Notebooks on methods for causal inference (Work in progress)
There are two types of notebooks (above, click on the title to view it)
- Summary of theory (brief)
- Detailed empirical examples applying the theory
Below are links to some unpolished YouTube videos with very brief summaries of the topics.
Brief intro/review lectures
- Intro to causal inference
- Potential outcome model
- Propensity score matching
- Instrumental variables
- Difference-in-Difference (Applied)
- Three strategies to estimate causal effects
See also
- Ben Lambert: A full course in econometrics
Useful links
-
Microsoft: DoWhy
-
Microsoft: EconML
-
Uber: CausalML
-
Laurence Wong: Causal inference in Python
-
Dafiti: Causal impact
-
Yusuke Minami: CausalLift
-
Iain Barr: CausalGraphicalModels, Causal Graphical Models in Python
-
akhelle: Causality
-
Daggity: Daggity, Draw causal graphs
-
Facebook: Prophet
-
Adam Kelleher and Amit Sharma: Introducing the do-sampler for causal inference
-
Vivian Zheng: Causal inference 101: difference-in-differences
-
Yusuke Minami: CausalLift: Python package for Uplift Modeling in real-world business; applicable for both A/B testing and observational data My understanding of Causality comes mainly from the reading of the follow work:
-
If correlation doesn’t imply causation, then what does?](http://www.michaelnielsen.org/ddi/if-correlation-doesnt-imply-causation-then-what-does/), Michael Nielsen
-
Jonas Peters' lecture notes, Jonas Peters
-
Lecture notes on causality https://github.com/microsoft/EconML