The SAS System                       15:42 Thursday, October 29, 2015   1

                                                        The RSREG Procedure

                                          Coding Coefficients for the Independent Variables
 
                                              Factor    Subtracted off      Divided by

                                              temp           24.000000       10.092000
                                              ph              3.800000        0.672800
                                              inocsz         10.000000        8.410000


                                               Response Surface for Variable ethanol

                                              Response Mean                   7.755000
                                              Root MSE                        0.422003
                                              R-Square                          0.9714
                                              Coefficient of Variation          5.4417


                                                          Type I Sum
                              Regression          DF      of Squares    R-Square    F Value    Pr > F

                              Linear               3       13.137539      0.2106      24.59    <.0001
                              Quadratic            3       42.727344      0.6851      79.97    <.0001
                              Crossproduct         3        4.723750      0.0757       8.84    0.0037
                              Total Model          9       60.588632      0.9714      37.80    <.0001


                                                                      Sum of
                                       Residual           DF         Squares     Mean Square

                                       Total Error        10        1.780868        0.178087


                                                                                                      Parameter
                                                                                                       Estimate
                                                                Standard                             from Coded
                     Parameter        DF        Estimate           Error    t Value    Pr > |t|            Data

                     Intercept         1      -88.088035       12.223256      -7.21      <.0001        9.971758
                     temp              1        1.012243        0.283907       3.57      0.0051       -0.881673
                     ph                1       45.821999        5.543945       8.27      <.0001       -0.259746
                     inocsz            1       -0.036288        0.320992      -0.11      0.9122        1.369836
                     temp*temp         1       -0.026619        0.003087      -8.62      <.0001       -2.711146
                     ph*temp           1        0.067708        0.062167       1.09      0.3016        0.459733
                     ph*ph             1       -6.762575        0.694648      -9.74      <.0001       -3.061146
                     inocsz*temp       1       -0.007917        0.004973      -1.59      0.1425       -0.671917
                     inocsz*ph         1        0.356250        0.074600       4.78      0.0008        2.015751
                     inocsz*inocsz     1       -0.048229        0.004446     -10.85      <.0001       -3.411146


                                                        Sum of
                                 Factor     DF         Squares     Mean Square    F Value    Pr > F

                                 temp        4       17.654610        4.413653      24.78    <.0001
                                 ph          4       21.476444        5.369111      30.15    <.0001
                                 inocsz      4       34.529957        8.632489      48.47    <.0001
                                                           The SAS System                       15:42 Thursday, October 29, 2015   2

                                                        The RSREG Procedure
                                     Canonical Analysis of Response Surface Based on Coded Data

                                                                Critical Value
                                               Factor           Coded         Uncoded

                                               temp         -0.188955       22.093064
                                               ph            0.017305        3.811642
                                               inocsz        0.224511       11.888138

                                           Predicted value at stationary point: 10.206581


                                                                    Eigenvectors
                                     Eigenvalues            temp              ph          inocsz

                                       -2.209322       -0.095312        0.749458        0.655155
                                       -2.615383        0.966369        0.227577       -0.119747
                                       -4.358732        0.238844       -0.621708        0.745944

                                                   Stationary point is a maximum.