fsdaR (version 0.9-0)

corfwdplot: Monitoring the correlations between consecutive distances or residuals

Description

Provides a method for obtaining the maximum empirical efficiency (in case of MM estimates) or maximum empirical breakdownplot (in case of S estimates) or maximum subset size (in case of forward search), using various measures of correlation between the n Mahalanobis distances or residuals at adjacent values of efficiecy, breakdown point or subset size.

Usage

corfwdplot(out, trace = FALSE, ...)

Value

A ggplot plot object which can be printed on screen or to a file.

Arguments

out

An object of S3 class returned by one of the estimation functions with the monitoring option selected (monitoring=TRUE): fsreda.object, sregeda.object, mmregeda.object, fsmeda.object, smulteda.object or mmmulteda.object. This is a list containing the monitoring of minimum Mahalanobis distance in case of multivariate analysis or the monitoring of residuals in case of regression.

The needed elements of out are

1. MAL: matrix containing the squared Mahalanobis distances monitored in each step of the forward search. Every row is associated with a unit (row of data matrix Y). This matrix can be created using one of the functions fsmult, smult or mmmult with the monitoring option selected, i.e. monitoring=TRUE.

2. RES: matrix containing the residuals monitored in each step of the forward search. Every row is associated with a unit (row of data matrix Y). This matrix can be created using the function fsreg with the monitoring option selected, i.e. monitoring=TRUE .

3. bdp: a vector containing breakdown point values that have been used, in case of S estimates.

4. eff: a vector containing efficiency values that have been used, in case of MM estimates.

trace

Whether to print intermediate results. Default is trace=FALSE.

...

potential further arguments passed to lower level functions.

Author

FSDA team,

Examples

 if (FALSE) {

 data(hbk, package="robustbase")
 (out <- fsmult(hbk[,1:3], monitoring=TRUE))
 corfwdplot(out)

 (out1 <- smult(hbk, monitoring=TRUE, trace=TRUE))
 corfwdplot(out1)

 (out2 <- mmmult(hbk[,1:3], monitoring=TRUE, trace=TRUE))
 corfwdplot(out2)

 (out3 <- fsreg(hbk[,1:3], hbk[,4], monitoring=TRUE, trace=TRUE, method="FS"))
 corfwdplot(out3)

 (out4 <- fsreg(hbk[,1:3], hbk[,4], monitoring=TRUE, trace=TRUE, method="S"))
 corfwdplot(out4)

 (out5 <- fsreg(hbk[,1:3], hbk[,4], monitoring=TRUE, trace=TRUE, method="MM"))
 corfwdplot(out5)

 }