source-code-phd-dissertation

Collection of source code implementing methods and for reproducing experiments included in each chapter of the Ph.D. dissertation "Safe causal inference: Statistical algorithms for falsification and assumption-lean learning of treatment effects". The source code also includes methods for generating simulated datasets used in the evaluation of the methods. The goal of the of the research was to develop methods to improve treatment effect estimation, this includes: methods to detect unmeasured confounding from observational data, methods to integrate historical data into randomized experiments to improve data efficiency, methods to evaluate treatment policies under treatment interference.