What is the value added by using causal machine learning methods in a welfare experiment evaluation?

Abstract

Recent studies have proposed causal machine learning (CML) methods to estimate conditional average treatment effects (CATEs). In this study, I investigate whether CML methods add value compared to conventional CATE estimators by re-evaluating Connecticut’s Jobs First welfare experiment. This experiment entails a mix of positive and negative work incentives. Previous studies show that it is hard to tackle the effect heterogeneity of Jobs First by means of CATEs. I report evidence that CML methods can provide support for the theoretical labor supply predictions. Furthermore, I document reasons why some conventional CATE estimators fail and discuss the limitations of CML methods.