Optimal sampling design for the gls estimators of the mean parameters for the stationary spatial random process

Dučinskas, Kęstutis; Borisenko, Ingrida

Use this url to cite publication: https://hdl.handle.net/20.500.14172/12589

Optimal sampling design for the gls estimators of the mean parameters for the stationary spatial random process

Type of publication

Straipsnis recenzuojamoje Lietuvos tarptautinės konferencijos medžiagoje / Article in peer-reviewed Lithuanian international conference proceedings (P1e)

Type of document

type::text::conference output::conference proceedings::conference paper

Author(s)

Author	Affiliation
Dučinskas, Kęstutis	Informatikos ir statistikos katedra / Department of Informatics and Statistics (2703)
Borisenko, Ingrida	Informatikos ir statistikos katedra / Department of Informatics and Statistics (2703)

Title

Optimal sampling design for the gls estimators of the mean parameters for the stationary spatial random process

[en]

Date Issued

Date
2009

Extent

p. 23-26

Is part of

The XIIIth international conference Applied stochastic models and data analysis : ASMDA-2009, June 30-July 3, 2009, Vilnius, Lithuania : selected papers. Vilnius : Technika, 2009. ISBN 9789955284635.

Research Area

Field of Science

Keywords (en)

Abstract (en)

The performance of estimators of the mean parameters for the stationary spatial random process (SRP) are affected substantially by the spatial configuration of locations where observations are taken (sampling design). Criteria functions for D-optimal and A-optimal sampling designs for GLS estimators of mean parameters based on spatial semivariogram are derived. In the case of stationary SRP with exponential semivariogram the second-order neighborhood scheme are numerically investigated.