EUVIMEDDescoperă EUVIMED
Open access

Practical strategies for operationalizing optimal allocation in stratified cluster‐based outcome‐dependent sampling designs

Sara Sauer iD, Bethany Hedt-Gauthier, Sebastien Haneuse

Statistics in Medicine · 2023

DOI: 10.1002/sim.9650 ↗

At a glance

Journal article in Statistics in Medicine, 2023. Written by Sara Sauer and 2 co-authors. Institution: Department of Global Health and Social Medicine, Harvard Medical School, Boston, Massachusetts, USA. Major MEDLINE topics: Research Design. Cited 1 times so far (Crossref); 21 references. The full text is freely available in PubMed Central. Funded by: NHLBI NIH HHS, NIEHS NIH HHS, National Institute of Environmental Health Sciences.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Cluster‐based outcome‐dependent sampling (ODS) has the potential to yield efficiency gains when the outcome of interest is relatively rare, and resource constraints allow only a certain number of clusters to be visited for data collection. Previous research has shown that when the intended analysis is inverse‐probability weighted generalized estimating equations, and the number of clusters that can be sampled is fixed, optimal allocation of the (cluster‐level) sample size across strata defined by auxiliary variables readily available at the design stage has the potential to increase efficiency in the estimation of the parameter(s) of interest. In such a setting, the optimal allocation formulae depend on quantities that are unknown in practice, currently making such designs difficult to implement. In this paper, we consider a two‐wave adaptive sampling approach, in which data is collected from a first wave sample, and subsequently used to compute the optimal second wave stratum‐specific sample sizes. We consider two strategies for estimating the necessary components using the first wave data: an inverse‐probability weighting (IPW) approach and a multiple imputation (MI) approach. In a comprehensive simulation study, we show that the adaptive sampling approach performs well, and that the MI approach yields designs that are very near‐optimal, regardless of the covariate type. The IPW approach, on the other hand, has mixed results. Finally, we illustrate the proposed adaptive sampling procedures with data on maternal characteristics and birth outcomes among women enrolled in the Safer Deliveries program in Zanzibar, Tanzania.

Subjects

MeSH terms (MEDLINE)

Research DesignHumansFemaleSample SizeComputer SimulationProbabilityData Collection

Author keywords

adaptive samplinggeneralized estimating equationsmultilevel multiple imputationoptimal allocationoutcome-dependent sampling

Authors and institutions

  • Department of Global Health and Social Medicine, Harvard Medical School, Boston, Massachusetts, USA.
  • Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA.

ORCID profiles: Sara Sauer

Funding

  • NHLBI NIH HHS
  • NIEHS NIH HHS
  • National Institute of Environmental Health Sciences
  • National Institutes of Health

Cite

APA

Sauer, S., Hedt-Gauthier, B., & Haneuse, S. (2023). Practical strategies for operationalizing optimal allocation in stratified cluster‐based outcome‐dependent sampling designs. Statistics in Medicine. https://doi.org/10.1002/sim.9650

Vancouver

Sauer S, Hedt-Gauthier B, Haneuse S. Practical strategies for operationalizing optimal allocation in stratified cluster‐based outcome‐dependent sampling designs. Statistics in Medicine. 2023. doi:10.1002/sim.9650

BibTeX
@article{Sauer2023,
  author = {Sauer, Sara and Hedt-Gauthier, Bethany and Haneuse, Sebastien},
  title = {Practical strategies for operationalizing optimal allocation in stratified cluster‐based outcome‐dependent sampling designs},
  journal = {Statistics in Medicine},
  year = {2023},
  doi = {10.1002/sim.9650}
}
Start for free →