robscale: Faster Robustness: Accelerated Estimation of Location and Scale

Robust estimation ensures statistical reliability in data contaminated by outliers. Yet, computational bottlenecks in existing 'R' implementations frequently obstruct both very small sample analysis and large-scale processing. 'robscale' resolves these inefficiencies by providing high-performance implementations of logistic M-estimators and the 'Qn' and 'Sn' scale estimators. By leveraging platform-specific Single Instruction, Multiple Data (SIMD) vectorization and Intel Threading Building Blocks (TBB) parallelism, the package delivers speedups of 11–39x for small samples and up to 10x for massive datasets. These performance gains enable the integration of robust statistics into modern, time-critical computational workflows. Replaces 'revss' with an 'Rcpp' backend.

Version:	0.1.5
Imports:	Rcpp (≥ 1.0.0), RcppParallel (≥ 5.0.0)
LinkingTo:	Rcpp, RcppParallel, BH
Suggests:	testthat (≥ 3.0.0), revss, microbenchmark, robustbase
Published:	2026-03-09
DOI:	10.32614/CRAN.package.robscale
Author:	Dennis Alexis Valin Dittrich [aut, cre, cph]
Maintainer:	Dennis Alexis Valin Dittrich <davd at economicscience.net>
BugReports:	https://github.com/davdittrich/robscale/issues
License:	MIT + file LICENSE
URL:	https://github.com/davdittrich/robscale, https://doi.org/10.5281/zenodo.18828607
NeedsCompilation:	yes
SystemRequirements:	GNU make, TBB
Citation:	robscale citation info
Materials:	NEWS
CRAN checks:	robscale results

Documentation:

Reference manual:

robscale.html , robscale.pdf

Downloads:

Package source:	robscale_0.1.5.tar.gz
Windows binaries:	r-devel: robscale_0.1.1.zip, r-release: not available, r-oldrel: robscale_0.1.1.zip
macOS binaries:	r-release (arm64): robscale_0.1.5.tgz, r-oldrel (arm64): robscale_0.1.5.tgz, r-release (x86_64): not available, r-oldrel (x86_64): not available
Old sources:	robscale archive

Linking:

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