A computational tool designed to execute a non-parametric statistical hypothesis test for assessing whether two related samples have distributions with equal medians is readily available. This specific test, applicable when data are at least ordinal, compares the ranks of the differences between paired observations. For example, researchers might utilize this to determine if a training program significantly alters employee performance scores, by comparing scores before and after the program’s implementation.
The significance of such a tool lies in its capacity to analyze data where the assumptions of parametric tests, such as normality, are not met. This offers a more robust analysis when dealing with non-normally distributed data, or ordinal data, commonly encountered in social sciences, medical research, and other fields. Historically, these tests were performed manually using tables, a process that was both time-consuming and prone to error. Automated computation significantly enhances efficiency and accuracy.
