I am trying to run a Mann Whitney tests for my data which is comparing contaminated and uncontaminated soil samples from different locations. The only place I am seeing that uses Mann Whitney is the Performing longitudinal and paired sample comparisons with q2-longitudinl tutorial. The issue with that is the command I don't have overlap between locations and if they are contaminated. Is there any other ways to run a Mann-Whitney analysis?
Hi @hmarti,
The generalized case of the Mann Whitney test is the Kruskal Wallis test, which is implemented in the alpha-group-significance command (Also see the PD Mouse Tutorial). As a quick reminder, Mann Whitney is not appropriate for differential abundance, and QIIME doesn't support a per-taxon Mann Whitney or Kruskal Wallis test.
Best,
Justine
3 Likes