msPCA: Sparse Principal Component Analysis with Multiple Principal Components
Implements an algorithm for computing multiple sparse principal components of a dataset. The method is based on Cory-Wright and Pauphilet "Sparse PCA with Multiple Components" (2026) <doi:10.1287/opre.2023.0598>. The algorithm uses an iterative deflation heuristic with a truncated power method applied at each iteration to compute sparse principal components with controlled sparsity.
| Version: | 0.5.1 |
| Depends: | R (≥ 3.5) |
| Imports: | Rcpp (≥ 1.0.11) |
| LinkingTo: | Rcpp, RcppEigen |
| Suggests: | covr, datasets, knitr, rmarkdown, testthat (≥ 3.0.0) |
| Published: | 2026-08-25 |
| DOI: | 10.32614/CRAN.package.msPCA |
| Author: | Ryan Cory-Wright 
[aut, cph],
Jean Pauphilet
[aut, cre, cph] |
| Maintainer: | Jean Pauphilet <jpauphilet at london.edu> |
| BugReports: | https://github.com/jeanpauphilet/msPCA/issues |
| License: | MIT + file LICENSE |
| URL: | https://jeanpauphilet.github.io/msPCA/ |
| NeedsCompilation: | yes |
| Citation: | msPCA citation info |
| Materials: | README, NEWS |
| In views: | ChemPhys, MachineLearning |
| CRAN checks: | msPCA results |
Documentation:
| Reference manual: | msPCA.html , msPCA.pdf |
| Vignettes: |
Algorithm and implementation notes (source, R code) Case study: sparse factors in S&P 500 returns (source, R code) Worked example: msPCA on mtcars (source, R code) |
Downloads:
| Package source: | msPCA_0.5.1.tar.gz |
| Windows binaries: | r-devel: msPCA_0.5.0.zip, r-release: msPCA_0.5.0.zip, r-oldrel: msPCA_0.5.0.zip |
| macOS binaries: | r-release (arm64): msPCA_0.5.0.tgz, r-oldrel (arm64): msPCA_0.5.0.tgz, r-release (x86_64): msPCA_0.5.0.tgz, r-oldrel (x86_64): msPCA_0.5.0.tgz |
| Old sources: | msPCA archive |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=msPCA to link to this page.