1.
Select DOE > Classical > Mixture Design.
Figure 12.12 Ranges for Five-factors
4.
Enter 4 in the Degree text box and click Extreme Vertices.
Figure 12.13 Display and Modify Panel for Extreme Vertices Example
6.
Note: The Find Subset option uses the row exchange method (not coordinate exchange) to find the optimal subset of rows.
Figure 12.14 Ten Run D-optimal Extreme Vertices Design
7.
Click Make Table.
8.
From the design table, select Graph >Ternary Plot.
9.
Select X1, X2, X3, X4, and X5 and click X, Plotting, and then click OK.
Figure 12.15 Partial Output of Ternary Plot for Five-Factor Design
Consider the classic example presented by Snee (1979) and Piepel (1988). This example has three factors, X1, X2, and X3, with factor bounds and three linear constraints.
1.
Select DOE > Classical > Mixture Design.
2.
Enter the values from Figure 12.16 for X1, X2, and X3 and click Continue.
Figure 12.16 Values and Linear Constraints for the Snee and Piepel Example
3.
Click Linear Constraint three times. Enter the constraints as shown in Figure 12.16.
4.
Click the Extreme Vertices button.
5.
Click Make Table.
6.
From the design table, select Graph >Ternary Plot.
7.
Select X1, X2, and X3 and click X, Plotting, and then click OK.
Figure 12.17 Ternary Plot Showing Piepel Example with Constraints
If there are linear constraints, JMP uses the CONSIM algorithm developed by R.E. Wheeler, described in Snee (1979) and presented by Piepel (1988) as CONVRT. The method is also described in Cornell (1990, Appendix 10a). The method combines constraints and checks to see whether vertices violate them. If so, it drops the vertices and calculates new ones. The method named CONAEV for doing centroid points is by Piepel (1988).
If there are no linear constraints (only range constraints), the extreme vertices design is constructed using the XVERT method developed by Snee and Marquardt (1974) and Snee (1975). After the vertices are found, a simplex centroid method generates combinations of vertices up to a specified order.
The XVERT method first creates a full 2nf 1 design using the given low and high values of the nf – 1 factors with smallest range. Then, it computes the value of the one factor left out based on the restriction that the factors’ values must sum to one. It keeps points that are not in factor’s range. If not, it increments or decrements the value to bring it within range, and decrements or increments each of the other factors in turn by the same amount. This method keeps the points that still satisfy the initial restrictions.
The above algorithm creates the vertices of the feasible region in the simplex defined by the factor constraints. However, Snee (1975) has shown that it can also be useful to have the centroids of the edges and faces of the feasible region. A generalized n-dimensional face of the feasible region is defined by nf – n of the boundaries and the centroid of a face defined to be the average of the vertices lying on it. The algorithm generates all possible combinations of the boundary conditions and then averages over the vertices generated on the first step.

Help created on 7/12/2018