compare.cv {automap}  R Documentation 
Allows comparison of the results from several outcomes of autoKrige.cv
in both statistics and spatial plots
(bubble plots).
compare.cv(..., col.names, bubbleplots = FALSE, zcol = "residual", layout, key.entries, reference = 1, plot.diff = FALSE, digits = 4, ggplot = FALSE, addPoly = NULL)
... 

col.names 
Names for the different objects in 
bubbleplots 
logical, if 
zcol 
Which column in the objects in 
layout 

key.entries 
A list of numbers telling what the key entries in the bubbleplots are. See 
reference 
An integer telling which of the objects should be taken as a reference if 
plot.diff 
logical, if 
digits 
The number of significant digits in the resulting data.frame. 
ggplot 
logical, determines if spplot or ggplot2 is used to make the spatial plot of the crossvalidation residuals.
Note that the 
addPoly 
if this object contains a 
A data.frame with for each crossvalidation result a number of diagnostics:
mean_error 
The mean of the crossvalidation residual. Ideally small. 
me_mean 
mean error divided by the mean of the observed values, measure for how large the mean_error is in contrast to the mean of the dataset 
MSE 
Mean Squared error. 
MSNE 
Mean Squared Normalized Error, mean of the squared zscores. Ideally small. 
cor_obspred 
Correlation between the observed and predicted values. Ideally 1. 
cor_predres 
Correlation between the predicted and the residual values. Ideally 0. 
RMSE 
Root Mean Squared Error of the residual. Ideally small. 
RMSE_sd 
RMSE divided by the standard deviation of the observed values. Provides a measure variation of the residuals vs the variation of the observed values. 
URMSE 
Unbiased Root Mean Squared Error of the residual. Ideally small. 
iqr 
Interquartile Range of the residuals. Ideally small. 
Paul Hiemstra, paul@numbertheory.nl
krige.cv
, bubble
, autofitVariogram
, autoKrige.cv
,
# Load the data data(meuse) coordinates(meuse) = ~x+y data(meuse.grid) gridded(meuse.grid) = ~x+y # Perform crossvalidation kr.cv = autoKrige.cv(log(zinc)~1, meuse, model = c("Exp"), nfold = 10) kr_dist.cv = autoKrige.cv(log(zinc)~sqrt(dist), meuse, model = c("Exp"), nfold = 10) kr_dist_ffreq.cv = autoKrige.cv(log(zinc)~sqrt(dist)+ffreq, meuse, model = c("Exp"), nfold = 10) # Compare the results compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv) compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, bubbleplots = TRUE) compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, bubbleplots = TRUE, col.names = c("OK","UK1","UK2")) compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, bubbleplots = TRUE, col.names = c("OK","UK1","UK2"), plot.diff = TRUE) # I recently added a new bubble plot that uses ggplot # I find it preferable, note that it requires ggplot2. ## Not run: compare.cv(kr.cv, kr_dist.cv, kr_dist_ffreq.cv, bubbleplots = TRUE, col.names = c("OK","UK1","UK2"), ggplot = TRUE) ## End(Not run)