Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders

10/11/2022
by   Olivier Jeunen, et al.
0

The ability to answer causal questions is crucial in many domains, as causal inference allows one to understand the impact of interventions. In many applications, only a single intervention is possible at a given time. However, in some important areas, multiple interventions are concurrently applied. Disentangling the effects of single interventions from jointly applied interventions is a challenging task – especially as simultaneously applied interventions can interact. This problem is made harder still by unobserved confounders, which influence both treatments and outcome. We address this challenge by aiming to learn the effect of a single-intervention from both observational data and sets of interventions. We prove that this is not generally possible, but provide identification proofs demonstrating that it can be achieved under non-linear continuous structural causal models with additive, multivariate Gaussian noise – even when unobserved confounders are present. Importantly, we show how to incorporate observed covariates and learn heterogeneous treatment effects. Based on the identifiability proofs, we provide an algorithm that learns the causal model parameters by pooling data from different regimes and jointly maximizing the combined likelihood. The effectiveness of our method is empirically demonstrated on both synthetic and real-world data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2020

Learning Joint Nonlinear Effects from Single-variable Interventions in the Presence of Hidden Confounders

We propose an approach to estimate the effect of multiple simultaneous i...
research
11/11/2020

Split-Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions

For many kinds of interventions, such as a new advertisement, marketing ...
research
01/17/2020

Causal models for dynamical systems

A probabilistic model describes a system in its observational state. In ...
research
04/09/2018

Merging joint distributions via causal model classes with low VC dimension

If X,Y,Z denote sets of random variables, two different data sources may...
research
11/30/2016

Joint Causal Inference from Observational and Experimental Datasets

We introduce Joint Causal Inference (JCI), a powerful formulation of cau...
research
06/16/2016

Learning Optimal Interventions

Our goal is to identify beneficial interventions from observational data...
research
11/03/2018

Instrumental Variable Methods using Dynamic Interventions

Recent work on dynamic interventions has greatly expanded the range of c...

Please sign up or login with your details

Forgot password? Click here to reset