Translator Disclaimer
May 2019 Smooth, identifiable supermodels of discrete DAG models with latent variables
Robin J. Evans, Thomas S. Richardson
Bernoulli 25(2): 848-876 (May 2019). DOI: 10.3150/17-BEJ1005

Abstract

We provide a parameterization of the discrete nested Markov model, which is a supermodel that approximates DAG models (Bayesian network models) with latent variables. Such models are widely used in causal inference and machine learning. We explicitly evaluate their dimension, show that they are curved exponential families of distributions, and fit them to data. The parameterization avoids the irregularities and unidentifiability of latent variable models. The parameters used are all fully identifiable and causally-interpretable quantities.

Citation

Download Citation

Robin J. Evans. Thomas S. Richardson. "Smooth, identifiable supermodels of discrete DAG models with latent variables." Bernoulli 25 (2) 848 - 876, May 2019. https://doi.org/10.3150/17-BEJ1005

Information

Received: 1 December 2015; Revised: 1 January 2017; Published: May 2019
First available in Project Euclid: 6 March 2019

zbMATH: 07049393
MathSciNet: MR3920359
Digital Object Identifier: 10.3150/17-BEJ1005

Rights: Copyright © 2019 Bernoulli Society for Mathematical Statistics and Probability

JOURNAL ARTICLE
29 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

SHARE
Vol.25 • No. 2 • May 2019
Back to Top