Abstract
Albert’s Theorem, which is closely related to general results on Schur complements can be successfully applied to statistical problems.
In the present paper a concise proof for a slightly more general version of the theorem will be given. Two applications on efficiency and a structured overview of results on MSE superiority are then presented. They are the main statistical results of this self-contained paper.
In the present paper a concise proof for a slightly more general version of the theorem will be given. Two applications on efficiency and a structured overview of results on MSE superiority are then presented. They are the main statistical results of this self-contained paper.
| Original language | English |
|---|---|
| Pages (from-to) | 157-167 |
| Number of pages | 11 |
| Journal | Statistica Neerlandica |
| Volume | 43 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - Sept-1989 |
Keywords
- covariance matrix difference
- Lowner ordering
- generalized inverse
- mean-squarederror matrix difference