Learn R Programming

rrscale (version 1.0)

Robust Re-Scaling to Better Recover Latent Effects in Data

Description

Non-linear transformations of data to better discover latent effects. Applies a sequence of three transformations (1) a Gaussianizing transformation, (2) a Z-score transformation, and (3) an outlier removal transformation. A publication describing the method has the following citation: Gregory J. Hunt, Mark A. Dane, James E. Korkola, Laura M. Heiser & Johann A. Gagnon-Bartsch (2020) "Automatic Transformation and Integration to Improve Visualization and Discovery of Latent Effects in Imaging Data", Journal of Computational and Graphical Statistics, .

Copy Link

Version

Install

install.packages('rrscale')

Monthly Downloads

155

Version

1.0

License

GPL-3

Maintainer

Gregory Hunt

Last Published

May 26th, 2020

Functions in rrscale (1.0)

box_cox_plus1

Box-cox transformation with a shift of 1 added to the data
box_cox

Traditional box-cox power transformation. Accepts one real parameter
center

Centers the data column-wise
gm_mean

Calculate the geometric mean
list_transformations

List possible transformations
box_cox_negative

A generalized box-cox transformation that can handle negative data
box_cox_exp

Exponential of the tranditional box-cox transformation
box_cox_plusmin

Box-cox transformation with the data shifted so that it is positive
asinh

Arc-hyperbolic-sine transformation
box_cox_shift

Box-cox transformation of shifted variable
log_box_cox

Log of the traditional box-cox transformation
winsor

Winsorizes the data
power

Simple power transformation
svdc

The completed SVD
rrscale

Re-scale a data matrix