Specify the design for Create Response Surface Design (Central Composite)

Stat > DOE > Response Surface > Create Response Surface Design > Designs

In This Topic

Designs table
Number of center points
Value of Alpha
Number of replicates

Designs table

Select the number of experimental runs and the number of blocks for the base design. The number of experimental runs in the design also depends on the number of center points, the number of replicates, and the number of categorical factor levels. For more information on how Minitab blocks central composite designs, go to Blocks in a central composite design.

Number of center points

Select the number of center points for the design. Center points are experimental runs where all of the factors are set midway between their low and high levels. Each replicate of the design adds the same number of center points. Each level of a categorical factor also adds the same number of center points.

Default

Select this option to have Minitab determine the number of center points that makes orthogonal blocks. For designs without blocks, the default produces a rotatable design.

Custom

Select this option to specify the number of center points in the design. If the design has an axial block, then you can specify how many center points to add with the experimental runs in each type of block.

Cube block: Specify the number of center points to add in each block with the experimental runs at the high and low levels of the factors. If the design has multiple cube blocks, then Minitab divides the center points as evenly as possible into the blocks.
Axial block: Specify the number of center points to add in each block with the experimental runs at the axial levels of the factors.

Value of Alpha

Select the distance, in coded units, of each axial point from the center. For more information on alpha, go to Alpha.

Default: Choose to have Minitab determine the value of alpha so that the design makes orthogonal blocks. For designs without blocks, the default produces a rotatable design.
Face Centered: Choose to use the high and low levels of the factors for the axial points.
Custom: Choose to specify the value of alpha. A value less than 1 places the axial points inside of the cube. A value greater than 1 places the axial points outside of the cube.

Note

A value of F^0.25 guarantees rotatability. F is the number of factorial points in the design.

Number of replicates

Enter how many times to perform each experimental run that is in the base design. Usually, you consider the available resources and the purpose of your design when you select the number of replicates. You can add replicates to your design later with Stat > DOE > Modify Design. For more information on replicates, go to Replicates and repeats in designed experiments.

Block on replicates: Select whether to put each replicate in its own block. If the base design has blocks, then the total number of blocks is the product of the number of blocks in the base design and the number of replicates.