Abstract
Abstract The estimation of causal effects is fundamental in situations where the underlying system will be subject to active interventions. Part of building a causal inference engine is defining how variables relate to each other, that is, defining the functional relationship between variables entailed by the graph conditional dependencies. In this article, we deviate from the common assumption of linear relationships in causal models by making use of neural autoregressive density estimators and use them to estimate causal effects within Pearl’s do-calculus framework. Using synthetic data, we show that the approach can retrieve causal effects from non-linear systems without explicitly modeling the interactions between the variables and include confidence bands using the non-parametric bootstrap. We also explore scenarios that deviate from the ideal causal effect estimation setting such as poor data support or unobserved confounders.
Highlights
One way of thinking about causal models is to consider them as inference engines [1]
4.5.2 Results Since the analytical solution of this causal graph is not readily available, the true causal effects were simulated from binned conditional distributions using the true generative process
We propose the neural autoregressive density estimators (NADEs) to estimate the causal conditionals
Summary
One way of thinking about causal models is to consider them as inference engines [1]. These engines take causal assumptions and queries as input and give an answer to those queries as output. The most important assumption required to compute interventional queries is that the topology of the causal graph is known. This topology can be elicited either by expert knowledge or by “causal discovery” algorithms. Regardless of where the causal topology comes from, we will assume throughout the article that the causal graph is known. Sensitivity with respect to this assumption will be investigated in the Experimental section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
