This section describes the Evaluate Design report. For complete details, see Creating a Custom Design in Building Custom Designs.
Lists the factors in the design and their roles (continuous, discrete numeric, categorical, blocking, covariate, mixture, constant, uncontrolled).
Lists the terms in the model that you want to fit using the results of the experiment. The buttons let you add or remove terms from the model.
Lists the alias terms included in the computation of the alias matrix, and for computing correlations between model terms and alias terms. The buttons let you add or remove terms from the list of alias terms. By default, second order interactions are included as alias terms.
Lists the factor level settings for the design. Gives a text column for Anticipated Responses. See The Design Report.
Gives diagnostics for assessing the design. A brief description of each section is given in Design Evaluation. Further details are in Understanding Design Evaluation.
The Design Evaluation report has several component reports that address various aspects of the design. For complete details, see Understanding Design Evaluation in Building Custom Designs.
The Power Analysis report (Power Analysis) allows you to calculate the power of tests for the parameters in your model. You can set values for your Significance Level, Anticipated RMSE, and Anticipated Coefficients. Click Apply Changes to Anticipate Coefficients to update the Power calculations. This action also updates the Anticipated Responses in the Design report. Alternatively, you can specify Anticipated Responses in the Design report. Then click Apply Changes to Anticipated Responses to update Power in the Power Analysis report.
The Prediction Variance Profile gives a profiler of the relative variance of prediction as a function of each factor at fixed values of the other factors. See Prediction Variance Profile. To see how the prediction variance changes, drag the vertical dotted lines of the factors. To find the maximum prediction variance in the design space, select Maximize Desirability on the red triangle menu.
The Fraction of Design Space Plot shows how much of the model prediction variance lies above (or below) a given value. See Fraction of Design Space Plot. This is most useful when there are multiple factors. It summarizes the prediction variance, showing the fractional design space for all the factors taken together.
The Prediction Variance Surface report plots the prediction variance surface as a function of the design factors. See Prediction Variance Surface. Show or hide the controls by selecting Control Panel on the red triangle menu.
For each parameter in the model, this report gives the Fractional Increase in CI (Confidence Interval) Length and Relative Std (Standard) Error of Parameters. (See Estimation Efficiency Report.)
This report shows the alias matrix for the model terms and the alias terms. In the Bounce Data.jmp example, the three two-way interactions were automatically added to the list of Alias Terms. Therefore, the Alias Matrix gives these three interactions as columns and shows the confounding of model terms with these columns (Alias Matrix). Note that the only confounding involves two-way interactions with themselves, which is expected.
The Color Map on Correlations shows the absolute value of the correlation between each model term and alias term. The Color Map on Correlations for the Bounce Data.jmp example is shown in Color Map on Correlations. The deep red coloring indicates correlations of one. Note that there are red cells on the diagonal, showing correlations of model terms with themselves. Three red cells off the main diagonal show the correlations of the Alias Terms with themselves. This is because those three terms appear both in the model and in the Alias Terms list.
Note: Terms that appear in both the model and Alias Terms list appear twice in the Color Map on Correlations.
All other cells are either deep blue or light blue, indicating no or little correlation. From the perspective of correlation, this is a good design.
The Design Diagnostics report shows D, G, and A Efficiency values, and the average variance of prediction. The design creation time gives the time taken to compute the various diagnostics.