Prscores {GeoModels}

Computation of three predictive scores: RMSE, LSCORE, CRPS based on drop-one cross-validation prediction for spatial, spatiotemporal and bivariate Gaussian RF.

Description

The function computes RMSE, LSCORE, CRPS predictive scores.

Usage

Prscores(data,  method="cholesky", matrix)

Arguments

data

A d-dimensional vector (a single spatial realisation) or a a(t \times d)-matrix (a single spatial-temporal realisation). or a a(2 \times d)-matrix (a single bivariate realisation).

method

String; the type of matrix decomposition used in the computation of the predictive scores. Default is cholesky. The other possible choices is svd.

matrix

An object of class GeoCovmatrix. See the Section Details.

Details

For a given covariance matrix object (GeoCovmatrix) and a given spatial, spatiotemporal or bivariare realization from a Gaussian random field, the function computes three predictive scores.

Value

Returns a list containing the following informations:

RMSE

Root-mean-square error predictive score

MAE

Mean absolute error predictive score

LSCORE

Logarithmic predictive score

CRPS

Continuous ranked probability predictive score

Author(s)

Moreno Bevilacqua, [e-mail],https://sites.google.com/view/moreno-bevilacqua/home, Víctor Morales Oñate, [e-mail], https://sites.google.com/site/moralesonatevictor/, Christian", Caamaño-Carrillo, [e-mail],https://www.researchgate.net/profile/Christian-Caamano

References

Zhang H. and Wang Y. (2010). Kriging and cross-validation for massive spatial data. Environmetrics, 21, 290–304. Gneiting T. and Raftery A. Strictly Proper Scoring Rules, Prediction, and Estimation. Journal of the American Statistical Association, 102

See Also

GeoCovmatrix

Examples

library(GeoModels)
library(fields)

################################################################
######### Examples of predictive score computation  ############
################################################################

  # Define the spatial-coordinates of the points:
x <- runif(500, 0, 2)
y <- runif(500, 0, 2)
coords=cbind(x,y)
matrix1 <- GeoCovmatrix(coordx=coords, corrmodel="Matern", param=list(smooth=0.5,
                      sill=1,scale=0.2,nugget=0))
 
data <- GeoSim(coordx=coords, corrmodel="Matern", param=list(mean=0,smooth=0.5,
                      sill=1,scale=0.2,nugget=0))$data

Pr_scores <- Prscores(data,matrix=matrix1)

Pr_scores