zhaoni153/GHT: Generalized Hoteling’s test for paired microbiome data

Package “GHT” tests whether the average composition between two groups of paired samples, such as, whether the compositions are the same before and after a treatment. It first constructs a centered log-ratio transformation of the relative abundances, and then uses a generalized Hoteling’s test with permutation for hypothesis testing. GHT extends the classical Hoteling’s test statistic by replacing the sample covariance matrix (which is singular due to the dimensionality and the compositionality nature of the data) by a shrinkage based covariance, which is calculated as a weighted average of the sample covariance and a target matrix. Code from package “ShrinkCovMat” [Anestis Touloumis] is used to obtain the optimal value of the weighting parameter.

Getting started

Package details

AuthorNi Zhao
MaintainerNi Zhao <[email protected]>
LicenseGPL (>= 2)
Version1.0
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("devtools")
library(devtools)
install_github("zhaoni153/GHT")
zhaoni153/GHT documentation built on March 23, 2018, 8:59 p.m.