Decomposition of Prediction Error (Q3676988)
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 3898044
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Decomposition of Prediction Error |
scientific article; zbMATH DE number 3898044 |
Statements
1985
0 references
decomposition of prediction error
0 references
best linear unbiased prediction
0 references
mixed linear models
0 references
empirical Bayes estimation
0 references
James-Stein estimator
0 references
different stages of knowledge
0 references
random one way classification model
0 references
Decomposition of Prediction Error (English)
0 references
0.7508698105812073
0 references
0.749554455280304
0 references
0.7424005270004272
0 references
0.7406286597251892
0 references
The author considers random vectors y and w and the prediction of w by means of y. This prediction is done under the different stages of knowledge: (i) knowledge of the joint distribution, (ii) knowledge of the first and second moments, (iii) the full rank regular regression model, (iv) in the regression model the variances and covariances are depending on an unknown parameter. In each case predictors are proposed which are in a certain sense optimal. The prediction error is decomposed into four components. Finally the four prediction principles are applied to the random one way classification model.
0 references