Learn R Programming

ade4 (version 1.7-16)

loocv.dudi: Leave-one-out cross-validation for a dudi

Description

Leave-one-out cross-validation to check the dispersion of row coordinates in a dudi.

Usage

# S3 method for dudi
loocv(x, progress = FALSE, …)

Arguments

x

the dudi of the bca on which cross-validation should be done

progress

logical to display a progress bar during computations (see the progress package)

further arguments passed to or from other methods

Value

a list with two elements: $XValCoord and $lsFac containing the cross-validated row coordinates and the factor to plot them using the s.class (see example).

Details

This function returns a list with two elements: $XValCoord and $lsFac, the cross-validated row coordinates and a factor to plot them. The analysis is redone after removing each row of the data table, one at a time. The coordinates of the missing row are computed by projection as supplementary element in the dudi space. This can be used to check the dispersion of the coordinates of one point and it's sensitivity to outliers.

See Also

suprow

Examples

Run this code
# NOT RUN {
data(meaudret)
envpca <- dudi.pca(meaudret$env, scannf = FALSE, nf = 3)
xvpca <- loocv(envpca)
s.match(envpca$li, xvpca$XValCoord)
# }

Run the code above in your browser using DataLab