decorrelate: Decorrelation Projection Scalable to High Dimensional Data
Data whitening is a widely used preprocessing step to remove correlation structure since statistical models often assume independence. Here we use a probabilistic model of the observed data to apply a whitening transformation. This Gaussian Inverse Wishart Empirical Bayes model substantially reduces computational complexity, and regularizes the eigen-values of the sample covariance matrix to improve out-of-sample performance.
| Version: | 0.1.6.4 |
| Depends: | R (≥ 4.2.0), methods |
| Imports: | Rfast, irlba, graphics, Rcpp, CholWishart, Matrix, utils, stats |
| LinkingTo: | Rcpp, RcppArmadillo |
| Suggests: | knitr, pander, whitening, CCA, yacca, mvtnorm, ggplot2, cowplot, colorRamps, RUnit, latex2exp, clusterGeneration, rmarkdown |
| Published: | 2025-07-18 |
| DOI: | 10.32614/CRAN.package.decorrelate |
| Author: | Gabriel Hoffman 
[aut, cre] |
| Maintainer: | Gabriel Hoffman <gabriel.hoffman at mssm.edu> |
| BugReports: | https://github.com/GabrielHoffman/decorrelate/issues |
| License: | Artistic-2.0 |
| URL: | https://gabrielhoffman.github.io/decorrelate/ |
| NeedsCompilation: | yes |
| Materials: | README, NEWS |
| CRAN checks: | decorrelate results |
Documentation:
| Reference manual: | decorrelate.html , decorrelate.pdf |
| Vignettes: |
Decorrelate (source, R code) |
Downloads:
| Package source: | decorrelate_0.1.6.4.tar.gz |
| Windows binaries: | r-devel: decorrelate_0.1.6.4.zip, r-release: decorrelate_0.1.6.4.zip, r-oldrel: decorrelate_0.1.6.4.zip |
| macOS binaries: | r-release (arm64): decorrelate_0.1.6.4.tgz, r-oldrel (arm64): decorrelate_0.1.6.4.tgz, r-release (x86_64): decorrelate_0.1.6.4.tgz, r-oldrel (x86_64): decorrelate_0.1.6.4.tgz |
| Old sources: | decorrelate archive |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=decorrelate to link to this page.