×

Bayes unbiased estimation in a model with three variance components. (English) Zbl 0689.62026

Summary: Necessary and sufficient conditions for an existence and an explicit expression for the Bayes invariant quadratic unbiased estimate of a linear function of variance components are presented for the mixed linear model \[ t=X\beta +\epsilon,\quad E(t)=X\beta,\quad Var(t)=\theta_ 1U_ 1+\theta_ 2U_ 2+\theta_ 3U_ 3, \] with three unknown variance components in the normal case. An application to some examples from the analysis of variance is given.

MSC:

62F15 Bayesian inference
62H12 Estimation in multivariate analysis
62J10 Analysis of variance and covariance (ANOVA)
62J99 Linear inference, regression
PDF BibTeX XML Cite
Full Text: EuDML

References:

[1] S. Gnot J. Kleffe: Quadratic estimation in mixed linear models with two variance components. Journal of Statist. Planning and Inference 8 (1983), 267-279. · Zbl 0561.62064
[2] J. Kleffe R. Pincus: Bayes and best quadratic unbiased estimators for parameters of the covariance matrix in a normal linear model. Math. Operationsf. Statist. 5 (1974), 43 - 67. · Zbl 0277.62027
[3] A. Olsen J. Seely D. Birkes: Invariant quadratic unbiased estimation for two variance components. Ann. Statist. 4 (1976), 878-890. · Zbl 0344.62060
[4] C. R. Rao: Linear Statistical Inference and Its Applications. 2nd J. Wiley, New York 1973. · Zbl 0256.62002
[5] C. R. Rao: Minimum variance quadratic unbiased estimation of variance components. J. Multivariate Anal. I (1971), 445-456. · Zbl 0259.62061
[6] J. Stuchlý: Bayes unbiased estimation in a model with two variance components. Aplikace matematiky 32, No. 2 (1987), 120-130. · Zbl 0625.62019
[7] S. Zacks: The Theory of Statistical Inference. J. Wiley, New York, 1971.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.