Requirements
 Two variables in your dataset that you want to test for correlation.
 You should use numeric variables as inputs. If you use categorical or ordinal variables, they will be coerced to numeric based on their values for the purposes of running the test.
Method
 From the toolbar menu, select Create > Test > Correlation.
 From the object inspector on the right, select your variables from the Variable 1 and Variable 2 dropdown box under Inputs.
 Two variables in your dataset that you want to test for correlation.
 You should use numeric variables as inputs. If you use categorical or ordinal variables, they will be coerced to numeric based on their values for the purposes of running the test.
 OPTIONAL: Select one of the following options for the Type of correlation:
 Pearson productmoment (default selection)  measures the strength and direction of a linear association between the two variables.
 Spearman rankorder  a nonparametric measure of the strength and direction of association that exists between two variables on an ordinal scale.
 Kendall's Taub  a nonparametric measure of the strength and direction of association that exists between two variables on an ordinal scale.
 Spearman rankorder and Kendall's Taub are rankbased measures of association which are useful when the data does not necessarily come from a bivariate normal distribution
 OPTIONAL: Select an Alternative hypothesis:

 Twosided (selected by default)
 Correlation < 0 (onesided test)
 Correlation > 0 (onesided test)
 OPTIONAL: Select one of the following Outputs:
 Summary (selected by default)  shows a nicely formatted table of the test results.
 R  the original textbased output from the cor.test function.
 OPTIONAL: Tick the Variable names check box to display variable names in the output instead of variable labels.
 Tick the More decimal places checkbox to display numeric values in the output with 8 decimal places.
 Click Calculate to run the test and generate the output.
Next
How to Create a Correlation Matrix