I am willing to see whether there is a significant difference between my groups of samples. I was wondering:
what is the strengths and weaknesses of permanova test and what factors should I take into account when using this statistical test.
Please let me know if I need to provide any info about my data.
The PERMANOVA test has been around for a while now and so there is great materials online about its appropriate use and as well as some key assumptions. I recommend reading the original paper or at least this nice summary of the test which includes limitations.
The key limitations to be aware of are
a) your features are independent
b) Your group have similar multivariate dispersion. This one you an actually test by re-running your beta group significant test, but changing the default
permanova setting to
permdisp. Which then tests for multivariate dispersion.