Modified ridge type estimator in partially linear regression models and numerical comparisons
Küçük Resim Yok
Tarih
2016
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
American Scientific Publishers
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In this article, we introduce a modified ridge type estimator for the vector of parameters in a partially linear model. This estimator is a generalization of the well-known Speckman's approach and is based on smoothing splines method. Most important in the implementation of this method is the choice of the smoothing parameter. Many Criteria of selecting smoothing parameters such as improved version of Akaike information criterion (AICc), generalized cross-validation (GCV), crossvalidation (CV), Mallows' Cp criterion, risk estimation using classical pilots (REC) and Bayes information criterion (BIC) are developed in literature. In order to illustrate the ideas in the paper, a real data example and a Monte Carlo simulation study are carried out. Thus, the appropriate selection criteria are provided for a suitable smoothing parameter selection. © Copyright 2016 American Scientific Publishers All rights reserved.
Açıklama
Anahtar Kelimeler
Cross-validation, Generalized cross-validation, Partially linear model, Ridge type estimator, Smoothing parameter, Smoothing splines
Kaynak
Journal of Computational and Theoretical Nanoscience
WoS Q Değeri
Scopus Q Değeri
Q4
Cilt
13
Sayı
10
