Constructing a More Closely Matched Control Group in a Difference-in-Differences Analysis: Its Effect on History Interacting with Group Bias

TL;DR

This paper investigates how creating a more closely matched control group in difference-in-differences analysis can reduce bias from historical events, demonstrated through simulation and a case study on mountaintop removal mining's impact on mortality.

Contribution

It introduces a method for constructing better-matched control groups in difference-in-differences studies to mitigate bias from historical interactions, supported by simulations and empirical analysis.

Findings

More closely matched control groups can reduce bias from historical events.

Simulation studies show improved accuracy with matched controls.

Empirical analysis of MRM effects on mortality shows varied potential impacts.

Abstract

Difference-in-differences analysis with a control group that differs considerably from a treated group is vulnerable to bias from historical events that have different effects on the groups. Constructing a more closely matched control group by matching a subset of the overall control group to the treated group may result in less bias. We study this phenomenon in simulation studies. We study the effect of mountaintop removal mining (MRM) on mortality using a difference-in-differences analysis that makes use of the increase in MRM following the 1990 Clean Air Act Amendments. For a difference-in-differences analysis of the effect of MRM on mortality, we constructed a more closely matched control group and found a 95\% confidence interval that contains substantial adverse effects along with no effect and small beneficial effects.