Ridge regression revisited
2005-08-31
Research Paper
This publication is part of collection
| Related Files |
|---|
View PDF Version
(ei200529.pdf, 0.2MB) |
We argue in this paper that general ridge (GR) regression implies no major complication compared with simple ridge regression. We introduce a generalization of an explicit GR estimator derived by Hemmerle and by Teekens and de Boer and show that this estimator, which is more conservative, performs better than the Hoerl and Kennard estimator in terms of a weighted quadratic loss criterion.
Keywords
Automatically Extracted Terms
- estimator
- ridge
- ridge estimator
- ols estimator
- regression
- estimators
- gr estimator
- efficiency
- parameter
- matrix
- choice
- ridge regression
- erasmus university rotterdam
- distribution
- 2 z dz
- weight function
- value
- mse performance
- loss criterion
- information
