Robust designs for experiments with blocks

TL;DR

This paper develops robust experimental designs for block experiments with correlated errors, using neighborhood-based covariance modeling and simulated annealing to optimize design robustness.

Contribution

It introduces a neighborhood-based covariance model and a modified generalized least squares estimator for constructing robust block experiment designs.

Findings

Proposed a neighborhood model for error covariance matrices.

Developed a simulated annealing algorithm for robust design optimization.

Derived theoretical results supporting the design methodology.

Abstract

For experiments running in field plots or over time, the observations are often correlated due to spatial or serial correlation, which leads to correlated errors in a linear model analyzing the treatment means. Without knowing the exact correlation matrix of the errors, it is not possible to compute the generalized least squares estimator for the treatment means and use it to construct optimal designs for the experiments. In this paper we propose to use neighbourhoods to model the covariance matrix of the errors, and apply a modified generalized least squares estimator to construct robust designs for experiments with blocks. A minimax design criterion is investigated, and a simulated annealing algorithm is developed to find robust designs. We have derived several theoretical results, and representative examples are presented.