A Note on The Moments of Stochastic Shrinkage Parameters in Ridge Regression
A common problem in econometric models and multiple regression in general is multicollinearity, which produces undesirable effects on the Least Squares estimators. A possible solution to this problem is the "Ridge" Regression estimator proposed by Hoerl and Kennard (1970). Ridge Regression has been applied to such diverse areas as economics, marketing and the calibration of instruments in industrial processes. However, the properties of these estimators crucially depend upon the selection of certain biasing parameters which are stochastic. In this regard several proposals have been made and the purpose of this paper is to derive general expressions for the moments of the stochastic biasing parameters. With this knowledge we expect to stablish conditions under which a Ridge Regression estimator is better than others.
|Date of creation:||Mar 2000|
|Date of revision:|
|Contact details of provider:|| Postal: Casilla No967, Santiago|
Phone: (562) 670 2000
Fax: (562) 698 4847
Web page: http://www.bcentral.cl/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:chb:bcchwp:65. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Claudio Sepulveda)
If references are entirely missing, you can add them using this form.