modQR: Multiple-Output Directional Quantile Regression

Contains basic tools for performing multiple-output quantile regression and computing regression quantile contours by means of directional regression quantiles. In the location case, one can thus obtain halfspace depth contours in two to six dimensions. Hallin, M., Paindaveine, D. and Šiman, M. (2010) Multivariate quantiles and multiple-output regression quantiles: from L1 optimization to halfspace depth. Annals of Statistics 38, 635-669 For more references about the method, see Help pages.

Version: 0.1.3
Depends: R (≥ 2.5.0), lpSolve (≥ 5.6.1), geometry (≥ 0.3-1)
Suggests: rgl
Published: 2022-05-11
Author: Miroslav Šiman [aut], Pavel Boček [aut, cre]
Maintainer: Pavel Boček <bocek at utia.cas.cz>
License: LGPL-2
Copyright: The Institute of Information Theory and Automation of the Czech Academy of Sciences, Pod Vodarenskou vezi 4, CZ-18208 Prague 8, Czech Republic, email: utia@utia.cas.cz, phone: +420 266 053 111
NeedsCompilation: no
Classification/MSC: 62H05, 62J99, 62G08, 65C60
Materials: ChangeLog
CRAN checks: modQR results

Documentation:

Reference manual: modQR.pdf

Downloads:

Package source: modQR_0.1.3.tar.gz
Windows binaries: r-devel: modQR_0.1.3.zip, r-release: modQR_0.1.3.zip, r-oldrel: modQR_0.1.3.zip
macOS binaries: r-release (arm64): modQR_0.1.3.tgz, r-oldrel (arm64): modQR_0.1.3.tgz, r-release (x86_64): modQR_0.1.3.tgz, r-oldrel (x86_64): modQR_0.1.3.tgz
Old sources: modQR archive

Linking:

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