Estimation in a special structure of the linear model. (English) Zbl 0779.62061

The author considers a linear model with diagonal covariance matrix whose elements have the form \(\sigma^ 2(a+b|\varphi|)^ 2\), where \(\sigma^ 2\), \(a\) and \(b\) are known positive constants. A locally best linear-quadratic unbiased estimator of the elements of the covariance matrix is investigated in some simple cases. The method can be generalized to general cases.


62J05 Linear regression; mixed models
62F10 Point estimation
Full Text: EuDML


[1] FAJT V.: Electrical Measurements. (Czech), SNTL/ALFA, Praha, 1978.
[2] HUMAK K. M. S.: Statistische Methoden der Modellbildung III. Akademie Verlag, Berlin, 1984. · Zbl 0556.62051
[3] KUBÁČEK L.: Foundations of Estimation Theory. Elsevier, Amsterdam, 1988. · Zbl 0698.62004
[4] RAO C. R.: Linear Statistical Inference and Its Applications. J.Wiley, New York, 1965. · Zbl 0137.36203
[5] RAO C. R., MITRA S. K.: Generalized Inverse of Matrices and Its Applications. J. Wiley, New York, 1971. · Zbl 0236.15005
[6] RINNER K., BENZF.: Jordan/Eggert/Kneissl Handbuch der Vermessungskunde. Band VI, Stuttgart, 1966.
[7] WIMMER G.: Linear model with variances depending on the mean value. Math. Slovaca 42 (1992), 223-238. · Zbl 0764.62055
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.