Estimating the average causal effect of intervention in continuous variables using machine learning

TL;DR

This paper introduces a novel method for estimating the average causal effect of interventions in continuous variables, applicable across various data generating models and independent of specific machine learning algorithms.

Contribution

It provides a new approach for causal effect estimation in continuous variables that is model-agnostic and maintains data identifiability.

Findings

Method is applicable to any data generating model.

Independent of specific machine learning algorithms.

Preserves data identifiability.

Abstract

The most widely discussed methods for estimating the Average Causal Effect/Average Treatment Effect are those for intervention in discrete binary variables whose value represents intervention/non-intervention groups. On the other hand, methods for intervening in continuous variables independent of data generating models have not been developed. In this study, we give a method for estimating the average causal effect for intervention in continuous variables that can be applied to data of any generating models as long as the causal effect is identifiable. The proposing method is independent of machine learning algorithms and preserves the identifiability of data.