Direct and Indirect Effects based on Changes-in-Changes

TL;DR

This paper introduces a new causal mediation analysis method using changes-in-changes assumptions, enabling the separation of direct and indirect effects in observational studies with unobserved heterogeneity.

Contribution

It develops a novel approach for identifying direct and indirect causal effects under specific assumptions about unobserved heterogeneity and monotonicity.

Findings

Successfully identifies average and quantile effects for subgroups.

Demonstrates the method's effectiveness through simulation studies.

Applies the approach to evaluate the Jobs II programme.

Abstract

We propose a novel approach for causal mediation analysis based on changes-in-changes assumptions restricting unobserved heterogeneity over time. This allows disentangling the causal effect of a binary treatment on a continuous outcome into an indirect effect operating through a binary intermediate variable (called mediator) and a direct effect running via other causal mechanisms. We identify average and quantile direct and indirect effects for various subgroups under the condition that the outcome is monotonic in the unobserved heterogeneity and that the distribution of the latter does not change over time conditional on the treatment and the mediator. We also provide a simulation study and an empirical application to the Jobs II programme.