mgc: Multiscale Graph Correlation

Multiscale Graph Correlation (MGC) is a framework developed by Vogelstein et al. (2019) <doi:10.7554/eLife.41690> that extends global correlation procedures to be multiscale; consequently, MGC tests typically require far fewer samples than existing methods for a wide variety of dependence structures and dimensionalities, while maintaining computational efficiency. Moreover, MGC provides a simple and elegant multiscale characterization of the potentially complex latent geometry underlying the relationship.

Version: 2.0.2
Depends: R (≥ 3.4.0)
Imports: stats, MASS, abind, boot, energy, raster
Suggests: testthat (≥ 2.1.0), ggplot2, reshape2, knitr, rmarkdown
Published: 2020-06-23
Author: Eric Bridgeford [aut, cre], Censheng Shen [aut], Shangsi Wang [aut], Joshua Vogelstein [ths]
Maintainer: Eric Bridgeford <ericwb95 at gmail.com>
License: GPL-2
URL: https://github.com/neurodata/r-mgc
NeedsCompilation: yes
CRAN checks: mgc results

Documentation:

Reference manual: mgc.pdf
Vignettes: discriminability
mgc
class_sims
reg_sims

Downloads:

Package source: mgc_2.0.2.tar.gz
Windows binaries: r-devel: mgc_2.0.2.zip, r-release: mgc_2.0.2.zip, r-oldrel: mgc_2.0.2.zip
macOS binaries: r-release (arm64): mgc_2.0.2.tgz, r-oldrel (arm64): mgc_2.0.2.tgz, r-release (x86_64): mgc_2.0.2.tgz
Old sources: mgc archive

Reverse dependencies:

Reverse imports: coveR2, mineSweepR

Linking:

Please use the canonical form https://CRAN.R-project.org/package=mgc to link to this page.