Causal Inference is Not Just a Statistics Problem

This lecture will explore two major challenges in causal inference: (1) how to determine which variables to adjust for and (2) how to assess the impact of unmeasured variables. The first half of the talk will showcase the Causal Quartet, which consists of four datasets that have the same statistical properties, but different true causal effects due to different ways in which the data was generated. Then we will discuss sensitivity analyses for unmeasured confounders, showcasing the tipr R package.