cvTools (version 0.3.2)

plot.cv: Plot cross-validation results

Description

Plot results from (repeated) \(K\)-fold cross-validation.

Usage

# S3 method for cv
plot (x,
    method = c("bwplot", "densityplot", "xyplot", "dotplot"),
    ...)
  # S3 method for cvSelect
plot (x,
    method = c("bwplot", "densityplot", "xyplot", "dotplot"),
    ...)

Value

An object of class "trellis" is returned invisibly. The

update method can be used to update components of the object and the

print method (usually called by default) will plot it on an appropriate plotting device.

Arguments

x

an object inheriting from class "cv" or "cvSelect" that contains cross-validation results.

method

a character string specifying the type of plot. For the "cv" method, possible values are "bwplot" to create a box-and-whisker plot via bwplot (the default), or "densityplot" to create a kernel density plot via densityplot. Note that those plots are only meaningful for results from repeated cross-validation. For the "cvSelect" method, there are two additional possibilities: "xyplot" to plot the (average) results for each model via xyplot, or "dotplot" to create a similar dot plot via dotplot. The default is to use "bwplot" for results from repeated cross-validation and "xyplot" otherwise. In any case, partial string matching allows supply abbreviations of the accepted values.

...

additional arguments to be passed down.

Author

Andreas Alfons

Details

For objects with multiple columns of cross-validation results, conditional plots are produced.

See Also

cvFit, cvSelect, cvTuning, bwplot, densityplot, xyplot, dotplot

Examples

library("robustbase")
data("coleman")
set.seed(1234)  # set seed for reproducibility

# set up folds for cross-validation
folds <- cvFolds(nrow(coleman), K = 5, R = 50)


## compare LS, MM and LTS regression

# perform cross-validation for an LS regression model
fitLm <- lm(Y ~ ., data = coleman)
cvFitLm <- cvLm(fitLm, cost = rtmspe, 
    folds = folds, trim = 0.1)

# perform cross-validation for an MM regression model
fitLmrob <- lmrob(Y ~ ., data = coleman, k.max = 500)
cvFitLmrob <- cvLmrob(fitLmrob, cost = rtmspe, 
    folds = folds, trim = 0.1)

# perform cross-validation for an LTS regression model
fitLts <- ltsReg(Y ~ ., data = coleman)
cvFitLts <- cvLts(fitLts, cost = rtmspe, 
    folds = folds,  trim = 0.1)

# combine results into one object
cvFits <- cvSelect(LS = cvFitLm, MM = cvFitLmrob, LTS = cvFitLts)
cvFits

# plot results for the MM regression model
plot(cvFitLmrob, method = "bw")
plot(cvFitLmrob, method = "density")

# plot combined results
plot(cvFits, method = "bw")
plot(cvFits, method = "density")
plot(cvFits, method = "xy")
plot(cvFits, method = "dot")


## compare raw and reweighted LTS estimators for 
## 50% and 75% subsets

# 50% subsets
fitLts50 <- ltsReg(Y ~ ., data = coleman, alpha = 0.5)
cvFitLts50 <- cvLts(fitLts50, cost = rtmspe, folds = folds, 
    fit = "both", trim = 0.1)

# 75% subsets
fitLts75 <- ltsReg(Y ~ ., data = coleman, alpha = 0.75)
cvFitLts75 <- cvLts(fitLts75, cost = rtmspe, folds = folds, 
    fit = "both", trim = 0.1)

# combine results into one object
cvFitsLts <- cvSelect("0.5" = cvFitLts50, "0.75" = cvFitLts75)
cvFitsLts

# plot combined results
plot(cvFitsLts, method = "bw")
plot(cvFitsLts, method = "density")
plot(cvFitsLts, method = "xy")
plot(cvFitsLts, method = "dot")