TABLE 4.

Power analysis protocol for a Kruskal–Wallis test using Shannon’s alpha metric.

Power analysis protocol: univariate case—alpha diversity
t-tests – Means: Wilcoxon–Mann–Whitney test (two groups)
Options:	A.R.E. method
Analysis:	A priori: compute required sample size
Input:	Tail(s)	= One
	Parent distribution	= Normal
	Effect size d	= 0.5
	Alpha metric	= Shannon
	α err prob	= 0.05
	Power (1 - β err prob)	= 0.8
	Allocation ratio N2/N1	= 1
Output:	Non-centrality parameter δ	= 2.51
	Critical t	= 1.66
	df	= 99.2
	Sample size group 1	= 53
	Sample size group 2	= 53
	Total sample size	= 106
	Actual power	= 0.803

This protocol is adapted from the protocol generated by the G*Power software (Faul et al., 2007).