Causal inference and policy evaluation without a control group

TL;DR

This paper introduces the Machine Learning Control Method, a novel approach for causal inference in panel data without a control group, utilizing machine learning algorithms for estimation and formal identification.

Contribution

It provides a new methodology for causal analysis without untreated units, formalizes identification, and demonstrates practical applications including simulations, replication, and empirical case studies.

Findings

Effective estimation of causal effects without control groups

Successful application to COVID-19 impact on educational inequality

Implementation available in R package MachineControl

Abstract

Without a control group, the most widespread methodologies for estimating causal effects cannot be applied. To fill this gap, we propose the Machine Learning Control Method, a new approach for causal panel analysis that estimates causal parameters without relying on untreated units. We formalize identification within the potential outcomes framework and then provide estimation based on machine learning algorithms. To illustrate the practical relevance of our method, we present simulation evidence, a replication study, and an empirical application on the impact of the COVID-19 crisis on educational inequality. We implement the proposed approach in the companion R package MachineControl