Optimal Design Result: Mixture (No Intercept) - Confounding Tab

Select the Confounding tab of the Optimal Design Result: Mixture (No Intercept) dialog box to access options to review the correlation matrix for the design matrix, and thus to determine the confounding of main effects and interactions.

Summary: Efficiency measures

Click this button to produce a spreadsheet containing the summary of efficiency measures. For a description of these efficiency measures, see Efficiency Measures for D- and A-Optimal Designs. For a discussion of the different optimality criteria, refer to the Introductory Overview.

Triangular scatterplot

Click the Triangular scatterplot button to produce a triangular scatterplot of the design points. If there are more than three factors in the current design, after clicking the button, the Select factors for 3D Scatterplot dialog box will be displayed. In this dialog box, select the three factors for the 3D scatterplot. Note that this scatterplot shows not only points for which the sum of the components is equal to the mixture total, but also "projected" points. If there are only three factors in the design, then the sum of the component values are, of course, always equal to the mixture total. However, if there are more than three variables in the design, then the scatterplot also shows those points where the values for the components in the plot is not equal to the mixture total (but greater than 0). The values for those points are proportionately adjusted in the plot (maintaining the ratio of the component values), so that they add to the mixture total.

Correlation matrix (no intercept)

Click this button to produce a correlation matrix of the columns of the current design matrix. If the current design is a mixture design, then these coefficients are computed without the intercept, that is, as the standardized sums of the raw cross-products.

Inverse of correlation matrix

Click this button to produce 1) the inverse of the correlation matrix, and 2) the standardized inverse of that correlation matrix. This matrix can be interpreted as the correlation matrix of effects; that is, it is the standardized variance/covariance matrix of the parameter estimates for the current model. The greater the absolute value of a correlation between effects in this matrix, the more redundant are the respective effects.