EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Embedded multilevel regression and poststratification: Model‐based inference with incomplete auxiliary information

Katherine Li, Yajuan Si iD

Statistics in Medicine · 30.01.2024 · 43 (2) · 256-278

DOI: 10.1002/sim.9956 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, online erschienen am 15.11.2023. Verfasst von Katherine Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, Michigan, USA. Hauptthemen laut MEDLINE: Bayes Theorem. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIMHD NIH HHS, National Science Foundation of Sri Lanka, National Institute on Minority Health and Health Disparities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Health disparity research often evaluates health outcomes across demographic subgroups. Multilevel regression and poststratification (MRP) is a popular approach for small subgroup estimation as it can stabilize estimates by fitting multilevel models and adjust for selection bias by poststratifying on auxiliary variables, which are population characteristics predictive of the analytic outcome. However, the granularity and quality of the estimates produced by MRP are limited by the availability of the auxiliary variables' joint distribution; data analysts often only have access to the marginal distributions. To overcome this limitation, we embed the estimation of population cell counts needed for poststratification into the MRP workflow: embedded MRP (EMRP). Under EMRP, we generate synthetic populations of the auxiliary variables before implementing MRP. All sources of estimation uncertainty are propagated with a fully Bayesian framework. Through simulation studies, we compare different methods of generating the synthetic populations and demonstrate EMRP's improvements over alternatives on the bias‐variance tradeoff to yield valid subpopulation inferences of interest. We apply EMRP to the Longitudinal Survey of Wellbeing and estimate food insecurity prevalence among vulnerable groups in New York City. We find that all EMRP estimators can correct for the bias in classical MRP while maintaining lower standard errors and narrower confidence intervals than directly imputing with the weighted finite population Bayesian bootstrap (WFPBB) and design‐based estimates. Performances from the EMRP estimators do not differ substantially from each other, though we would generally recommend using the WFPBB‐MRP for its consistently high coverage rates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremHumansBiasSelection BiasComputer SimulationLongitudinal Studies

Stichwörter der Autor:innen

Bayesian bootstrapincomplete poststratifierssequential imputationsynthetic population

Autor:innen und Institutionen

  • Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, Michigan, USA.
  • Survey Research Center, Institute for Social Research, University of Michigan, Ann Arbor, Michigan, USA.

ORCID-Profile: Yajuan Si

Förderung

  • NIMHD NIH HHS
  • National Science Foundation of Sri Lanka
  • National Institute on Minority Health and Health Disparities

Zitieren

APA

Li, K., & Si, Y. (2024). Embedded multilevel regression and poststratification: Model‐based inference with incomplete auxiliary information. Statistics in Medicine, 43(2), 256-278. https://doi.org/10.1002/sim.9956

Vancouver

Li K, Si Y. Embedded multilevel regression and poststratification: Model‐based inference with incomplete auxiliary information. Statistics in Medicine. 2024;43(2):256-278. doi:10.1002/sim.9956

BibTeX
@article{Li2024,
  author = {Li, Katherine and Si, Yajuan},
  title = {Embedded multilevel regression and poststratification: Model‐based inference with incomplete auxiliary information},
  journal = {Statistics in Medicine},
  year = {2024},
  volume = {43},
  number = {2},
  pages = {256--278},
  doi = {10.1002/sim.9956}
}
Kostenlos starten →