EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Causal message-passing for experiments with unknown and general network interference

Sadegh Shirani iD, Mohsen Bayati iD

Proceedings of the National Academy of Sciences · 2024-10 · 121 (40)

DOI: 10.1073/pnas.2322232121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 27.09.2024. Verfasst von Sadegh Shirani und 1 weiteren Autor:innen. Beteiligte Einrichtung: Operations, Information & Technology, Graduate School of Business, Stanford University, Stanford, CA 94305. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stanford University (SU).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Randomized experiments are a powerful methodology for data-driven evaluation of decisions or interventions. Yet, their validity may be undermined by network interference. This occurs when the treatment of one unit impacts not only its outcome but also that of connected units, biasing traditional treatment effect estimations. Our study introduces a framework to accommodate complex and unknown network interference, moving beyond specialized models in the existing literature. Our framework, termed causal message-passing, is grounded in high-dimensional approximate message-passing methodology. It is tailored for multiperiod experiments and is particularly effective in settings with many units and prevalent network interference. The framework models causal effects as a dynamic process where a treated unit’s impact propagates through the network via neighboring units until equilibrium is reached. This approach allows us to approximate the dynamics of potential outcomes over time, enabling the extraction of valuable information before treatment effects reach equilibrium. Utilizing causal message-passing, we introduce a practical algorithm to estimate the total treatment effect, defined as the impact observed when all units are treated compared to the scenario where no unit receives treatment. We demonstrate the effectiveness of this approach across five numerical scenarios, each characterized by a distinct interference structure.

Schlagwörter

Stichwörter der Autor:innen

approximate message-passingexperiment designnetwork interferencetotal treatment effect

Autor:innen und Institutionen

  • Operations, Information & Technology, Graduate School of Business, Stanford University, Stanford, CA 94305.

ORCID-Profile: Sadegh Shirani, Mohsen Bayati

Förderung

  • Stanford University (SU)

Zitieren

APA

Shirani, S., & Bayati, M. (2024). Causal message-passing for experiments with unknown and general network interference. Proceedings of the National Academy of Sciences, 121(40). https://doi.org/10.1073/pnas.2322232121

Vancouver

Shirani S, Bayati M. Causal message-passing for experiments with unknown and general network interference. Proceedings of the National Academy of Sciences. 2024;121(40). doi:10.1073/pnas.2322232121

BibTeX
@article{Shirani2024,
  author = {Shirani, Sadegh and Bayati, Mohsen},
  title = {Causal message-passing for experiments with unknown and general network interference},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2024},
  volume = {121},
  number = {40},
  doi = {10.1073/pnas.2322232121}
}
Kostenlos starten →