EUVIMEDEUVIMED entdecken
Open Access

Bayesian nonparametric trees for principal causal effects

Chanmin Kim iD, Corwin Zigler

Biometrics · 07.01.2025 · 81 (1)

DOI: 10.1093/biomtc/ujaf024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 17.03.2025. Verfasst von Chanmin Kim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, SungKyunKwan University, Seoul 03062, Korea. Hauptthemen laut MEDLINE: Causality, Models, Statistical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIEHS NIH HHS, National Research Foundation of Korea, US National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Principal stratification analysis evaluates how causal effects of a treatment on a primary outcome vary across strata of units defined by their treatment effect on some intermediate quantity. This endeavor is substantially challenged when the intermediate variable is continuously scaled and there are infinitely many basic principal strata. We employ a Bayesian nonparametric approach to flexibly evaluate treatment effects across flexibly modeled principal strata. The approach uses Bayesian Causal Forests (BCF) to simultaneously specify 2 Bayesian Additive Regression Tree models; one for the principal stratum membership and one for the outcome, conditional on principal strata. We show how the capability of BCF for capturing treatment effect heterogeneity is particularly relevant for assessing how treatment effects vary across the surface defined by continuously scaled principal strata, in addition to other benefits relating to targeted selection and regularization-induced confounding. The capabilities of the proposed approach are illustrated with a simulation study, and the methodology is deployed to investigate how causal effects of power plant emissions control technologies on ambient particulate pollution vary as a function of the technologies’ impact on sulfur dioxide emissions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CausalityModels, StatisticalBayes TheoremComputer SimulationHumansStatistics, NonparametricBiometryData Interpretation, StatisticalAir PollutionSulfur DioxideParticulate MatterRegression Analysis

Stichwörter der Autor:innen

BCFBayesian nonparametricsair pollutioncausal inferenceprincipal stratification

Substanzen

Sulfur DioxideParticulate Matter

Autor:innen und Institutionen

  • Department of Statistics, SungKyunKwan University, Seoul 03062, Korea.
  • Department of Biostatistics, Brown University School of Public Health, Providence, RI 02903, United States.

ORCID-Profile: Chanmin Kim

Förderung

  • NIEHS NIH HHS
  • National Research Foundation of Korea
  • US National Institutes of Health

Zitieren

APA

Kim, C., & Zigler, C. (2025). Bayesian nonparametric trees for principal causal effects. Biometrics, 81(1). https://doi.org/10.1093/biomtc/ujaf024

Vancouver

Kim C, Zigler C. Bayesian nonparametric trees for principal causal effects. Biometrics. 2025;81(1). doi:10.1093/biomtc/ujaf024

BibTeX
@article{Kim2025,
  author = {Kim, Chanmin and Zigler, Corwin},
  title = {Bayesian nonparametric trees for principal causal effects},
  journal = {Biometrics},
  year = {2025},
  volume = {81},
  number = {1},
  doi = {10.1093/biomtc/ujaf024}
}
Kostenlos starten →