A Comparison of Agent-Based Models and the Parametric G-Formula for Causal Inference

Decision-making requires choosing from treatments on the basis of correctly estimated outcome distributions under each treatment. In the absence of randomized trials, 2 possible approaches are the parametric g-formula and agent-based models (ABMs). The g-formula has been used exclusively to estimate...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	American journal of epidemiology Jg. 186; H. 2; S. 131
Hauptverfasser:	Murray, Eleanor J, Robins, James M, Seage, George R, Freedberg, Kenneth A, Hernán, Miguel A
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States 15.07.2017
Schlagworte:	Bias Causality Cause of Death - trends Computer Simulation - statistics & numerical data Data Interpretation, Statistical Decision Making Epidemiologic Research Design Humans Models, Statistical Monte Carlo Method Outcome Assessment, Health Care - methods Outcome Assessment, Health Care - statistics & numerical data Risk Assessment - methods Systems Analysis Monte Carlo methods agent-based models decision analysis mathematical models medical decision making causal inference individual-level models parametric g-formula
ISSN:	1476-6256, 1476-6256
Online-Zugang:	Weitere Angaben
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Decision-making requires choosing from treatments on the basis of correctly estimated outcome distributions under each treatment. In the absence of randomized trials, 2 possible approaches are the parametric g-formula and agent-based models (ABMs). The g-formula has been used exclusively to estimate effects in the population from which data were collected, whereas ABMs are commonly used to estimate effects in multiple populations, necessitating stronger assumptions. Here, we describe potential biases that arise when ABM assumptions do not hold. To do so, we estimated 12-month mortality risk in simulated populations differing in prevalence of an unknown common cause of mortality and a time-varying confounder. The ABM and g-formula correctly estimated mortality and causal effects when all inputs were from the target population. However, whenever any inputs came from another population, the ABM gave biased estimates of mortality-and often of causal effects even when the true effect was null. In the absence of unmeasured confounding and model misspecification, both methods produce valid causal inferences for a given population when all inputs are from that population. However, ABMs may result in bias when extrapolated to populations that differ on the distribution of unmeasured outcome determinants, even when the causal network linking variables is identical.
Bibliographie:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23
ISSN:	1476-6256 1476-6256
DOI:	10.1093/aje/kwx091