argminCS: Argmin Inference over a Discrete Candidate Set

Provides methods to construct frequentist confidence sets with valid marginal coverage for identifying the population-level argmin or argmax based on IID data. For instance, given an n by p loss matrix—where n is the sample size and p is the number of models—the CS.argmin() method produces a discrete confidence set that contains the model with the minimal (best) expected risk with desired probability. The argmin.HT() method helps check if a specific model should be included in such a confidence set. The main implemented method is proposed by Tianyu Zhang, Hao Lee and Jing Lei (2024) "Winners with confidence: Discrete argmin inference with an application to model selection".

Version:	1.1.0
Imports:	BSDA, glue, LDATS, MASS, methods, Rdpack, stats, withr
Published:	2025-07-14
DOI:	10.32614/CRAN.package.argminCS
Author:	Tianyu Zhang [aut], Hao Lee [aut, cre, cph], Jing Lei [aut]
Maintainer:	Hao Lee <haolee at andrew.cmu.edu>
License:	MIT + file LICENSE
URL:	https://github.com/xu3cl4/argminCS
NeedsCompilation:	no
Materials:	README
CRAN checks:	argminCS results

Documentation:

Reference manual:

argminCS.pdf

Downloads:

Package source:	argminCS_1.1.0.tar.gz
Windows binaries:	r-devel: argminCS_1.1.0.zip, r-release: not available, r-oldrel: argminCS_1.1.0.zip
macOS binaries:	r-release (arm64): argminCS_1.1.0.tgz, r-oldrel (arm64): argminCS_1.1.0.tgz, r-release (x86_64): argminCS_1.1.0.tgz, r-oldrel (x86_64): argminCS_1.1.0.tgz

Linking:

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