Performances of some high dimensional regression methods

KURNAZ F. S.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, cilt.50, sa.6, ss.1820-1836, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 50 Sayı: 6
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1080/03610918.2021.1881115
  • Dergi Adı: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, CAB Abstracts, Compendex, Computer & Applied Sciences, Veterinary Science Database, zbMATH, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1820-1836
  • Anahtar Kelimeler: lasso, L, (1) penalty, Robustness, Variable selection
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

Variable selection is one of the important practical issues for many scientific areas, particularly in chemometrics, where data sets include several hundreds of variables and low number of observations. The aim of this paper is to compare some newly proposed variable selection methods by means of extensive simulation studies and to give some practical hints for use of the compared methods. Furthermore, we underpin the performances of compared methods based on real data examples.