Note on general linear estimators and matrix inverses
From MaRDI portal
For a Gauss-Markov model \(E(L)=AX\), the author proves that the condition A\({\mathcal G}A=A\) is not necessary for the operator \({\mathcal G}\) of the unbiased estimator \(\hat L_ 0=A_ 0{\mathcal G}L=HL\) of the function \(L_ 0=A_ 0X\), and an estimability condition \(A_ 0{\mathcal G}A=A_ 0\) without any restriction on \({\mathcal G}\) is proposed. An unique loop inverse is an example of such operators \({\mathcal G}\) which are not explicitly computed in practice.
Recommendations
- scientific article; zbMATH DE number 4022399
- Admissible linear estimators in the general Gauss-Markov model
- Admissible linear estimators of an arbitrary vector of parametric functions in the general Gauss-Markov model
- Two matrix-based proofs that the linear estimator G y is the best linear unbiased estimator
- scientific article; zbMATH DE number 3956252
Cited in
(3)
This page was built for publication: Note on general linear estimators and matrix inverses
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3323042)