Using the Correlation Matrix Chart

The Correlation Matrix chart is a visual rendering of information in the parameters correlation table. The correlation coefficient indicates if there is a relationship between two variables and whether the relationship is a positive or negative number.

Color-coding of the cells indicates the strength of the correlation. The correlation value is displayed when you place the mouse cursor over a cell. The closer the absolute correlation value is to 1, the stronger the relationship. A value of 1 indicates a positive correlation, which means that when the first parameter increases, the second parameter increases as well. A value of -1 indicates a negative correlation, which means that when the first parameter increases, the second parameter decreases.

When you run a Pearson's correlation, the square of the correlation value corresponds to the R2 of the linear fitting between the pair of parameters. When you run a Spearman's correlation, the correlation value corresponds to the R2of the linear fitting between rank values of the pair of parameters. For more information on these correlation types, see Sample Generation.

In the following parameters correlation table, input parameter P13-PIPE_Thickness is a major input with a strong impact on the design.

On the other hand, input parameter P12-Hoop Dist is not important to the study because it has little impact on the outputs. In this case, you might want to disable P12-Hoop Dist by clearing the Enabled check box in the Properties view. When the input is disabled, the chart changes accordingly.

To disable parameters, you can also right-click a cell corresponding to that parameter and select the desired option from the context menu. You can disable the selected input, disable the selected output, disable all other inputs, or disable all other outputs.

To generate a Correlation Scatter chart for a given parameter combination, right-click the corresponding cell in the correlation matrix chart and select Insert <x-axis> vs <y-axis> Correlation Scatter.

If desired, you can export the correlation matrix data to a CSV file by selecting the Export Chart Data as CSV context option. For more information, see Exporting Design Point Parameter Values to a CSV File in the ANSYS Workbench documentation.


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