Abstract
In a general linear model, it is shown that all admissible linear estimators are limits of linear estimators that are uniquely best at some point in an extended parameter set. The principal result shows that a linear estimator that is uniquely best at a pointW 2 among multiple linear estimators that are best at a pointW 1 is the limit of uniquely best estimators at points approachingW 1 along the line joiningW 1 andW 2.
Similar content being viewed by others
References
Farrell RH (1968) Towards a theory of generalized Bayes tests. Ann Math Statist 39:1–22
LaMotte LR (1973) An optimal BLUE when V is singular. Unpublished manuscript
LaMotte LR (1977) On admissibility and completeness of linear unbiased estimators in a general linear model. J Amer Statist Assoc 72:438–441
LaMotte LR (1982) Admissibility in linear estimation. Ann Statist 10:245–255
LaMotte LR (1985) Admissibility, unbiasedness, and nonnegativity in the balanced, random, one-way ANOVA model. In: Caliński T, Klonecki W (Eds) Linear Statistical Inference, Proceedings of the International Conference held at Poznań, Poland, June 4–8, 1984, 184–199. Berlin Springer-Verlag
Olsen A, Seely J, Birkes D (1976) Invariant quadratic estimation for two variance components. Ann Statist 4:878–890
Rockafellar RT (1970) Convex analysis. Princeton, New Jersey, Princeton University Press
Stępniak C (1987) A complete class for linear estimation in a general linear model. Ann Inst Statist Math 39(A):563–573
Zontek S (1988) Admissibility of limits of the unique locally best linear estimators with application to variance components models. Probab Math Statist 9:29–44
Zontek S, Klonecki W (1990) Limiting admissible estimators for variance components. Comm Statist Theory Methods 19:2485–2508
Author information
Authors and Affiliations
Additional information
Research supported in part by U.S.A.F. Aerospace Research Laboratories under contract F33615-71-C-1463, summer 1973, and in part by Grant DMS-9104811 from the National Science Foundation.
Rights and permissions
About this article
Cite this article
LaMotte, L.R. On Limits of Uniquely Best Linear Estimators. Metrika 45, 197–211 (1997). https://doi.org/10.1007/BF02717103
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02717103