Ridge regression estimator: combining unbiased and ordinary ridge regression methods of estimation
Journal Title: Surveys in Mathematics and its Applications - Year 2009, Vol 4, Issue 0
Abstract
Statistical literature has several methods for coping with multicollinearity. This paper introduces a new shrinkage estimator, called modified unbiased ridge (MUR). This estimator is obtained from unbiased ridge regression (URR) in the same way that ordinary ridge regression (ORR) is obtained from ordinary least squares (OLS). Properties of MUR are derived. Results on its matrix mean squared error (MMSE) are obtained. MUR is compared with ORR and URR in terms of MMSE. These results are illustrated with an example based on data generated by Hoerl and Kennard (1975).
Authors and Affiliations
Feras Batah, Sharad Damodar Gore
Keywords
Related Articles
- EP ID EP91729
- DOI -
- Views 193
- Downloads 0
Some Absolutely Continuous Representations of Function Algebras
In this paper we study some absolutely continuous representations of function algebras, which are weak ρ-spectral in the sense of [5] and [6], for a scalar ρ > 0. More precisely, we investigate certain conditions for...
Some applications of generalized Ruscheweyh derivatives involving a general fractional derivative operator to a class of analytic functions with negative coefficients I
For certain univalent function f, we study a class of functions f as defined by making use of the generalized Ruscheweyh derivatives involving a general fractional derivative operator, satisfying <CENTER>Re { (zJ&l...
On the Spectrum of a Morphism of Quotient Hilbert Spaces
In this paper we define the notion of spectrum for a morphism of quotient Hilbert spaces. The definition is the same with the one given by L.Waelbroeck but the proofs that the spectrum is a compact and nonempty set are d...
Function valued metric spaces
In this paper we introduce the notion of an &#8497;-metric, as a function valued distance mapping, on a set X and we investigate the theory of &#8497;-metrics paces. We show that every metric space may be viewed...
Almost-periodic solution for BAM neural networks
In this paper, we study the existence and uniqueness solution and investigate the conditions that make it almost-periodic solution for BAM neural networks with retarded delays. The existence of solution established by us...