Toggle navigation sidebar
Toggle in-page Table of Contents
Causal Inference for the Brave and True
Causal Inference for The Brave and True
Part I - The Yang
01 - Introduction To Causality
02 - Randomised Experiments
03 - Stats Review: The Most Dangerous Equation
04 - Graphical Causal Models
05 - The Unreasonable Effectiveness of Linear Regression
06 - Grouped and Dummy Regression
07 - Beyond Confounders
08 - Instrumental Variables
09 - Non Compliance and LATE
10 - Matching
11 - Propensity Score
12 - Doubly Robust Estimation
13 - Difference-in-Differences
14 - Panel Data and Fixed Effects
15 - Synthetic Control
16 - Regression Discontinuity Design
Part II - The Yin
17 - Predictive Models 101
18 - Heterogeneous Treatment Effects and Personalization
19 - Evaluating Causal Models
20 - Plug-and-Play Estimators
21 - Meta Learners
22 - Debiased/Orthogonal Machine Learning
23 - Challenges with Effect Heterogeneity and Nonlinearity
24 - The Difference-in-Differences Saga
25 - Synthetic Difference-in-Differences
Appendix
Debiasing with Orthogonalization
Debiasing with Propensity Score
When Prediction Fails
Why Prediction Metrics are Dangerous For Causal Models
Conformal Inference for Synthetic Controls
Contribute
Patreon
Index