A Friendly Introduction To Causality

on YouTube ↗24m

" summary

Surveys Pearl’s Structural Equation Models and shows interventions are the gold standard: randomize a variable (example: 50% treatment vs placebo) and check post-intervention independences to identify directionality; with only two observed variables the joint distribution is ambiguous. Covers the PC algorithm for conditional independencies, bounds on intervention counts (log χ chromatic bound, adaptivity doesn’t help worst‑case, randomized can reach ~log log n for cliques), and presents entropic causality as an information‑theoretic method for categorical data; recommends TETRAD.

AI-written summary · about

" chapters (9)

1. 0:00Introduction
2. 2:57Directed Graphs
3. 8:05What is Causality
4. 13:15Interventions
5. 15:45Dollars Buyers Club
6. 16:59More than two variables
7. 18:45Intervention
8. 19:38Key Question
9. 21:01Graph Tips

" related talks

• 31mLearning And Testing Causal Models: A Property Testing ViewpointArnab Bhattacharyya · Learning from Interventions 2022
• 31mA Gentle Introduction To Causal InferenceEyal Kazin · PyData Global 2022
• 01h 08mAn Introduction to Potential Outcomes, DAGs and Single-World Intervention GraphsThomas S Richardson · Causality Boot Camp
• 49mCausal Inference in Complex Systems: Network Interference, Strategic Agents, and BeyondPanos Toulis · Quantifying Uncertainty: Stochastic, Adversarial, and Beyond
• 41mOn the Path to Causal InferenceMark Farragher · PyData London 2019
• 01h 01mThe Mathematics of Causal Inference, with Reflections on Machine Learning and the Logic of ScienceJudea Pearl · Symposium on Visions of the Theory of Computing 2013
• 01h 02mUnmeasured Confounding and More Recent Developments/Challenges in Causal DiscoveryDaniel Malinsky · Causality Boot Camp
• 30mCausal Estimands And InterventionsVanessa Didelez · Learning from Interventions 2022