robustStandard: Robust standardization

In kernDeepStackNet: Kernel Deep Stacking Networks

Description

Scales the data matrix with the median and median absolute deviation.

Usage

robustStandard(X)

Arguments

X	Data design matrix.

Value

Numeric transformed data matrix with same dimension as original data.

Author(s)

Thomas Welchowski [e-mail]

References

Ricardo A. Maronna and R. Douglas Martin and Victor J. Yohai, (2006), Robust Statistics: Theory and Methods, John Wiley \& Sons, Ltd.

Examples

# Generate data matrix
set.seed(150)
X <- matrix(rnorm(100*3), ncol=3)

# Robust standardization
scaledX <- robustStandard(X=X)

# Median equals 0
all.equal(sapply(1:3, function(x) median(scaledX[,x])), rep(0, 3))

# MAD equals 1
all.equal(sapply(1:3, function(x) mad(scaledX[,x], constant=1)), rep(1, 3))

kernDeepStackNet documentation built on May 2, 2019, 8:16 a.m.