gdm.varsig: Calculates statistical significance of predictor variable...

In steppebird/sparsegdm: Package for performing sparse generalized dissimilarity model including tools for gdm

Description

This function calculates the statistical significance of predictor variable contributions in GDM model, as calculated with the gdm.varcont function.

Significance is calculated through random matrix permutations, to infer if the variable (drop) contributions are greater than those obtained by chance.

It requires a biological ("bioData" format) and a predictor ("spData" format) datasets, the optional use of geographical distance as predictor variable in the GDM, the number of permutations to be run and the significance level to be tested.

This current implementation only allows biological data in the format 1 using abundance values, as described in the gdm package.

For more details relating to "bioData" and "predData" data formats, check gdm package.

Usage

gdm.varsig(predData, bioData, geo = F, perm = 100, sig = 0.05)

Arguments

predData	Predictor dataset ("predData" format).
bioData	Biological dataset ("bioData" format).
geo	Optional use of geographical distance as predictor in GDM model. Set to FALSE per default
perm	Number of matrix permutations to be used for calculating statistical significance.
sig	Significance level (p-value) to be tested. Set as 0.05 per default.

Value

Returns vector resulting of the significance test. Variables with significant model contributions are assigned value TRUE, and non-significant variables the value FALSE, according to the defined p-value threshold.

steppebird/sparsegdm documentation built on May 16, 2019, 2:55 a.m.