Viewing Significance and Correlation Values

Significance of an input parameter to an output parameter is determined using a statistical hypothesis test. In the hypothesis test, a NULL hypothesis of insignificance is assumed, and is tested to see whether it is statistically true according to the significance level (or acceptable risk) set by the user. From the hypothesis test, a p-value (probability value) is calculated, and is compared with the significance level. If the p-value is greater than the significance level, it is concluded that the NULL hypothesis is true, and that the input parameter is insignificant to the output parameter, and vice versa. For more information, see Six Sigma Analysis (SSA) Theory.

If you select Sensitivities in the Outline view for the Six Sigma Analysis cell, you can review the sensitivities derived from the samples generated for the correlation. The correlation sensitivities are global sensitivities. In the Properties view for the Sensitivities chart, you can choose the output parameters for which you want to review sensitivities and the input parameters that you would like to evaluate for the output parameters.

On the Design Exploration tab of the Options dialog box, the default setting for Significance Level is 0.025. Parameters with a sensitivity value above this significance are shown with a flat line on the Sensitivities chart. The value displayed for these parameters when you place the mouse cursor over them on the chart is 0.

To view the actual correlation value of the insignificant parameter pair, you select Correlation Matrix in the Outline view and then place the mouse cursor over the square for that pair in the matrix. Or, you can set Significance Level to 1 in the Options dialog box, which bypasses the significance test and displays all input parameters on the Sensitivities chart with their actual correlation values.

In addition, linear information is shown in the Correlation Scatter chart and the general parameters correlation table. The Correlation Scatter chart displays both the quadratic trend line and the linear trend line equation for the selected parameter pair. The general parameters correlation table shows quadratic data, linear data, and correlation design points.


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