Marginal Causal Flows for Validation and Inference

TL;DR

This paper introduces Frugal Flows, a novel likelihood-based normalising flow model that learns data-generating processes and directly infers marginal causal effects from observational data, aiding validation of causal inference methods.

Contribution

Frugal Flows is the first generative model to simultaneously learn flexible data representations and exactly parameterise causal quantities like treatment effects.

Findings

Successfully generates synthetic data resembling real datasets.

Precisely infers average treatment effects from observational data.

Demonstrates effectiveness on simulated and real-world datasets.

Abstract

Investigating the marginal causal effect of an intervention on an outcome from complex data remains challenging due to the inflexibility of employed models and the lack of complexity in causal benchmark datasets, which often fail to reproduce intricate real-world data patterns. In this paper we introduce Frugal Flows, a novel likelihood-based machine learning model that uses normalising flows to flexibly learn the data-generating process, while also directly inferring the marginal causal quantities from observational data. We propose that these models are exceptionally well suited for generating synthetic data to validate causal methods. They can create synthetic datasets that closely resemble the empirical dataset, while automatically and exactly satisfying a user-defined average treatment effect. To our knowledge, Frugal Flows are the first generative model to both learn flexible data representations and also exactly parameterise quantities such as the average treatment effect and the degree of unobserved confounding. We demonstrate the above with experiments on both simulated and real-world datasets.