A Review on Shrinkage Parameters in Ridge Regression

GÖKPINAR E., EBEGİL M., GÖKPINAR F.

GAZI UNIVERSITY JOURNAL OF SCIENCE, cilt.30, sa.4, ss.565-582, 2017 (ESCI) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 30 Sayı: 4
  • Basım Tarihi: 2017
  • Dergi Adı: GAZI UNIVERSITY JOURNAL OF SCIENCE
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus
  • Sayfa Sayıları: ss.565-582
  • Gazi Üniversitesi Adresli: Evet

Özet

Multicollinearity problem arises in the case of near-linear dependencies among the independent (explanatory) variables. Ridge regression based on different shrinkage parameters is a commonly used method for solving this problem. There are many shrinkage parameters; therefore, the proper selection of the shrinkage parameters is important. In this study, we investigated the popular shrinkage parameters and compared them by means of a simulation study in terms of Mean Square Error. Furthermore, a test statistic for Ridge estimator was analyzed for comparing these parameters through simulation.