Predicted vs. Observed Chart

The Predicted vs Observed scatter chart shows the values predicted from the response surface versus the values observed from the design points. This chart enables you to quickly determine if the response surface correctly fits the points of the design points table and refinement table. The closer the points are to the diagonal line, the better the response surface fits the points.

To view the Predicted vs. Observed chart, select either Goodness of Fit or Verification Points under the Quality node of the response surface Outline view. An instance of the chart is available for each Goodness of Fit analysis. The display is determined by your selections in the Properties view.

By default, all of the output parameters are displayed on the chart and the output values are normalized. However, if only one output parameter is plotted, the values are not normalized.

Verification points are not taken into account to build the response surface, so if they appear close to the diagonal line, the response surface is correctly representing the parametric model. Otherwise, it means that there is not enough data provided for the response surface to catch the parametric behavior of the model: you must refine the response surface.

If you position the mouse cursor over a point of the chart, the corresponding parameter values appear in the Properties view, including the predicted and observed values for the output parameters.

If you right-click a point of the chart, you can select from the context menu options available for that point. For example, you can insert the point as a refinement point or response point in the response surface table, which is a good way to improve the response surface around a verification point with an insufficient Goodness of Fit.


Release 18.2 - © ANSYS, Inc. All rights reserved.