In the regression
analysis, it is desired that no multicollinearity between the independent
(explanatory) variables exists. In the cases where this is not achieved, the
use of Least Square (LS) estimation method leads to mismodelling. Some methods
have been developed to solve this problem; one of which is the ‘biased
estimation method’. When there exists collinearity, selection of the shrinkage
parameter is important. In this study, a test statistics for Ridge estimator
that is kind of shrinkage biased estimators was investigated. Also the estimators
of shrinkage parameter are compared via simulation.
Bölüm | Statistics |
---|---|
Yazarlar | |
Yayımlanma Tarihi | 11 Aralık 2017 |
Yayımlandığı Sayı | Yıl 2017 Cilt: 30 Sayı: 4 |