snwikaij/GRASS: GRadient AnalySiS for ecologists

The GRASS package has multiple functions. The basic of some functions relies on the Area Under the Curve (AUC). The AUC gives the probability random sample of taxon from distribution x will rank higher than a sample from distribution y. The AUC is addapted so that it can be used to analyse the variation around a single gradient (i.e. after multivariate analysis). This can be used to answer the question, “how likely are we to find a specific taxon deviating from the other taxa (residual assembly).” The threshold indiction functions are used to identify thresholds in prescence/abscence data. These function uses the cumulative sum principle to detect changes in precence/abscence in relation to the sample distribution. These functions also have the ability to incorporate the AUC as selection criteria. The random forest model function is a simplification of the functions used in the randomForest and party packages. It creates a training and validation dataset. Based on the training dataset it determines the relative importance of the used predictor variables. Also, it computes a single tree based on the training dataset with the ctree function. And, it computes accuracy measures of the model based on the rel and caret packages. All functions in this package use present and absent (presence/absence) information.

install.packages("remotes")
remotes::install_github("snwikaij/GRASS")