Design of agricultural field experiments accounting for both complex blocking structures and network effects

TY - JOUR

T1 - Design of agricultural field experiments accounting for both complex blocking structures and network effects

AU - Koutra, Vasiliki

AU - Gilmour, Steven G.

AU - Parker, Ben M.

AU - Mead, Andrew

N1 - Funding Information: The authors gratefully acknowledge funding for this research. Most of it was supported by a studentship from the ESRC South Coast Doctoral Training Partnership, and the research was completed under EPSRC grant EP/T021624/1 Multi-Objective Optimal Design of Experiments. The work was initiated under an internship scheme at Rothamsted Research in the Applied Statistics Group. The authors are grateful for constructive comments from the anonymous reviewers that improved the paper. Funding Information: The authors gratefully acknowledge funding for this research. Most of it was supported by a studentship from the ESRC South Coast Doctoral Training Partnership, and the research was completed under EPSRC grant EP/T021624/1 Multi-Objective Optimal Design of Experiments. The work was initiated under an internship scheme at Rothamsted Research in the Applied Statistics Group. The authors are grateful for constructive comments from the anonymous reviewers that improved the paper. Publisher Copyright: © 2023, The Author(s).

PY - 2023/9

Y1 - 2023/9

N2 - We propose a novel model-based approach for constructing optimal designs with complex blocking structures and network effects for application in agricultural field experiments. The potential interference among treatments applied to different plots is described via a network structure, defined via the adjacency matrix. We consider a field trial run at Rothamsted Research and provide a comparison of optimal designs under various different models, specifically new network designs and the commonly used designs in such situations. It is shown that when there is interference between treatments on neighboring plots, designs incorporating network effects to model this interference are at least as efficient as, and often more efficient than, randomized row–column designs. In general, the advantage of network designs is that we can construct the neighbor structure even for an irregular layout by means of a graph to address the particular characteristics of the experiment. As we demonstrate through the motivating example, failing to account for the network structure when designing the experiment can lead to imprecise estimates of the treatment parameters and invalid conclusions.Supplementary materials accompanying this paper appear online.

AB - We propose a novel model-based approach for constructing optimal designs with complex blocking structures and network effects for application in agricultural field experiments. The potential interference among treatments applied to different plots is described via a network structure, defined via the adjacency matrix. We consider a field trial run at Rothamsted Research and provide a comparison of optimal designs under various different models, specifically new network designs and the commonly used designs in such situations. It is shown that when there is interference between treatments on neighboring plots, designs incorporating network effects to model this interference are at least as efficient as, and often more efficient than, randomized row–column designs. In general, the advantage of network designs is that we can construct the neighbor structure even for an irregular layout by means of a graph to address the particular characteristics of the experiment. As we demonstrate through the motivating example, failing to account for the network structure when designing the experiment can lead to imprecise estimates of the treatment parameters and invalid conclusions.Supplementary materials accompanying this paper appear online.

UR - http://www.scopus.com/inward/record.url?scp=85153116803&partnerID=8YFLogxK

U2 - 10.1007/s13253-023-00544-3

DO - 10.1007/s13253-023-00544-3

M3 - Article

SN - 1085-7117

VL - 28

SP - 526

EP - 548

JO - JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS

JF - JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS

IS - 3

ER -