|
Abstract:
|
High-stakes decision-makers have used causal inference methods to inform their decision making. For instance, public health experts and epidemiologists perform controlled trials to understand the efficacy of a vaccine. Our discussion focuses on few causal inference frameworks such as controlled trials and alternatives for cases when controlled trials are not feasible. It guides through fundamental causal inference concepts such as potential outcomes and causal graphs. We outline classic causal inference tools such as regressions and matchings. The conversation involves working through real-world case-studies in development-economics, critical-healthcare, and academic publications. During the round-table, we aim at providing an intuitive introduction to causal inference literature and motivate the idea via real-world examples.
|
