Model-based regression adjustment with model-free covariates for network interference

zu Verbundenen Objekten

Abstract: When estimating a global average treatment effect (GATE) under network interference, units can have widely different relationships to the treatment depending on a combination of the structure of their network neighborhood, the structure of the interference mechanism, and how the treatment was distributed in their neighborhood. In this work, we introduce a sequential procedure to generate and select graph- and treatment-based covariates for GATE estimation under regression adjustment. We show that it is possible to simultaneously achieve low bias and considerably reduce variance with such a procedure. To tackle inferential complications caused by our feature generation and selection process, we introduce a way to construct confidence intervals based on a block bootstrap. We illustrate that our selection procedure and subsequent estimator can achieve good performance in terms of root-mean-square error in several semi-synthetic experiments with Bernoulli designs, comparing favorably to an oracle estimator that takes advantage of regression adjustments for the known underlying interference structure. We apply our method to a real-world experimental dataset with strong evidence of interference and demonstrate that it can estimate the GATE reasonably well without knowing the interference process a priori.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
Model-based regression adjustment with model-free covariates for network interference ; volume:11 ; number:1 ; year:2023 ; extent:29
Journal of causal inference ; 11, Heft 1 (2023) (gesamt 29)

Urheber
Han, Kevin
Ugander, Johan

DOI
10.1515/jci-2023-0005
URN
urn:nbn:de:101:1-2023110813252920682268
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
14.08.2025, 10:53 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Original beim Datenpartner anzeigen

Beteiligte

  • Han, Kevin
  • Ugander, Johan

Ähnliche Objekte (12)

Model-Based and Model-Free Decisions in Alcohol Dependence

Model-Based and Model-Free Decisions in Alcohol Dependence

Retrospective model-based inference guides model-free credit assignment

Retrospective model-based inference guides model-free credit assignment

Model-Based and Model-Free Decisions in Alcohol Dependence

Model-Based and Model-Free Decisions in Alcohol Dependence

Reliance on model-based and model-free control in obesity

Reliance on model-based and model-free control in obesity

Dopamine enhances model-free credit assignment through boosting of retrospective model-based inference

Dopamine enhances model-free credit assignment through boosting of retrospective model-based inference

Model-free impulse responses

Arbeitspapier

Model-free impulse responses

Model-Free Impulse Responses

Arbeitspapier

Model-Free Impulse Responses

Model-Free or Not?

Model-Free or Not?

Data-driven computational mechanics: comparison of model-free and model-based methods in constitutive modeling

Data-driven computational mechanics: comparison of model-free and model-based methods in constitutive modeling

Model-based entropy estimation for data with covariates and dependence structures

Model-based entropy estimation for data with covariates and dependence structures

Proactive interference in aging: A model-based study

Proactive interference in aging: A model-based study

Computational characterization of human sequential decision making under uncertainty : Model-free, model-based, exploitative and explorative strategies

Computational characterization of human sequential decision making under uncertainty : Model-free, model-based, exploitative and explorative strategies

Verbundene Objekte