A Rational Interpretation of the Ridge Trace (Q3217463)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3883439
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A Rational Interpretation of the Ridge Trace |
scientific article; zbMATH DE number 3883439 |
Statements
1984
0 references
Bayes estimator
0 references
ridge regression estimator
0 references
weighted average of least squares estimators
0 references
subset regressions
0 references
ridge trace
0 references
sample information
0 references
prior information
0 references
sensitivity
0 references
A Rational Interpretation of the Ridge Trace (English)
0 references
0.7994030714035034
0 references
0.7839447855949402
0 references
0.7779762148857117
0 references
0.7595903277397156
0 references
The ridge regression estimator is expressed as a weighted average of least squares estimators of all possible subset regressions and is exploited to understand the behaviour of the ridge trace asymptotically as well as near \(k=0.\) Through Bayes formulation, the weights are shown to incorporate sample information and prior information. This approach might help in understanding the sensitivity of regression estimates to the choice of variables in the model through the ridge trace. Insights achievable are illustrated through a real problem with ten explanatory variables.
0 references