Causal Inference in Panel Data with a Continuous Treatment

TL;DR

This paper introduces a new framework for causal inference in panel data with continuous, time-varying treatments, utilizing fixed effects, GMM estimators, and DAGs to test assumptions, demonstrated through an aid-growth case study.

Contribution

It develops a comprehensive methodology combining fixed effects, GMM, and DAGs for causal inference with continuous treatments in panel data, extending existing models.

Findings

Proposes a new framework for causal inference with continuous treatments.

Develops GMM estimators with established asymptotic properties.

Uses DAGs to validate sequential independence assumptions.

Abstract

This paper proposes a framework that incorporates the two-way fixed effects model as a special case to conduct causal inference with a continuous treatment. Treatments are allowed to change over time and potential outcomes are dependent on historical treatments. Regression models on potential outcomes, along with the sequentially conditional independence assumptions (SCIAs) are introduced to identify the treatment effects, which are measured by aggre causal responses. Least squares and generalized method of moments (GMM) estimators are developed for model parameters, which are then used to estimate the aggregate causal effects. We establish the asymptotic properties of these aggregate estimators. Additionally, we propose employing directed acyclic graphs (DAGs) to test the validity of the SCIAs. An application examining the aid-growth relationship illustrates the proposed methodology.