Non-negative variance component estimation in the Gauss-Helmert adjustment model
The general Gauss-Helmert adjustment model reads: \(AX+B\epsilon =W\), \(E(\epsilon)=0\), \(E(\epsilon \epsilon ')=Q\), where A and B are, respectively, \(k\times m\) and \(k\times n\) known matrices, \(W=BL-c\), c a constant vector, L a vector of observations, X an unknown vector of parameters, \(\epsilon\) a vector of random errors, \(Q=\sum^{q}_{i=1}\sigma^ 2_ iQ_ i\) positive definite, and \(Q_ i\), \(\sigma^ 2_ i\), \(i=1,...,q(\leq n)\) are, respectively, positive semidefinite matrices and unknown variance components. The author derives the best quadratic unbiased estimator, the best quadratic estimator and the best quadratic unbiased non-negative estimator of individual variance components. The best quadratic minimum bias non-negative estimator in a variance-covariance model is also given.
- Best unbiased estimation of variance-covariance components: from condition adjustment to a generalized methodology
- A note on non-negative minimum bias MINQE in variance components model
- scientific article; zbMATH DE number 62424
- A universal formula of maximum likelihood estimation of variance-covariance components
- Best Nonnegative Invariant Partially Orthogonal Quadratic Estimation in Normal Regression
- The response ratio hypothesis for magnitude estimation
- A universal formula of maximum likelihood estimation of variance-covariance components
- Simplified formulae for the BIQUE estimation of variance components in disjunctive observation groups.
- Stress tensor inversion from focal mechanism data: variance component estimation approach for data weighting
This page was built for publication: Non-negative variance component estimation in the Gauss-Helmert adjustment model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3681769)