An introduction to flexible methods for policy evaluation

TL;DR

This chapter introduces various flexible causal inference methods for policy evaluation, emphasizing machine learning techniques for high-dimensional data, effect heterogeneity, and optimal targeting of interventions.

Contribution

It provides a comprehensive overview of semi- and nonparametric methods, integrating machine learning for flexible treatment effect estimation and subgroup analysis.

Findings

Machine learning enhances covariate control in high-dimensional settings.

Methods enable estimation of heterogeneous treatment effects.

Flexible approaches improve causal inference accuracy.

Abstract

This chapter covers different approaches to policy evaluation for assessing the causal effect of a treatment or intervention on an outcome of interest. As an introduction to causal inference, the discussion starts with the experimental evaluation of a randomized treatment. It then reviews evaluation methods based on selection on observables (assuming a quasi-random treatment given observed covariates), instrumental variables (inducing a quasi-random shift in the treatment), difference-in-differences and changes-in-changes (exploiting changes in outcomes over time), as well as regression discontinuities and kinks (using changes in the treatment assignment at some threshold of a running variable). The chapter discusses methods particularly suited for data with many observations for a flexible (i.e. semi- or nonparametric) modeling of treatment effects, and/or many (i.e. high dimensional) observed covariates by applying machine learning to select and control for covariates in a data-driven way. This is not only useful for tackling confounding by controlling for instance for factors jointly affecting the treatment and the outcome, but also for learning effect heterogeneities across subgroups defined upon observable covariates and optimally targeting those groups for which the treatment is most effective.