During the Data redundancy step, the following options are available on the
Data redundancy tab.
Element Name
Description
Method
Use the options in this group box to select a method for measuring the correlation coefficient between a pair of inputs. The correlation coefficient is used as criteria for deciding whether an input is redundant (excluded from the analysis) because another input contains the same information.
Correlation coefficient: Select the
Pearson's Product Moment Correlation Coefficient to test the strength of the relationship between continuous inputs and determine which variables are redundant (carry the same or similar information).
Spearman Rank Correlation R: Select the
Spearman Rank Correlation R statistic to determine redundancy among the continuous inputs.
Note: This nonparametric procedure is an approximation of Pearson's correlation coefficient based on ranked values of the data.
None: Select this if you do not want to apply a redundancy criterion to the data.
Criterion value
Specify the value of the correlation coefficient that must exist between an input pair so one of them can be considered redundant.