Step 8: 筛选设计-标示重要效果
可以使用会话窗口输出和两个主效果图来帮助你决定那个效果对于过程来说是重要的。首先查看会话窗口输出
Factorial Fit: Yield versus Temp, Pressure, Catalyst
Estimated Effects and Coefficients for Yield (coded units)
Term Effect Coef SE Coef T P
Constant 74.81 2.561 29.21 0.000
Temp 1.38 0.69 2.561 0.27 0.795
Pressure 14.12 7.06 2.561 2.76 0.025
Catalyst -30.38 -15.19 2.561 -5.93 0.000
Temp*Pressure -0.13 -0.06 2.561 -0.02 0.981
Temp*Catalyst -1.13 -0.56 2.561 -0.22 0.832
Pressure*Catalyst -13.37 -6.69 2.561 -2.61 0.031
Temp*Pressure*Catalyst -0.13 -0.06 2.561 -0.02 0.981
S = 10.2439 R-Sq = 86.14% R-Sq(adj) = 74.01%
Analysis of Variance for Yield (coded units)
Source DF Seq SS Adj SS Adj MS F P
Main Effects 3 4496.19 4496.19 1498.73 14.28 0.001
2-Way Interactions 3 720.69 720.69 240.23 2.29 0.155
3-Way Interactions 1 0.06 0.06 0.06 0.00 0.981
Residual Error 8 839.50 839.50 104.94
Pure Error 8 839.50 839.50 104.94
Total 15 6056.44
Estimated Coefficients for Yield using data in uncoded units
Term Coef
Constant 60.6667
Temp 0.079167
Pressure 4.83333
Catalyst -2.6667
Temp*Pressure -0.004167
Temp*Catalyst -0.045833
Pressure*Catalyst -4.33333
Temp*Pressure*Catalyst -0.004167
Effects Plot for Yield
Effects Pareto for Yield
Alias Structure
I
Temp
Pressure
Catalyst
Temp*Pressure
Temp*Catalyst
Pressure*Catalyst
拟合了一个全因子模型，包含3个主效果，3个双向因子交互，1个3向因子交互。使用评估效果和系数表中的P列值来决定那个效果是有意义的。使用alpha=0.05，可以看到压力和催化剂的主效果，及压力和催化剂的交互效果的作用是显著的，他们的p值小于0.05。
