EUVIMEDEUVIMED entdecken
Crossref

Causal inference with misspecified exposure mappings: separating definitions and assumptions

F Sävje

Biometrika · 12.02.2024 · 111 (1) · 1-15

DOI: 10.1093/biomet/asad019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrika, online erschienen am 16.03.2023. Verfasst von F Sävje. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 18 Literaturangaben. Gefördert von: Department of Statistics & Data Science at Yale University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exposure mappings facilitate investigations of complex causal effects when units interact in experiments. Current methods require experimenters to use the same exposure mappings to define the effect of interest and to impose assumptions on the interference structure. However, the two roles rarely coincide in practice, and experimenters are forced to make the often questionable assumption that their exposures are correctly specified. This paper argues that the two roles exposure mappings currently serve can, and typically should, be separated, so that exposures are used to define effects without necessarily assuming that they are capturing the complete causal structure in the experiment. The paper shows that this approach is practically viable by providing conditions under which exposure effects can be precisely estimated when the exposures are misspecified. Some important questions remain open.

Förderung

  • Department of Statistics & Data Science at Yale University

Zitieren

APA

Sävje, F. (2024). Causal inference with misspecified exposure mappings: separating definitions and assumptions. Biometrika, 111(1), 1-15. https://doi.org/10.1093/biomet/asad019

Vancouver

Sävje F. Causal inference with misspecified exposure mappings: separating definitions and assumptions. Biometrika. 2024;111(1):1-15. doi:10.1093/biomet/asad019

BibTeX
@article{Svje2024,
  author = {Sävje, F},
  title = {Causal inference with misspecified exposure mappings: separating definitions and assumptions},
  journal = {Biometrika},
  year = {2024},
  volume = {111},
  number = {1},
  pages = {1--15},
  doi = {10.1093/biomet/asad019}
}
Kostenlos starten →