Select a D-optimal Design from a Factorial or a Central Composite Design mainline

This macro selects a D-optimal design from either a 2-level factorial design or a central composite design as the base design. This D-optimal design will be able to estimate all main effects, all 2-way interactions and, if a central composite base design is specified, all quadratics.

Download the Macro

Be sure that Minitab knows where to find your downloaded macro. Choose File > Options > General. Under Macro location browse to the location where you save macro files.

Important

If you use an older web browser, when you click the Download button, the file may open in Quicktime, which shares the .mac file extension with Minitab macros. To save the macro, right-click the Download button and choose Save target as.

Required Inputs

  • A column of factor names. You can have 2 to 11 factors for a factorial design, or 2 to 9 factors for a central composite.
  • A numeric column containing the low levels for each factor
  • A numeric column containing the high levels for each factor
Note

For a factorial design with text factors use the coded levels -1 for low and +1 for high. For a central composite design, the low and high levels are for the cube points and the factors are assumed to be continuous.

Running the Macro

  1. To run the macro choose View > Command Line/History and type the following:
    %customdoe
  2. Click Run. The macro will prompt you to select either a 2-level factorial base design (enter 1) or a central composite base design (enter 2). Next, the macro will prompt you to enter a number of runs.

The D-optimal design is stored in the same worksheet as the factor name and level columns beginning in columns C4 and beyond. Any data stored in these columns before the macro is run may be lost.

If a 2-level factorial base design is selected, when analyzing the experiment in Stat > DOE > Factorial > Analyze Factorial Design, click the Terms list and select Include terms up through order 2.

The Initial D-Optimal design is generated by Sequential Optimization. The Exchange method with 1 exchange point is employed for Improving the Initial Design.