Algebraic representations, dimensional expressions, and characterizations are given for the subspace of functionals of the main parameters γ, which can be estimated with full efficiency under a linear model (y, Wγ + Zδ, σ2V) containing nuisance parameters δ. Subspaces of functionals of γ, for which the ordinary least-squares estimator is robust against an alternative dispersion matrix V, are obtained, and a particular subspace of such functionals is found wherein the ordinary least-squares estimator is both dispersion-matrix robust and robust against the presence of nuisance parameters.
ASJC Scopus subject areas
- Algebra and Number Theory
- Numerical Analysis
- Geometry and Topology
- Discrete Mathematics and Combinatorics