Causal Learning with Interactions

Identification and estimation of causal effects are challenging in an environment where the agents interact through markets or social networks, since the standard framework of causal inference rules out the spillovers of the actions and outcomes among the subjects in the study. How to learn causal effects and design policies in the presence of spillovers are important topics of research with interdisciplinary interest.

This two-day workshop presents recent methodological advances and empirical applications on the topic in economics, epidemiology, and statistics. A special focus will be on the applications of tools in machine learning and computational statistics to causal inference with interacting agents. It aims to foster the exchange of ideas among different scientific communities including economics, epidemiology, machine learning, and statistics.