Parameterizing and simulating from causal models
Journal of the Royal Statistical Society Series B: Statistical Methodology · 12.07.2024 · 86 (3) · 535-568
DOI: 10.1093/jrsssb/qkad058 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Royal Statistical Society Series B: Statistical Methodology, online erschienen am 24.05.2023. Verfasst von Robin J Evans und 1 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission within the Sixth RTD Framework Programme.
Abstract (Originalsprache)
Many statistical problems in causal inference involve a probability distribution other than the one from which data are actually observed; as an additional complication, the object of interest is often a marginal quantity of this other probability distribution. This creates many practical complications for statistical inference, even where the problem is non-parametrically identified. In particular, it is difficult to perform likelihood-based inference, or even to simulate from the model in a general way. We introduce the ‘frugal parameterization’, which places the causal effect of interest at its centre, and then builds the rest of the model around it. We do this in a way that provides a recipe for constructing a regular, non-redundant parameterization using causal quantities of interest. In the case of discrete variables, we can use odds ratios to complete the parameterization, while in the continuous case copulas are the natural choice; other possibilities are also discussed. Our methods allow us to construct and simulate from models with parametrically specified causal distributions, and fit them using likelihood-based methods, including fully Bayesian approaches. Our proposal includes parameterizations for the average causal effect and effect of treatment on the treated, as well as other causal quantities of interest.
Förderung
- European Commission within the Sixth RTD Framework Programme
Zitieren
APA
Evans, R. J., & Didelez, V. (2024). Parameterizing and simulating from causal models. Journal of the Royal Statistical Society Series B: Statistical Methodology, 86(3), 535-568. https://doi.org/10.1093/jrsssb/qkad058
Vancouver
Evans RJ, Didelez V. Parameterizing and simulating from causal models. Journal of the Royal Statistical Society Series B: Statistical Methodology. 2024;86(3):535-568. doi:10.1093/jrsssb/qkad058
BibTeX
@article{Evans2024,
author = {Evans, Robin J and Didelez, Vanessa},
title = {Parameterizing and simulating from causal models},
journal = {Journal of the Royal Statistical Society Series B: Statistical Methodology},
year = {2024},
volume = {86},
number = {3},
pages = {535--568},
doi = {10.1093/jrsssb/qkad058}
}
EUVIMED