perm_disper: Permutational Dispersion Analysis
In jfq3/QsNullModels: My null model functions

Description Usage Arguments Details Value Author(s) References

This function tests if the dispersion about a group centroid is significantly different from null model expectation. It makes the test using Jaccard distances and randomizes the matrix using the randomize_by_row function. It is based on the procedure used in Zhou et al. (2014).

1	perm_disper(com, w, n.reps=999)

`com`	A binary community matrix with samples in rows and taxa in columns.
`w`	Sampling weights.
`n.reps`	Number of replications.

The binary community matrix is randomized using the function randomize_by_rows. Sampling weights are species sums by default, but may be specified differently by the user. This method maintains sample sums (species richness) and constrains species occurrences.

Result of vegan's betadisper test between observed and null model expectation.

John Quensen

Zhou, J. Z., Y. Deng, P. Zhang, K. Xue, Y. T. Liang, J. D. Van Nostrand, Y. F. Yang, Z. L. He, L. Y. Wu, D. A. Stahl, T. C. Hazen, J. M. Tiedje, and A. P. Arkin. 2014. Stochasticity, succession, and environmental perturbations in a fluidic ecosystem. Proceedings of the National Academy of Sciences of the United States of America 111:E836-E845. @importFrom vegan vegdist, betadisper

jfq3/QsNullModels documentation built on April 6, 2020, 2:06 p.m.