EUVIMEDOdkrijte EUVIMED
Open access

Multilevel Regression and Poststratification Using Margins of Poststratifiers: Improving Inference for HIV Health Outcomes During the COVID‐19 Pandemic

Amy J Pitts iD, Maiko Yomogida, Angela Aidala iD, Andrew Gelman, Qixuan Chen

Statistics in Medicine · 2025

DOI: 10.1002/sim.70223 ↗

At a glance

Journal article in Statistics in Medicine, 2025. Written by Amy J Pitts and 4 co-authors. Institution: Department of Biostatistics, Columbia University, New York, New York, USA. Major MEDLINE topics: COVID-19, HIV Infections, Models, Statistical, Multilevel Analysis. Cited 2 times so far (Crossref); 39 references. The full text is freely available in PubMed Central. Funded by: NIH HHS, HRSA HHS, NIEHS NIH HHS.

PovzetekSubjectsBibliografski podatkiCiteRelated studies

Abstract (original language)

Multilevel regression and poststratification (MRP) has surged in popularity for population inference using survey samples. The method consists of two stages: First, fitting a regularized model that regresses the outcome on poststratification variables; second, predicting the outcome using the regularized model and aggregating the predictions to make population inferences. Existing MRP methods mostly focus on settings where the joint distribution of the poststratifiers is known in the population. However, in practice, such data information is often not available; instead, we are provided with the margins of the poststratifiers. Motivated by this challenge, we propose an adapted MRP in which we model both the survey outcome that we would like to estimate in the population and the population sizes of subgroups formed by the poststratifiers. We consider Poisson and negative binomial models for the population sizes of subgroups when the number of poststratifiers is small and Bayesian additive regression trees when there are many poststratifying variables. We apply the adapted MRP to estimate the proportion of viral load suppression and means of mental and physical health scales among persons with HIV in New York City using the 2018–2021 wave of the Community Health Advisory and Information Network survey, in which sampling and in‐person data collection were disrupted by the COVID‐19 pandemic.

Subjects

MeSH terms (MEDLINE)

COVID-19HIV InfectionsModels, StatisticalMultilevel AnalysisHumansBayes TheoremRegression AnalysisPandemics

Author keywords

BARTBayesian inferenceMRPrakingsampling bias

Authors and institutions

  • Department of Biostatistics, Columbia University, New York, New York, USA.
  • Department of Sociomedical Sciences, Columbia University, New York, New York, USA.
  • Department of Statistics and Political Science, Columbia University, New York, New York, USA.
  • Division of Social Solutions and Services Research, Nathan S. Kline Institute for Psychiatric Research, Orangeburg, New York, USA.

ORCID profiles: Amy J Pitts, Angela Aidala

Funding

  • NIH HHS
  • HRSA HHS
  • NIEHS NIH HHS
  • NIDA NIH HHS
  • NIA NIH HHS
  • National Institutes of Health
  • Health Resources and Services Administration

Cite

APA

Pitts, A. J., Yomogida, M., Aidala, A., Gelman, A., & Chen, Q. (2025). Multilevel Regression and Poststratification Using Margins of Poststratifiers: Improving Inference for HIV Health Outcomes During the COVID‐19 Pandemic. Statistics in Medicine. https://doi.org/10.1002/sim.70223

Vancouver

Pitts AJ, Yomogida M, Aidala A, Gelman A, Chen Q. Multilevel Regression and Poststratification Using Margins of Poststratifiers: Improving Inference for HIV Health Outcomes During the COVID‐19 Pandemic. Statistics in Medicine. 2025. doi:10.1002/sim.70223

BibTeX
@article{Pitts2025,
  author = {Pitts, Amy J and Yomogida, Maiko and Aidala, Angela and Gelman, Andrew and Chen, Qixuan},
  title = {Multilevel Regression and Poststratification Using Margins of Poststratifiers: Improving Inference for HIV Health Outcomes During the COVID‐19 Pandemic},
  journal = {Statistics in Medicine},
  year = {2025},
  doi = {10.1002/sim.70223}
}
Start for free →