Optimal is a good design choice when more flexibility is required. Unlike the simplex designs, where there is a specific pattern to the design points, points in this design are chosen by an algorithm to achieve a specific property. Because of this selection process and the fact that there are often many statistically equivalent sets of design points, it is possible to obtain slightly different designs for the same factor and model information.
Optimal designs are necessary when there are unequal component ranges, multi-component constraints, or a custom model is being fit to the responses.
Mixture Components: How many components are involved in this experiment?
Fillers may be components too unless their proportion of the mixture is held constant.
Components that will remain a constant proportion of the total can be added to the design by setting the low and high limits to the same value.
Total: The sum of all the components must equal the total for all runs.
Units: (optional) All components must use the same units of measurement.
Common units of measure include direct amounts (mass or volume), weight %, % volume by weight, and molecular equivalents.
Name: Provide names for the components to help with later documentation
Low: The lowest value a component can take (often zero).
High: The highest value a component can take (no larger than the Total)
Edit Constraints button: Click this button to impose additional constraints on component combinations allowed. For more details use the help button on the Edit Constraints dialog.