Please use this identifier to cite or link to this item:
Title: How well do covariates perform when adjusting for sampling bias in online COVID-19 research? Insights from multiverse analyses.
Austin Authors: Joyal-Desmarais, Keven;Stojanovic, Jovana;Kennedy, Eric B;Enticott, Joanne C;Boucher, Vincent Gosselin;Vo, Hung ;Košir, Urška;Lavoie, Kim L;Bacon, Simon L
Affiliation: Department of Health, Kinesiology and Applied Physiology, Concordia University
Montreal Behavioural Medicine Centre, CIUSSS-NIM, Montreal, Canada.
Disaster and Emergency Management, York University, Toronto, Canada.
Department of General Practice, Monash University, Melbourne, Australia.
School of Kinesiology, University of British Columbia, Vancouver, BC, Canada.
Austin Health
Issue Date: Nov-2022
Date: 2022
Publication information: European Journal of Epidemiology 2022
Abstract: COVID-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 sampling bias. 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 ( ). 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. Significant 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 differences in only 55% of cases and increased differences 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 findings. Using multiverse-style analyses as extended sensitivity analyses is recommended.
DOI: 10.1007/s10654-022-00932-y
ORCID: 0000-0003-0657-8367
Journal: European Journal of Epidemiology
Start page: 1233
End page: 1250
PubMed URL: 36335560
ISSN: 1573-7284
Type: Journal Article
Subjects: COVID-19
Collider bias
Covariate adjustment
Multiverse analysis
Sampling bias
Selection bias
COVID-19/prevention & control
Appears in Collections:Journal articles

Show full item record

Page view(s)

checked on Dec 1, 2023

Google ScholarTM


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.