No label defined (Q3768207)
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 4026604
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 4026604 |
Statements
1985
0 references
ellipsoidal inequality
0 references
prior information
0 references
nonlinear constraints
0 references
linear model
0 references
Linear minimax predictors
0 references
minimax estimators
0 references
quadratic risk
0 references
BLUP
0 references
BLUE
0 references
ridge-estimators
0 references
0.8308286666870117
0 references
0.824268102645874
0 references
0.8069102168083191
0 references
[For the entire collection see Zbl 0583.00027.] This paper deals with the linear model \(y=X\beta +\sigma \epsilon\) where \(E(\epsilon \epsilon ')=Q\). The unknown parameter \(\beta\) is constrained by \((\beta -\beta_ 0)'T(\beta -\beta_ 0)\leq k\) where T is a given symmetric nonnegative definite matrix. The main feature is that neither Q nor T are assumed to be regular. Linear minimax predictors and minimax estimators are considered for the usual quadratic risk. It is proved that such a predictor (estimator) can be obtained as the BLUP (BLUE) in a prediction (estimation) model deduced from the original one. Connexion with ridge-estimators is discussed.
0 references