Temel Bileşenlere Dayalı Bazı Regresyon Yöntemleri

Authors : Fatma Sevinç KURNAZ

Pages : 581-591

Doi:10.17714/gumusfenbil.641791

View : 15 | Download : 7

Publication Date : 2020-07-15

Article Type : Research Paper

Abstract :Principal component analysis (PCA) is commonly used technique in data processing and dimensionality reduction. However, PCA is very sensitive to outliers. To deal with this problem, the robust principal component analysis (RPCA) using Projection-Pursuit (PP) is a very appealing method. On the other hand, combining PCA on explanatory variables with least squares regression yields to principal component regression (PCR). Taking into consideration this general structure of PCR, we combine (R)PCA with OLS and MM regression estimators and show the performances of examined methods on extensive simulation studies and real data examples.
Keywords : Ordinary Least Squares, Principal Component Analysis, Principal Component Regression, Robustness