An introduction to Causal Inference with Python – making accurate estimates of cause and effect from
summary
Demonstrates how causal models and DoWhy estimate interventions: on the Lalonde dataset an estimated treatment effect is $1,629 increase in wages; a placebo test drops the effect to $2. Uses DoWhy with pandas and optional EconML estimators, and ships a causal-diagram editor app; estimates and refutations run and produce interpretable counterfactuals.
AI-written summary · about
chapters (11)
- 0:00Introduction to causality
- 1:17Correlation vs causation
- 5:05Causality without RCTs
- 7:05Industry application
- 8:23Introduction to DoWhy
- 10:12Modeling the problem
- 15:44Identifying the estimand
- 18:18Estimating the effect
- 19:19Refuting the estimate
- 20:28Counterfactual outcomes
- 22:38Conclusion and resources
related talks
01h 12mIntroduction to Causal Inference
31mA Gentle Introduction To Causal Inference
41mOn the Path to Causal Inference
36mWhat-if- Causal reasoning meets Bayesian Inference
43mA Practical Guide to Causality in Python (For The Perplexed)
26mCausal inference with Causallib
06mCausal Machine Learning – What’s in it for Data Scientists?
31mPython and the Holy Grail of Causal Inference