In the paper four types of estimations of the linear function of the variance components are presented for the mixed linear model $\bold{Y=X \beta + e}$ with expectation $E(\bold{Y)=X \beta}$ and covariance matrix $D(\bold{Y)=0_1V_1 + ... + 0_mV_m}$.
@article{104450, author = {\v Stefan Varga}, title = {Quadratic estimations in mixed linear models}, journal = {Applications of Mathematics}, volume = {36}, year = {1991}, pages = {134-144}, zbl = {0742.62074}, mrnumber = {1097697}, language = {en}, url = {http://dml.mathdoc.fr/item/104450} }
Varga, Štefan. Quadratic estimations in mixed linear models. Applications of Mathematics, Tome 36 (1991) pp. 134-144. http://gdmltest.u-ga.fr/item/104450/
Best quadratic unbiased estimators for variance components in mixed linear models, Sankhya, 38 (1976), 179-186. (1976) | MR 0468051 | Zbl 0413.62052
Estimation of variance and covariance components - MINQUE theory, Journ. Multivariant. Analysis, 1 (1971), 257-275. (1971) | MR 0301869 | Zbl 0223.62086
Generalized Inverse of Matrices and its Application, J. Wiley, N. York 1971. (1971) | MR 0338013
Estimation of Variance Components, In: P. R. Krisnaiah, ed. Handbook of Statistics, Vol. I. North Holland, N. York, (1980), 1-40. (1980)
Minimum Variance Quadratic Unbiased Estimation of Variance Components, Math. Slovaca, 36 No. 2 (1986), 163-170. (1986) | MR 0849707 | Zbl 0605.62077
Estimations in Mixed Linear Models, Sborník VŠCHT Praha Řada M - Matematika, (1990), 1-10. (1990)