The binomial example in the landmap help for train.spLearner do not estimate the model error

[ManuelSpinola]

Related to the previous question, I tried the binomial example in the landmap help but it does not estimate the model error.

eberg$Parabraunerde <- ifelse(eberg$TAXGRSC=="Parabraunerde", 1, 0) X <- eberg_grid[c("PRMGEO6","DEMSRT6","TWISRT6","TIRAST6")] mB <- train.spLearner(eberg["Parabraunerde"], covariates=X, family=binomial(), cov.model = "nugget", parallel=FALSE) eberg.Parabraunerde <- predict(mB)

eberg.Parabraunerde$pred Object of class "SpatialPixelsDataFrame" (package sp):

Grid parameters: cellcentre.offset cellsize cells.dim x 3570050 100 100 y 5708050 100 100

Variables measured: prob.0 prob.1 response error.0 error.1 1 0.8300358 0.16996416 0 NA NA 2 0.8251524 0.17484764 0 NA NA 3 0.8216094 0.17839064 0 NA NA 4 0.9327373 0.06726271 0 NA NA 5 0.9327373 0.06726271 0 NA NA 6 0.9327373 0.06726271 0 NA NA ...