enetLTS (version 0.1.0)

plot.enetLTS: plots from the "enetLTS" object

Description

Produce plots for the coefficients, residuals, and diagnostics of the current model.

Usage

# S3 method for enetLTS
plot(x,method=c("coefficients","resid","diagnostic"),
       vers=c("reweighted","raw"),...)

Arguments

x

object of class enetLTS, the model fit to be plotted.

method

a character string specifying the type of plot. Possible values are "coefficients" to plot the coefficients via plotCoef.enetLTS, "resid" to plot the residuals via plotResid.enetLTS, or "diagnostic" for diagnostic plot via plotDiagnostic.enetLTS.

vers

a character string denoting which model to use for the plots. Possible values are "reweighted" (the default) for plots from the reweighted fit, and "raw" for plots from the raw fit.

…

additional arguments from the enetLTS object if needed.

Value

An object of class "ggplot" (see ggplot).

References

Kurnaz, F.S., Hoffmann, I. and Filzmoser, P. (2017) Robust and sparse estimation methods for high dimensional linear and logistic regression. Chemometrics and Intelligent Laboratory Systems.

See Also

ggplot, enetLTS, coef.enetLTS, predict.enetLTS, residuals.enetLTS, fitted.enetLTS

Examples

# NOT RUN {
## for gaussian

set.seed(86)
n <- 100; p <- 25                             # number of observations and variables
beta <- rep(0,p); beta[1:6] <- 1              # 10% nonzero coefficients
sigma <- 0.5                                  # controls signal-to-noise ratio
x <- matrix(rnorm(n*p, sigma),nrow=n)
e <- rnorm(n,0,1)                             # error terms
eps <- 0.1                                    # contamination level
m <- ceiling(eps*n)                           # observations to be contaminated
eout <- e; eout[1:m] <- eout[1:m] + 10        # vertical outliers
yout <- c(x %*% beta + sigma * eout)          # response
xout <- x; xout[1:m,] <- xout[1:m,] + 10      # bad leverage points

# }
# NOT RUN {
fit1 <- enetLTS(xout,yout,alphas=0.5,lambdas=0.05,plot=FALSE)
plot(fit1)
plot(fit1,method="resid",vers="raw")
plot(fit1,method="coefficients",vers="reweighted")
plot(fit1,method="diagnostic")
# }
# NOT RUN {
## for binomial
eps <-0.05                                     # %10 contamination to only class 0
m <- ceiling(eps*n)
y <- sample(0:1,n,replace=TRUE)
xout <- x
xout[y==0,][1:m,] <- xout[1:m,] + 10;          # class 0
yout <- y                                      # wrong classification for vertical outliers

# }
# NOT RUN {
fit2 <- enetLTS(xout,yout,family="binomial",alphas=0.5,lambdas=0.05,plot=FALSE)
plot(fit2)
plot(fit2,method="resid",vers="raw")
plot(fit2,method="coefficients",vers="reweighted")
plot(fit2,method="diagnostic")
# }

Run the code above in your browser using DataCamp Workspace