SAS中文论坛

标题: 请教 [打印本页]

作者: shiyiming 时间: 2004-12-13 14:56
标题: 请教
The SAS System    10:48 Thursday, December 13, 2001 1

                                       The RSREG Procedure

                        Coding Coefficients for the Independent Variables

                           Factor Subtracted off    Divided by

                           x1          22.500000    12.500000
                           x2          170.000000    50.000000
                           x3          35.000000    25.000000

                                 Response Surface for Variable y

                           Response Mean                0.426333
                           Root MSE                            .
                           R-Square                         1.0000
                           Coefficient of Variation             .

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

            Linear             3       0.000433    0.5377       .    .
            Quadratic          1    0.000000762    0.0009       .    .
            Crossproduct       1       0.000372    0.4614       .    .
            Total Model       5       0.000805    1.0000       .    .

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

            Lack of Fit       0             0             .       .    .
            Pure Error       0             0             .
            Total Error       0             0             .

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

      Intercept    1    -0.407071             .       .       .          0.455438
      x1          1       0.047964             .       .       .          -0.000179
      x2          1       0.003450             .       .       .          0.008571
      x3          1       0.000436             .       .       .          0.010893
      x1*x1       1    -0.000516             .       .       .          -0.080580
      x2*x1       1    -0.000146             .       .       .          -0.091071
      x2*x2       0             0             .       .       .                0
      x3*x1       0             0             .       .       .                0
      x3*x2       0             0             .       .       .                0
      x3*x3       0             0             .       .       .                0

                                          The SAS System    10:48 Thursday, December 13, 2001 2

                                       The RSREG Procedure

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

               x1       3       0.000372       0.000124       .    .
               x2       2       0.000564       0.000282       .    .
               x3       1       0.000310       0.000310       .    .

                                          The SAS System    10:48 Thursday, December 13, 2001 3

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

                                             Critical Value
                              Factor          Coded       Uncoded

                              x1          0.094118    23.676471
                              x2          -0.168512    161.574394
                              x3                0    35.000000

                           Predicted value at stationary point: 0.454707

                                                   Eigenvectors
                  Eigenvalues             x1             x2             x3

                     0.020511    -0.410699       0.911771             0
                              0             0             0       1.000000
                     -0.101091       0.911771       0.410699             0

                              Stationary point is in a flatness.
                              Stationary point is a saddle point.
请教：上表中的“点号”是什么意思？？？
这个二次型回归有意义吗？
谢谢啦

欢迎光临 SAS中文论坛 (http://mysas.net/forum/)