HCTR: Higher Criticism Tuned Regression

A novel searching scheme for tuning parameter in high-dimensional penalized regression. We propose a new estimate of the regularization parameter based on an estimated lower bound of the proportion of false null hypotheses (Meinshausen and Rice (2006) <doi:10.1214/009053605000000741>). The bound is estimated by applying the empirical null distribution of the higher criticism statistic, a second-level significance testing, which is constructed by dependent p-values from a multi-split regression and aggregation method (Jeng, Zhang and Tzeng (2019) <doi:10.1080/01621459.2018.1518236>). An estimate of tuning parameter in penalized regression is decided corresponding to the lower bound of the proportion of false null hypotheses. Different penalized regression methods are provided in the multi-split algorithm.

Version: 0.1.1
Depends: R (≥ 3.4.0)
Imports: glmnet (≥ 2.0-18), harmonicmeanp (≥ 3.0), MASS, ncvreg (≥ 3.11-1), Rdpack (≥ 0.11-0), stats
Published: 2019-11-22
DOI: 10.32614/CRAN.package.HCTR
Author: Tao Jiang [aut, cre]
Maintainer: Tao Jiang <tjiang8 at ncsu.edu>
License: GPL-2
NeedsCompilation: no
Materials: README
CRAN checks: HCTR results


Reference manual: HCTR.pdf


Package source: HCTR_0.1.1.tar.gz
Windows binaries: r-devel: HCTR_0.1.1.zip, r-release: HCTR_0.1.1.zip, r-oldrel: HCTR_0.1.1.zip
macOS binaries: r-release (arm64): HCTR_0.1.1.tgz, r-oldrel (arm64): HCTR_0.1.1.tgz, r-release (x86_64): HCTR_0.1.1.tgz, r-oldrel (x86_64): HCTR_0.1.1.tgz
Old sources: HCTR archive


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