Applied Causal Inference
Powered by ML and AI

Victor Chernozhukov, Christian Hansen, Nathan Kallus, Martin Spindler, Vasilis Syrgkanis

An introduction to the emerging fusion of machine learning and causal inference.

The book introduces ideas from classical structural equation models (SEMs) and their modern AI equivalent, directed acyclical graphs (DAGs) and structural causal models (SCMs), and presents Debiased Machine Learning methods to do inference in such models using modern predictive tools.

Causal ML Book™

Applied Causal Inference Powered by ML and AI
V. Chernozhukov, C. Hansen, N. Kallus, M. Spindler, V. Syrgkanis

Preamble

PPreface

Sneak Peek

Powering Causal Inference with ML and AI

Core Material

Prediction Inference

Predictive Inference with Linear Regression in Moderately High Dimensions

Causality Inference

Causal Inference via Randomized Experiments

Prediction

Predictive Inference via Modern High-Dimensional Linear Regression

Causality Inference

Statistical Inference on Predictive Effects in High-Dimensional Linear Regression Models

Causality

Causal Inference via Conditional Ignorability

Causality

Causal Inference via Linear Structural Equations

Causality

Causal Inference via Directed Acyclical Graphs and Nonlinear Structural Equation Models

Causality

Valid Adjustment Sets from DAGs

Prediction

Predictive Inference via Modern Nonlinear Regression

Causality Inference

Statistical Inference on Predictive and Causal Effects in Modern Nonlinear Regression Models

Causality Inference

Feature Engineering for Causal and Predictive Inference

Advanced Topics

Advanced

Unobserved Confounders, Instrumental Variables, and Proxy Controls

Advanced

DML for IV and Proxy Controls Models and Robust DML Inference under Weak Identification

Advanced

Statistical Inference on Heterogeneous Treatment Effects

Advanced

Estimation and Validation of Heterogeneous Treatment Effects

Advanced

Difference-in-Differences

Advanced

Regression Discontinuity Designs

Feedback

Feedback, comments, or suggestions?

Endorsements

Citation

This is how you can cite us

Chernozhukov, V. & Hansen, C. & Kallus, N. & Spindler, M. & Syrgkanis, V. (2024): Applied Causal Inference Powered by ML and AI. CausalML-book.org; arXiv:2403.02467.

Labs

Take a look at our Labs

DOUBLEML, ECONML, STATA ML, ddml

Packages

DoubleML

Double / Debiased Machine Learning

The Python and R packages DoubleML provide an implementation of the double / debiased machine learning framework of Chernozhukov et al. (2018). The Python package is built on top of scikit-learn (Pedregosa et al., 2011) and the R package on top of mlr3 and the mlr3 ecosystem (Lang et al., 2019).

DocsGitHub

EconML

ML Estimation of Heterogeneous Treatment Effects

The Python package EconML provides an implementation of a variety of methods for estimating heterogeneous treatment effects with machine learning.

DocsGitHub

Stata ML & ddml

Stata Machine Learning & Double/Debiased ML for R

The Stata ML Page features packages tailored for machine learning in Stata, focusing on prediction, model selection, and causal inference, enhancing Stata's functionality with cutting-edge statistical methods.

ddml is an implementation for R of double/debiased machine learning estimators as proposed by Chernozhukov et al. (2018).

Stata ML Page(R) Double/Debiased ML