Inference is bliss: Simulation for power estimation for an observational study of a cholera outbreak intervention.

Ruwan Ratnayake ORCID logo; Francesco Checchi ORCID logo; Christopher I Jarvis ORCID logo; W John Edmunds ORCID logo; Flavio Finger ORCID logo; (2022) Inference is bliss: Simulation for power estimation for an observational study of a cholera outbreak intervention. PLoS neglected tropical diseases, 16 (2). e0010163-. ISSN 1935-2727 DOI: 10.1371/journal.pntd.0010163
Copy

BACKGROUND: The evaluation of ring vaccination and other outbreak-containment interventions during severe and rapidly-evolving epidemics presents a challenge for the choice of a feasible study design, and subsequently, for the estimation of statistical power. To support a future evaluation of a case-area targeted intervention against cholera, we have proposed a prospective observational study design to estimate the association between the strength of implementation of this intervention across several small outbreaks (occurring within geographically delineated clusters around primary and secondary cases named 'rings') and its effectiveness (defined as a reduction in cholera incidence). We describe here a strategy combining mathematical modelling and simulation to estimate power for a prospective observational study. METHODOLOGY AND PRINCIPAL FINDINGS: The strategy combines stochastic modelling of transmission and the direct and indirect effects of the intervention in a set of rings, with a simulation of the study analysis on the model results. We found that targeting 80 to 100 rings was required to achieve power ≥80%, using a basic reproduction number of 2.0 and a dispersion coefficient of 1.0-1.5. CONCLUSIONS: This power estimation strategy is feasible to implement for observational study designs which aim to evaluate outbreak containment for other pathogens in geographically or socially defined rings.


picture_as_pdf
Ratnayake_etal_2022_Inference-is-bliss-simulation-for.pdf
subject
Published Version
Available under Creative Commons: 4.0

View Download

Atom BibTeX OpenURL ContextObject in Span Multiline CSV OpenURL ContextObject Dublin Core Dublin Core MPEG-21 DIDL EndNote HTML Citation JSON MARC (ASCII) MARC (ISO 2709) METS MODS RDF+N3 RDF+N-Triples RDF+XML RIOXX2 XML Reference Manager Refer Simple Metadata ASCII Citation EP3 XML
Export

Downloads