EUVIMEDEUVIMED entdecken
Open Access

Multivariate causal effects: a Bayesian causal regression factor model

Dafne Zorzetto, Jenna Landy, Corwin Zigler, Giovanni Parmigiani iD, Roberta De Vito

Biometrics · 09.04.2026 · 82 (2)

DOI: 10.1093/biomtc/ujag101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 30.05.2026. Verfasst von Dafne Zorzetto und 4 weiteren Autor:innen. Beteiligte Einrichtung: Data Science Institute, Brown University, Providence, RI 02906, United States. Hauptthemen laut MEDLINE: Smoke, Particulate Matter, Air Pollution, Models, Statistical. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NIGMS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The impact of wildfire smoke on air quality is a growing concern, contributing to air pollution through a complex mixture of chemical species with important implications for public health. Although previous studies have focused mainly on its association with total particulate matter (pm$_{2.5}$), the causal relationship between wildfire smoke and the chemical composition of pm$_{2.5}$ remains largely unexplored. To fill this gap, we propose a Bayesian causal regression factor model that estimates the multivariate causal effects of wildfire smoke on the concentration of 27 chemical species in pm$_{2.5}$ across the United States. Our approach introduces two key innovations: (i) a causal inference framework for multivariate potential outcomes, and (ii) a novel Bayesian factor model that employs a probit stick-breaking process as prior for treatment-specific factor scores. By focusing on factor scores, our method addresses the missing data challenge common to causal inference and enables a flexible, data-driven characterization of the latent factor structure, which is crucial to capturing the complex correlation between multivariate outcomes. Through Monte Carlo simulations, we show the accuracy of the model in estimating the causal effects in multivariate outcomes and characterizing the treatment-specific latent structure. Finally, we apply our method to US air quality data, estimating the causal effect of wildfire smoke on 27 chemical species in pm$_{2.5}$, providing a deeper understanding of their interdependencies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SmokeParticulate MatterAir PollutionModels, StatisticalWildfiresBayes TheoremMonte Carlo MethodComputer SimulationMultivariate AnalysisUnited StatesCausalityAir PollutantsHumansRegression Analysis

Stichwörter der Autor:innen

causal inferencefactor analysisfactor scores’ priorinfinite mixture distributionpotential outcome framework

Substanzen

SmokeParticulate MatterAir Pollutants

Autor:innen und Institutionen

  • Data Science Institute, Brown University, Providence, RI 02906, United States.
  • Department of Biostatistics, Harvard University, Cambridge, MA 02115, United States.
  • Department of Biostatistics, Brown University, Providence, RI 02903, United States.
  • Department of Data Science, Dana Farber Cancer Institute, Boston, MA 02215, United States.

ORCID-Profile: Giovanni Parmigiani

Förderung

  • NCI NIH HHS
  • NIGMS
  • NIH HHS
  • NIH

Zitieren

APA

Zorzetto, D., Landy, J., Zigler, C., Parmigiani, G., & De Vito, R. (2026). Multivariate causal effects: a Bayesian causal regression factor model. Biometrics, 82(2). https://doi.org/10.1093/biomtc/ujag101

Vancouver

Zorzetto D, Landy J, Zigler C, Parmigiani G, De Vito R. Multivariate causal effects: a Bayesian causal regression factor model. Biometrics. 2026;82(2). doi:10.1093/biomtc/ujag101

BibTeX
@article{Zorzetto2026,
  author = {Zorzetto, Dafne and Landy, Jenna and Zigler, Corwin and Parmigiani, Giovanni and De Vito, Roberta},
  title = {Multivariate causal effects: a Bayesian causal regression factor model},
  journal = {Biometrics},
  year = {2026},
  volume = {82},
  number = {2},
  doi = {10.1093/biomtc/ujag101}
}
Kostenlos starten →