[R-sig-eco] PERMANOVA on unbalanced designs

[Marc Taylor]

Dear r-sig-ecology listers,

I'm wondering if anyone has experience dealing with unbalanced designs and
heterogeneity in dispersions in PERMANOVA.  According to a study by
Anderson and Walsh (2013), when both of these situations exist, "none of
the tests (PERMANOVA, Mantel, or ANOSIM) behaved reliably for unbalanced
designs in the face of heterogeneity."

I imagine that some sort of resampling (bootstrapping?) might overcome the
unequal sample sizes - If this is possible, then the issue of heterogeneity
seems to be less of an issue for PERMANOVA. Is anyone familiar with an
approach of this type, or perhaps another procedure?

All the best,
Marc

Reference:
Anderson, M. J., & Walsh, D. C. (2013). PERMANOVA, ANOSIM, and the Mantel
test in the face of heterogeneous dispersions: What null hypothesis are you
testing?. *Ecological Monographs*, *83*(4), 557-574.

	[[alternative HTML version deleted]]