Correlated optimum design with parametrized covariance function. Justification of the Fisher information matrix and of the method of virtual noise.

2004/01/01 by Andrej Pázman, Pazman, Andrej
Computer Science · Decision Sciences · #Advanced Multi-Objective Optimization Algorithms #Optimal Experimental Design Methods

paper · pdf · doi:10.57938/0720e841-aea2-4c8e-922c-b60f834f65a4

openalex publication_date 2004/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/23

Abstract

We consider observations of a random field (or a random process), which is modeled by a nonlinear regression with a parametrized mean (or trend) and a parametrized covariance function. In the first part we show that under the assumption that the errors are normal with small variances, even when the number of observations is small, the ML estimators of both parameters are approximately unbiased, uncorrelated, with variances given by the inverse of the Fisher information matrix. In the second part we are extending the result of Pazman & Müller (2001) to the case of parametrized covariance function, namely we prove that the optimum designs with and without the presence of the virtual noise are identical. This in principle justify the use the method of virtual noise as a computational device also in this case. (authors' abstract)

Related

• Optimal Design of Experiments Subject to Correlated Errors
• Extended Information Matrices for Optimal Designs when the Observations are Correlated II
• Extended Information Matrices for Optimal Designs when the Observations are Correlated
• A convex approach to optimum design of experiments with correlated observations
• Elimination of less informative design points in regression models with a known or parametrized covariance function