Notes on Causation, Comparison, and Regression

TL;DR

This paper discusses how linear regression can approximate randomized experiments in causal inference, emphasizing diagnostics, alternative methods, and the importance of covariate balance in non-experimental studies.

Contribution

It provides diagnostics and discusses alternative approaches to improve causal inference when randomized experiments are infeasible.

Findings

Diagnostics can assess how well regression mimics randomized experiments

Alternative methods like weighting and matching are valuable in causal analysis

Regression approaches have limitations that can be addressed with additional techniques

Abstract

Comparison and contrast are the basic means to unveil causation and learn which treatments work. To build good comparison groups, randomized experimentation is key, yet often infeasible. In such non-experimental settings, we illustrate and discuss diagnostics to assess how well the common linear regression approach to causal inference approximates desirable features of randomized experiments, such as covariate balance, study representativeness, interpolated estimation, and unweighted analyses. We also discuss alternative regression modeling, weighting, and matching approaches and argue they should be given strong consideration in empirical work.