Learn R Programming

mgc (version 2.0.2)

Multiscale Graph Correlation

Description

Multiscale Graph Correlation (MGC) is a framework developed by Vogelstein et al. (2019) 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.

Copy Link

Version

Install

install.packages('mgc')

Monthly Downloads

215

Version

2.0.2

License

GPL-2

Issues

Pull Requests

Stars

Forks

Maintainer

Eric Bridgeford

Last Published

June 23rd, 2020

Functions in mgc (2.0.2)

discr.sims.exp

Discriminability Exponential Simulation
Smoothing

An auxiliary function that finds the smoothed maximal within the significant region R: If area of R is too small, return the last local corr otherwise take the maximum within R.
discr.mnr

Discriminability Mean Normalized Rank
ConnCompLabel

Connected Components Labelling -- Unique Patch Labelling
discr.sims.cross

Discriminability Cross Simulation
Thresholding

An auxiliary function that finds a region of significance in the local correlation map by thresholding.
DistCentering

An auxiliary function that properly transforms the distance matrix X
DistRanks

An auxiliary function that sorts the entries within each column by ascending order: For ties, the minimum ranking is used, e.g. if there are repeating distance entries, the order is like 1,2,3,3,4,..,n-1.
discr.rdf

Reliability Density Function
discr.test.one_sample

Discriminability One Sample Permutation Test
LocalCov

An auxiliary function that computes all local correlations simultaneously in O(n^2).
discr.sims.radial

Discriminability Radial Simulation
discr.validator

Discriminability Utility Validator
mgc.sims.cubic

Cubic Simulation
discr.sims.fat_tails

Discriminability Spread Simulation
mgc.localcorr

MGC Local Correlations
mgc.sims.spiral

Spiral Simulation
discr.test.two_sample

Discriminability Two Sample Permutation Test
mgc.localcorr.driver

Driver for MGC Local Correlations
mgc.sims.step

Step Function Simulation
gen.coefs

A helper function to generate a d-dimensional linear transformation matrix.
mgc.sims.2ball

Sample from Unit 2-Ball
mgc.sims.2sphere

Sample from Unit 2-Sphere
discr.stat

Discriminability Statistic
gen.x.unif

A helper function to generate n samples of a d-dimensional uniform vector.
mgc.sims.linear

Linear Simulation
mgc.ksample

MGC K Sample Testing
mgc.sims.joint

Joint Normal Simulation
discr.sims.linear

Discriminability Linear Simulation
mgc.distance

Distance
mgc.sims.exp

Exponential Simulation
gen.sample.labels

A helper function for simulating sample labels
mgc.sims.quad

Quadratic Simulation
mgc.sims.random_rotate

Random Rotation
mgc.sims.ubern

Uncorrelated Bernoulli Simulation
mgc.sims.wshape

W Shaped Simulation
mgc.validator

MGC Utility Validator
mgc.test

MGC Permutation Test
remove.isolates

Remove Isolates
mgc.sims.sim_gmm

GMM Simulate
mgc.dist.xfm

MGC Distance Transform
mgc.stat

MGC Test
mgc.sims.rotation

Sample Random Rotation
mgc.dist.validator

Distance Matrix Validator
mgc.stat.driver

MGC Sample Statistic Internal Driver