Efficient design of geographically-defined clusters with spatial autocorrelation

Research output: Contribution to journalArticlepeer-review

Standard

Efficient design of geographically-defined clusters with spatial autocorrelation. / I. Watson, Samuel.

In: Journal of Applied Statistics, 17.06.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{e7dbe0e0d08042d697bc0312513c16f1,
title = "Efficient design of geographically-defined clusters with spatial autocorrelation",
abstract = "Clusters form the basis of a number of research study designs including survey and experimental studies. Cluster-based designs can be less costly but also less efficient than individual-based designs due to correlation between individuals within the same cluster. Their design typically relies on ad hoc choices of correlation parameters, and is insensitive to variations in cluster design. This article examines how to efficiently design clusters where they are geographically defined by demarcating areas incorporating individuals and households or other units. Using geostatistical models for spatial autocorrelation, we generate approximations to within cluster average covariance in order to estimate the effective sample size given particular cluster design parameters. We show how the number of enumerated locations, cluster area, proportion sampled, and sampling method affect the efficiency of the design and consider the optimization problem of choosing the most efficient design subject to budgetary constraints. We also consider how the parameters from these approximations can be interpreted simply in terms of {\textquoteleft}real-world{\textquoteright} quantities and used in design analysis.",
keywords = "Sampling, cluster randomised trial, power, spatial",
author = "{I. Watson}, Samuel",
note = "Publisher Copyright: {\textcopyright} 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.",
year = "2021",
month = jun,
day = "17",
doi = "10.1080/02664763.2021.1941807",
language = "English",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Taylor & Francis",

}

RIS

TY - JOUR

T1 - Efficient design of geographically-defined clusters with spatial autocorrelation

AU - I. Watson, Samuel

N1 - Publisher Copyright: © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

PY - 2021/6/17

Y1 - 2021/6/17

N2 - Clusters form the basis of a number of research study designs including survey and experimental studies. Cluster-based designs can be less costly but also less efficient than individual-based designs due to correlation between individuals within the same cluster. Their design typically relies on ad hoc choices of correlation parameters, and is insensitive to variations in cluster design. This article examines how to efficiently design clusters where they are geographically defined by demarcating areas incorporating individuals and households or other units. Using geostatistical models for spatial autocorrelation, we generate approximations to within cluster average covariance in order to estimate the effective sample size given particular cluster design parameters. We show how the number of enumerated locations, cluster area, proportion sampled, and sampling method affect the efficiency of the design and consider the optimization problem of choosing the most efficient design subject to budgetary constraints. We also consider how the parameters from these approximations can be interpreted simply in terms of ‘real-world’ quantities and used in design analysis.

AB - Clusters form the basis of a number of research study designs including survey and experimental studies. Cluster-based designs can be less costly but also less efficient than individual-based designs due to correlation between individuals within the same cluster. Their design typically relies on ad hoc choices of correlation parameters, and is insensitive to variations in cluster design. This article examines how to efficiently design clusters where they are geographically defined by demarcating areas incorporating individuals and households or other units. Using geostatistical models for spatial autocorrelation, we generate approximations to within cluster average covariance in order to estimate the effective sample size given particular cluster design parameters. We show how the number of enumerated locations, cluster area, proportion sampled, and sampling method affect the efficiency of the design and consider the optimization problem of choosing the most efficient design subject to budgetary constraints. We also consider how the parameters from these approximations can be interpreted simply in terms of ‘real-world’ quantities and used in design analysis.

KW - Sampling

KW - cluster randomised trial

KW - power

KW - spatial

UR - http://www.scopus.com/inward/record.url?scp=85108786052&partnerID=8YFLogxK

U2 - 10.1080/02664763.2021.1941807

DO - 10.1080/02664763.2021.1941807

M3 - Article

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

ER -