Simplex Centroid Design¶
This mixture design can be used for 3 to 8 components. A simplex-centroid design consists of all points that are equally weighted mixtures of 1 to q components. Included are permutations of:
Pure blends: (1, 0, …,0)
Binary blends: (1/2, 1/2, 0, …,0)
Tertiary blends: (1/3, 1/3, 1/3, 0, …,0)
and so on to the overall centroid: (1/q, 1/q, …, 1/q).
This design differs from a simplex-lattice design. It cannot be used to estimate the full cubic model, but can be used to estimate a special cubic model.
The default augmentation for the simplex-centroid design adds check points (half-way between the overall center and each vertex).
Unlike the simplex-lattice, the simplex centroid does not require specification of a model order to pick the design points. However, Stat-Ease 360 provides a model selection option for picking replicates. It uses the model you pick to duplicate the highest leverage points. You can choose whether or not to augment, and how many replicates you want, if any.
See Also: