standardize: Data standardization

In aalfons/robustHD: Robust Methods for High-Dimensional Data

Data standardization

Description

Standardize data with given functions for computing center and scale.

Usage

standardize(x, centerFun = mean, scaleFun = sd)

robStandardize(
  x,
  centerFun = median,
  scaleFun = mad,
  fallback = FALSE,
  eps = .Machine$double.eps,
  ...
)

Arguments

x	a numeric vector, matrix or data frame to be standardized.
centerFun	a function to compute an estimate of the center of a variable (defaults to mean).
scaleFun	a function to compute an estimate of the scale of a variable (defaults to sd).
fallback	a logical indicating whether standardization with mean and sd should be performed as a fallback mode for variables whose robust scale estimate is too small. This is useful, e.g., for data containing dummy variables.
eps	a small positive numeric value used to determine whether the robust scale estimate of a variable is too small (an effective zero).
...	currently ignored.

Details

robStandardize is a wrapper function for robust standardization, hence the default is to use median and mad.

Value

An object of the same type as the original data x containing the centered and scaled data. The center and scale estimates of the original data are returned as attributes "center" and "scale", respectively.

Note

The implementation contains special cases for the typically used combinations mean/sd and median/mad in order to reduce computation time.

Author(s)

Andreas Alfons

See Also

scale, sweep

Examples

## generate data
set.seed(1234)     # for reproducibility
x <- rnorm(10)     # standard normal
x[1] <- x[1] * 10  # introduce outlier

## standardize data
x
standardize(x)     # mean and sd
robStandardize(x)  # median and MAD

aalfons/robustHD documentation built on Sept. 30, 2023, 10:39 p.m.