Design points, factorial design

Include corner points (or cube points) and center points. Points on the diagram below represent combinations of factor levels in a two-factor design.

·    Corner points - represent experimental run when all factors are set at their highest or lowest level. For example, In a 2-factor design, the point on the upper right corner represents the experimental run when factor A is set at its high level and factor B is also set at its high level (1, 1).

·    Center points - represent experimental runs with all factor levels set halfway between the low and high settings.  

True center points can only be used with numeric factors set at the midpoint between the two chosen levels. If you have a combination of categorical and numeric factors, Minitab creates pseudo-center points. These points are the center points for numerical factors at each combination of the levels of the categorical factors.

Adding center points to a design checks for curvature in the response surface. If curvature exists, the response at the center point is either higher or lower than the average response at the factorial (corner) points. Curvature is usually present when factor settings are near an maximum or minimum response value.

You can also use center points to estimate variability without having to replicate all corner points.