Alternative Ridge Parameters in Linear Model
Nicel Bilimler Dergisi · 2022
DOI: 10.51541/nicel.1042316 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nicel Bilimler Dergisi, 2022. Verfasst von Kayode AYİNDE und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben.
Abstract (Originalsprache)
The ridge regression estimator produces efficient estimates than the Ordinary Least Square Estimator in a linear regression model that has multicollinearity problem. However, the efficiency of the ridge estimator depends on the choice of the ridge parameter, k. This parameter being the biasing parameter that shrinks the coefficient as it tends towards positive infinity needs to be chosen optimally to minimize the mean squared errors of the parameters. In this study, the ridge parameters are classified into different forms, various types and diverse kinds. These classifications resulted into proposing some other techniques of Ridge parameter estimation. Investigation of the existing and proposed ridge parameters were done by conducting Monte-Carlo experiments. Results from simulation study and reallife data application show that some newly proposed ridge parameters are among those that provide efficient estimates.
Zitieren
APA
AYİNDE, K., ADEWUYİ, E., & FOLARANMİ, L. A. (2022). Alternative Ridge Parameters in Linear Model. Nicel Bilimler Dergisi. https://doi.org/10.51541/nicel.1042316
Vancouver
AYİNDE K, ADEWUYİ E, FOLARANMİ LA. Alternative Ridge Parameters in Linear Model. Nicel Bilimler Dergisi. 2022. doi:10.51541/nicel.1042316
BibTeX
@article{AYNDE2022,
author = {AYİNDE, Kayode and ADEWUYİ, Emmanuel and FOLARANMİ, Lukman Adewale},
title = {Alternative Ridge Parameters in Linear Model},
journal = {Nicel Bilimler Dergisi},
year = {2022},
doi = {10.51541/nicel.1042316}
}
EUVIMED