The Value Added of Machine Learning to Causal Inference: Evidence from\n Revisited Studies

A new and rapidly growing econometric literature is making advances in the\nproblem of using machine learning methods for causal inference questions. Yet,\nthe empirical economics literature has not started to fully exploit the\nstrengths of these modern methods. We revisit influential empirical studies\nwith causal machine learning methods and identify several advantages of using\nthese techniques. We show that these advantages and their implications are\nempirically relevant and that the use of these methods can improve the\ncredibility of causal analysis.\n