gdm.cv: Performs n-fold cross-validation of GDM model

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

Description

This function performs n-fold cross-validation of a GDM model.

It requires a combined site pair ("spData" format) dataset, as well as the definition of the number of folds to be used in the cross-validation, the performance measure to be used and the optional use of geographical distance as predictor variable in the GDM.

For more details relating to "spData" data format, check gdm package.

Usage

gdm.cv(spData, nfolds = 10, performance = "rmse", geo = F)

Arguments

spData	Combined site pair dataset ("spData" format).
nfolds	Number of folds for cross-validation. Default is 10 folds. If number of folds equals number of samples then leave-one-out cross-validation is performed.
performance	Performance metric to be used for validation: "rmse" for root mean square error (RMSE) or "r2" for coefficient of determination (r2). Set as "rmse" per default.
geo	Optional use of geographical distance as predictor in GDM model. set to FALSE per default.

Value

Returns model performance value.

sparsegdm/sgdm_package documentation built on May 30, 2019, 6:35 a.m.