Random Subspace Method for high-dimensional regression with the R package regRSM

Robert Kłopotek , Jan Mielniczuk , Paweł Roman Teisseyre

Abstract

Model selection and variable importance assessment in high-dimensional regression are among the most important tasks in contemporary applied statistics. In our procedure, implemented in the package regRSM, the Random Subspace Method (RSM) is used to construct a variable importance measure. The variables are ordered with respect to the measures computed in the first step using the RSM and then, from the hierarchical list of models given by the ordering, the final subset of variables is chosen using information criteria or validation set. Modifications of the original method such as the weighted Random Subspace Method and the version with initial screening of redundant variables are discussed. We developed parallel implementations which enable to reduce the computation time significantly. In this paper, we give a brief overview of the methodology, demonstrate the package’s functionality and present a comparative study of the proposed algorithm and the competitive methods like lasso or CAR scores. In the performance tests the computational times for parallel implementations are compared.
Author Robert Kłopotek
Robert Kłopotek,,
-
, Jan Mielniczuk (FMIS / DSPFM)
Jan Mielniczuk,,
- Department of Stochastic Processes and Financial Mathematics
, Paweł Roman Teisseyre (FMIS)
Paweł Roman Teisseyre,,
- Faculty of Mathematics and Information Science
Journal seriesComputational Statistics, ISSN 0943-4062
Issue year2016
Vol31
No3
Pages943-972
Publication size in sheets1.45
Keywords in EnglishRandom Subspace Method, High-dimensional regression, Variable importance measure, Generalized Information Criterion, MPI, R
ASJC Classification2605 Computational Mathematics; 1804 Statistics, Probability and Uncertainty; 2613 Statistics and Probability
Abstract in PolishW pracy przedstawiono implementację metody Random Subspace Method w pakiecie regRSM. Omówiono dwa nowe warianty metody oraz zaimplementowaną wersję zrównolegloną.
DOIDOI:10.1007/s00180-016-0658-2
URL http://link.springer.com/article/10.1007/s00180-016-0658-2
Languageen angielski
Score (nominal)20
Score sourcejournalList
ScoreMinisterial score = 15.0, 01-01-2020, ArticleFromJournal
Ministerial score (2013-2016) = 20.0, 01-01-2020, ArticleFromJournal
Publication indicators WoS Citations = 3; Scopus SNIP (Source Normalised Impact per Paper): 2016 = 0.952; WoS Impact Factor: 2016 = 0.434 (2) - 2016=0.71 (5)
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?