Modified ridge regression parameters: A comparative Monte Carlo study
MetadataShow full item record
CitationAsar, Y., Karaibrahimoğlu, A., Genç, A. (2014). Modified ridge regression parameters: A comparative Monte Carlo study. Hacettepe Journal of Mathematics and Statistics, 43, 5, 827-841.
In multiple regression analysis, the independent variables should beuncorrelated within each other. If they are highly intercorrelated, thisserious problem is called multicollinearity. There are several methodsto get rid of this problem and one of the most famous one is the ridgeregression. In this paper, we will propose some modified ridge parameters. We will compare our estimators with some estimators proposedearlier according to mean squared error (MSE) criterion. All resultsare calculated by a Monte Carlo simulation. According to simulationstudy, our estimators perform better than the others in most of thesituations in the sense of MSE.
SourceHacettepe Journal of Mathematics and Statistics