How well do covariates perform when adjusting for sampling bias in online COVID‑19 research? Insights from multiverse analyses

Vista sencilla de ítem
dc.contributor.authorJoyal Desmarais, Keven
dc.contributor.authorStojanovic, Jovana
dc.contributor.authorKennedy, Eric B.
dc.contributor.authorEnticott, Joanne C.
dc.contributor.authorGosselin Boucher, Vincent
dc.contributor.authorVo, Hung
dc.contributor.authorKošir, Urška
dc.contributor.authorLavoie, Kim L.
dc.contributor.authorBacon, Simon L.
dc.contributor.authorLosada, Analía Verónica
dc.contributor.authoriCARE Study Team (Canadá)
dc.date.accessioned2025-09-05T23:09:18Z
dc.date.available2025-09-05T23:09:18Z
dc.date.issued2022
dc.description.abstractCOVID-19 research has relied heavily on convenience-based samples, which—though often necessary—are susceptible to important sampling biases. We begin with a theoretical overview and introduction to the dynamics that underlie samplingbias. We then empirically examine sampling bias in online COVID-19 surveys and evaluate the degree to which common statistical adjustments for demographic covariates successfully attenuate such bias. This registered study analysed responses to identical questions from three convenience and three largely representative samples (total N=13,731) collected online in Canada within the International COVID-19 Awareness and Responses Evaluation Study (www.icarestudy.com). We compared samples on 11 behavioural and psychological outcomes (e.g., adherence to COVID-19 prevention measures, vaccine intentions) across three time points and employed multiverse-style analyses to examine how 512 combinations of demographic covariates (e.g., sex, age, education, income, ethnicity) impacted sampling discrepancies on these outcomes. Signifcant discrepancies emerged between samples on 73% of outcomes. Participants in the convenience samples held more positive thoughts towards and engaged in more COVID-19 prevention behaviours. Covariates attenuated sampling diferences in only 55% of cases and increased diferences in 45%. No covariate performed reliably well. Our results suggest that online convenience samples may display more positive dispositions towards COVID-19 prevention behaviours being studied than would samples drawn using more representative means. Adjusting results for demographic covariates frequently increased rather than decreased bias, suggesting that researchers should be cautious when interpreting adjusted fndings. Using multiversestyle analyses as extended sensitivity analyses is recommended.en
dc.description.filiationJoyal Desmarais, Keven. Concordia University; Canada.
dc.description.filiationJoyal Desmarais, Keven. Montreal Behavioural Medicine Centre; Canada.
dc.description.filiationStojanovic, Jovana. Montreal Behavioural Medicine Centre; Canada.
dc.description.filiationStojanovic, Jovana. Canadian Agency for Drugs and Technologies in Health; Canada.
dc.description.filiationKennedy, Eric B. York University; Canada.
dc.description.filiationEnticott, Joanne C. Monash University; Australia.
dc.description.filiationGosselin Boucher, Vincent. University of British Columbia; Canada.
dc.description.filiationVo, Hung. Austin Health; Australia.
dc.description.filiationKošir, Urška. Concordia University; Canada.
dc.description.filiationKošir, Urška. Montreal Behavioural Medicine Centre; Canada.
dc.description.filiationLavoie, Kim L. Montreal Behavioural Medicine Centre; Canada.
dc.description.filiationLavoie, Kim L. Université du Québec à Montréal; Canada.
dc.description.filiationBacon, Simón L. Concordia University; Canada.
dc.description.filiationBacon, Simón L. Montreal Behavioural Medicine Centre; Canada.
dc.description.filiationLosada, Analía Verónica. Universidad de Flores; Argentina.
dc.identifier.citationJoyal Desmarais, K,, Stojanovic, J., Kennedy, E. B., Enticott, J. C., Gosselin Boucher, V., Vo, H., Košir, U., Lavoie, K. L., Bacon, S. L., & iCARE Study Team. (2022). How well do covariates perform when adjusting for sampling bias in online COVID‑19 research? Insights from multiverse analyses. European Journal of Epidemiology, 37, 1233-1250. https://link.springer.com/article/10.1007/s10654-022-00932-y#citeasen
dc.identifier.doihttps://doi.org/10.1007/s10654-022-00932-y
dc.identifier.issn1573-7284
dc.identifier.urihttps://hdl.handle.net/20.500.14340/2697
dc.language.isoenen
dc.publisherSpringer Nature (Alemania; Reino Unido)
dc.rightsopenAccess
dc.rights.uriother
dc.subjectANALISIS MULTIVARIANTEes_AR
dc.subjectSESGO DE MUESTREOes_AR
dc.subjectCOVARIABLESes_AR
dc.subjectPANDEMIAes_AR
dc.subjectCOVID-19es_AR
dc.subjectINVESTIGACIONes_AR
dc.subjectESTADISTICAes_AR
dc.titleHow well do covariates perform when adjusting for sampling bias in online COVID‑19 research? Insights from multiverse analysesen
dc.typeArtículoes_AR
dc.type.versionpublishedVersion
dspace.entity.typeArtículo

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Articulo_Joyal.pdf
Tamaño:
3.71 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.44 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Artículos