Estimating Causal Effects with Double Machine Learning -- A Method Evaluation

arXiv:2403.14385v1 Announce Type: cross
Abstract: The estimation of causal effects with observational data continues to be a very active research area. In recent years, researchers have developed new frameworks which use machine learning to relax classical assumptions necessary for the estimation of causal effects. In this paper, we review one of the most prominent methods - "double/debiased machine learning" (DML) - and empirically evaluate it by comparing its performance on simulated data relative to more traditional statistical methods, before applying …

abstract arxiv assumptions causal cs.lg data econ.em effects evaluation frameworks machine machine learning paper research researchers review stat.me stat.ml type