Data integration methods for micro-randomized trials
Biometrics · 2025
DOI: 10.1093/biomtc/ujaf002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biometrics, 2025. Verfasst von E Huch und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, University of Michigan, Ann Arbor, MI 48109, United States. Hauptthemen laut MEDLINE: Randomized Controlled Trials as Topic, Models, Statistical, Biometry. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH/NIDA, NIH/NIGMS, NCI NIH HHS.
Abstract (Originalsprache)
Existing statistical methods for the analysis of micro-randomized trials (MRTs) are designed to estimate causal excursion effects using data from a single MRT. In practice, however, researchers can often find previous MRTs that employ similar interventions. In this paper, we develop data integration methods that capitalize on this additional information, leading to statistical efficiency gains. To further increase efficiency, we demonstrate how to combine these approaches according to a generalization of multivariate precision weighting that allows for correlation between estimates, and we show that the resulting meta-estimator possesses an asymptotic optimality property. We illustrate our methods in simulation and in a case study involving 2 MRTs in the area of smoking cessation, finding that the proposed methods can reduce standard errors by over 30% without sacrificing asymptotic unbiasedness or calibrated statistical inference.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Statistics, University of Michigan, Ann Arbor, MI 48109, United States.
- Institute for Social Research, University of Michigan, Ann Arbor, MI 48104, United States.
- Department of Population Health Sciences and Huntsman Cancer Institute, University of Utah, Salt Lake City, UT 84108, United States.
- Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, United States.
ORCID-Profile: E Huch, I Nahum-Shani, L Potter
Förderung
- NIH/NIDA
- NIH/NIGMS
- NCI NIH HHS
- Huntsman Cancer Foundation
- NIDA NIH HHS
- NIGMS NIH HHS
- NIH/NCI
Zitieren
APA
Huch, E., Nahum-Shani, I., Potter, L., Lam, C., Wetter, D. W., & Dempsey, W. (2025). Data integration methods for micro-randomized trials. Biometrics. https://doi.org/10.1093/biomtc/ujaf002
Vancouver
Huch E, Nahum-Shani I, Potter L, Lam C, Wetter DW, Dempsey W. Data integration methods for micro-randomized trials. Biometrics. 2025. doi:10.1093/biomtc/ujaf002
BibTeX
@article{Huch2025,
author = {Huch, E and Nahum-Shani, I and Potter, L and Lam, C and Wetter, D W and Dempsey, W},
title = {Data integration methods for micro-randomized trials},
journal = {Biometrics},
year = {2025},
doi = {10.1093/biomtc/ujaf002}
}
EUVIMED