467 A²
-5.03 B²
-0.5428 C²

The equation in terms of coded factors can be used to make predictions about the response for
given levels of each factor. By default, the high levels of the factors are coded as +1 and the
low levels are coded as -1. The coded equation is useful for identifying the relative impact of
the factors by comparing the factor coefficients.

Final Equation in Terms of Actual Factors

angle =
-562.65067
+1.59034 Current
+64.48217 Volatage
-13.26579 Gas flow
-0.149077 Current * Volatage
+0.005571 Current * Gas flow
+0.811981 Volatage * Gas flow
+0.003763 Current²
-1.25719 Volatage²
-0.135689 Gas flow²

The equation in terms of actual factors can be used to make predictions about the response for
given levels of each factor. Here, the levels should be specified in the original units for each
factor. This equation should not be used to determine the relative impact of each factor
because the coefficients are scaled to accommodate the units of each factor and the intercept
is not at the center of the design space.
Report

Influence
Internally Externally
Run Actual Predicted Cook's on Fitted Standard
Residual Leverage Studentized Studentized
Order Value Value⁽¹⁾ Distance Value Order
Residuals Residuals
DFFITS
1 123.00 125.13 -2.13 0.443 -1.034 -1.036 0.077 -0.924 14
2 120.00 123.15 -3.15 0.140 -1.231 -1.254 0.022 -0.507 11
3 100.00 103.00 -3.00 0.821 -2.571 -3.321 2.751⁽²⁾ -7.106⁽²⁾ 4
4 122.00 121.26 0.7393 0.305 0.322 0.312 0.004 0.206 16
5 123.00 119.34 3.66 0.623 2.164 2.520 0.702 3.238⁽²⁾ 8
6 120.00 117.85 2.15 0.810 1.791 1.952 1.247⁽²⁾ 4.035⁽²⁾ 3
7 123.00 123.15 -0.1478 0.140 -0.058 -0.056 0.000 -0.023 20
8 123.00 122.81 0.1888 0.144 0.074 0.072 0.000 0.029 19
9 120.00 120.86 -0.8591 0.137 -0.335 -0.325 0.002 -0.130 10
10 121.00 121.78 -0.7798 0.908⁽³⁾ -0.932 -0.928 0.780 -2.916⁽²⁾ 6
11 125.00 122.31 2.69 0.142 1.052 1.056 0.017 0.429 15
12 125.00 122.20 2.80 0.383 1.291 1.323 0.094 1.042 13
13 124.00 125.20 -1.20 0.753 -0.876 -0.869 0.213 -1.517 2
14 120.00 122.31 -2.31 0.142 -0.906 -0.900 0.012 -0.366 17
15 120.00 121.26 -1.26 0.305 -0.548 -0.535 0.012 -0.354 12
16 126.00 124.10 1.90 0.540 1.018 1.020 0.111 1.105 1
17 123.00 121.26 1.74 0.305 0.756 0.745 0.023 0.493 9
 18 120.00 118.07 1.93 0.818 1.643 1.752 1.105⁽²⁾ 3.720⁽²⁾ 5
19 123.00 123.15 -0.1478 0.140 -0.058 -0.056 0.000 -0.023 18
20 122.00 124.81 -2.81 0.642 -1.706 -1.836 0.475 -2.460⁽²⁾ 7
21 123.00 122.51 0.4902 0.255 0.206 0.199 0.001 0.117 25
22 120.00 123.76 -3.76 0.412 -1.778 -1.933 0.201 -1.617 21
23 125.00 122.51 2.49 0.255 1.046 1.050 0.034 0.614 26
24 120.00 117.86 2.14 0.652 1.318 1.354 0.296 1.853 22
25 123.00 122.51 0.4902 0.255 0.206 0.199 0.001 0.117 24
26 120.00 121.85 -1.85 0.531 -0.982 -0.981 0.099 -1.044 23

⁽¹⁾ Predicted values include block corrections.

⁽²⁾ Exceeds limits.

⁽³⁾ Observation with leverage > 2.00 × (average leverage).