Test - Nonparametric - Two-Sample Wilcoxon Rank Sum Test

Performs the Wilcoxon rank sum test to compare the median between two samples.

Technical details

Description

This test can be applied to two samples of equal or different sizes. For paired samples see Test - Nonparametric - Paired Samples Wilcoxon Test.

Inputs

• Outcome Variable containing the sample to analyze.
• Group Variable specifying the group that each observation comes from. Where this Variable is numeric, it is automatically grouped into two approximately-equally-sized groups, using the median.
• mu Difference in the median of the two samples, as assumed under the null hypothesis.
• Alternative hypothesis Use a two-sided or one-sided test.
• Type of test Method by which the p-value is computed.
• Output
  • Summary Shows a nicely formatted table of the test results (default).
  • R The original text-based output from the wilcox.test function.
• Variable names Display Variable Names in the output, instead of Variable Labels.
• More decimal places Display numeric values with 8 decimal places.

Output

 

Acknowledgements

Uses the wilcox.test function from the stats R package.

Method

• In Displayr: How to Perform Two-Sample Wilcoxon Rank Sum Test
• In Q: Create > Test > Nonparametric > Two-Sample Wilcoxon Test