Causal Inference and Machine Learning are two fields that emerged and advanced separately. However, the intersection of these fields started to be explored in statistics and more recently in the econometrics literature.
Causal machine learning methods (CML) provide some promising new tools for causal analysis. These techniques combine machine learning methods with causal inference questions, while establishing theoretical results on the consistency, asymptotic normality and validity of confidence intervals of the causal parameters of interest. This talk focuses on some of my recent research on CML where we illustrate the implementation of these methods in a variety of settings and highlight the relevance and value added of these tools relative to traditional methods used in applied economics. Large-scale evaluations of the finite sample performance of recently introduced CML methods, under a wide range of economically relevant data generating processes, complement our claims.
Join at: imt.lu/aula2