class skbio.math.stats.distance.ANOSIM(distance_matrix, grouping, column=None)[source]

ANOSIM statistical method executor.

Analysis of Similarities (ANOSIM) is a non-parametric method that tests whether two or more groups of objects are significantly different based on a categorical factor. The ranks of the distances in the distance matrix are used to calculate an R statistic, which ranges between -1 (anti-grouping) to +1 (strong grouping), with an R value of 0 indicating random grouping.


See [R60] for the original ANOSIM reference. The general algorithm and interface are similar to vegan::anosim, available in R’s vegan package [R61].


[R60](1, 2) Clarke, KR. “Non-parametric multivariate analyses of changes in community structure.” Australian journal of ecology 18.1 (1993): 117-143.
[R61](1, 2)


__call__([permutations]) Execute the statistical method.