This chapter presents some of the recent developments in the machine learning literature for estimating heterogeneous treatment effects. The focus is on the variation in treatment effects for population subgroups based on their observed characteristics. Three algorithms, the X-learner, the R-learner, and causal forests are presented and illustrated using an empirical case study of a policy impact evaluation of a national health insurance programme in Indonesia.
You are not authenticated to view the full text of this chapter or article.
Get access to the full article by using one of the access options below.