cellWise (version 2.2.0)

wrap: Wrap the data.

Description

Transforms multivariate data X using the wrapping function with b = 1.5 and c = 4 and the location and scale given in locX and scaleX.

Usage

wrap(X, locX, scaleX, precScale = 1e-12, imputeNA = TRUE)

Arguments

X

the input data. It must be an \(n\) by \(d\) matrix or a data frame.

locX

The location estimates of the columns of the input data X. Must be a vector of length \(d\).

scaleX

The scale estimates of the columns of the input data X. Must be a vector of length \(d\).

precScale

The precision scale used throughout the algorithm. Defaults to \(1e-12\)

imputeNA

Whether or not to impute the NAs with the location estimate of the corresponding variable. Defaults to TRUE.

Value

A list with components:

• Xw The wrapped data.

• colInWrap The column numbers for which the scale estimate was larger than precScale. Those with scale estimate <= precScale do not occur in Xw to avoid division by (near) zero.

References

Raymaekers, J., Rousseeuw P.J. (2019). Fast robust correlation for high dimensional data. Technometrics, published online.

See Also

estLocScale

Examples

# NOT RUN {
library(MASS) 
set.seed(12345) 
n <- 100; d <- 10
X <- mvrnorm(n, rep(0, 10), diag(10))
locScale <- estLocScale(X)
Xw <- wrap(X, locScale$loc, locScale$scale)$Xw
# }