EUVIMEDDécouvrir EUVIMED
Open access · CC BY-NC-ND 4.0

Bayesian Sensitivity Analysis for Causal Estimation With Time‐Varying Unmeasured Confounding

Yushu Zou iD, Liangyuan Hu iD, Amanda Ricciuto iD, Mark Deneau iD, Kuan Liu iD

Statistics in Medicine · 2026-03 · 45 (6-7)

DOI: 10.1002/sim.70481 ↗

At a glance

Journal article in Statistics in Medicine, published online on 2026-03-10. Written by Yushu Zou and 4 co-authors. Institution: Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada. Major MEDLINE topics: Causality. Cited 1 times so far (Crossref); 47 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: NIH HHS, Data Sciences Institute at the University of Toronto, National Institutes of Health.

RésuméSubjectsRéférences bibliographiquesCiteRelated studies

Abstract (original language)

Causal inference relies on the untestable assumption of no unmeasured confounding to ensure the causal parameter of interest is identifiable. Sensitivity analysis quantifies the unmeasured confounding's impact on causal estimates. Among sensitivity analysis methods proposed in the literature, the latent confounder approach is favored for its intuitive interpretation via the use of bias parameters to specify the relationship between the observed and unobserved variables, and the sensitivity function approach directly characterizes the net causal effect of the unmeasured confounding without explicitly introducing latent variables to the causal models. In this paper, we developed and extended these two sensitivity analysis approaches, namely the Bayesian sensitivity analysis with latent confounding variables and the Bayesian sensitivity function approach for the estimation of time‐varying treatment effects with longitudinal observational data subjected to time‐varying unmeasured confounding. We investigated the performance of these methods in a series of simulation studies and applied them to a multicenter pediatric disease registry to provide practical guidance on their implementation.

Subjects

MeSH terms (MEDLINE)

CausalityBayes TheoremHumansComputer SimulationLongitudinal StudiesConfounding Factors, EpidemiologicModels, StatisticalBiasRegistries

Author keywords

Bayesian sensitivity analysislongitudinal datasensitivity functionunmeasured confounding

Authors and institutions

  • Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.
  • Public Health Ontario, Toronto, Ontario, Canada.
  • Department of Biostatistics and Epidemiology, Rutgers School of Public Health, Rutgers University, Piscataway, New Jersey, USA.
  • Division of Gastroenterology, Hepatology and Nutrition, The Hospital for Sick Children, Toronto, Ontario, Canada.
  • Division of Pediatric Gastroenterology, Department of Pediatrics, University of Utah School of Medicine, Salt Lake City, Utah, USA.

ORCID profiles: Yushu Zou, Liangyuan Hu, Amanda Ricciuto, Mark Deneau, Kuan Liu

Funding

  • NIH HHS
  • Data Sciences Institute at the University of Toronto
  • National Institutes of Health

Cite

APA

Zou, Y., Hu, L., Ricciuto, A., Deneau, M., & Liu, K. (2026). Bayesian Sensitivity Analysis for Causal Estimation With Time‐Varying Unmeasured Confounding. Statistics in Medicine, 45(6-7). https://doi.org/10.1002/sim.70481

Vancouver

Zou Y, Hu L, Ricciuto A, Deneau M, Liu K. Bayesian Sensitivity Analysis for Causal Estimation With Time‐Varying Unmeasured Confounding. Statistics in Medicine. 2026;45(6-7). doi:10.1002/sim.70481

BibTeX
@article{Zou2026,
  author = {Zou, Yushu and Hu, Liangyuan and Ricciuto, Amanda and Deneau, Mark and Liu, Kuan},
  title = {Bayesian Sensitivity Analysis for Causal Estimation With Time‐Varying Unmeasured Confounding},
  journal = {Statistics in Medicine},
  year = {2026},
  volume = {45},
  number = {6-7},
  doi = {10.1002/sim.70481}
}
Start for free →