The Mann Whitney U test is a non-parametric statistical procedure designed to assess whether there is a significant difference between two independent samples by comparing their rank sums rather than means. Operating within the domain of hypothesis testing, it serves as the distribution-free alternative to the t-test for independent samples, specifically addressing scenarios where data does not adhere to normality assumptions or when the underlying measurement scale requires ranking. The test relies on the mechanism of converting raw observations into ranks and deriving a U statistic based on these rank sums to determine if one population tends to have larger values than the other under the null hypothesis that both distributions are identical.
Prerequisite chain context: requires Ordinal Variable Classification in Statistics.