Causal inference: Mediation analysis and causally heterogeneous effects

Introduction

What this guide covers

A rigorous mathematical, structural and algorithmic approach to the discovery of internal mechanisms of causal transmission and the individualization of treatment effects through Machine Learning and robust double learning.

Overview

Topics covered

• Introduction
• Mediation Analysis and Causally Heterogeneous Effects
• The Potential Results Framework
• 1.1 Mathematical Definition and Potential Results
• 1.2 Fundamental Assumptions of the Rubin Model
• 1.3 Typical Causal Estimates

Related concepts

Main connections

• Causal inference & potential outcomes
• Mean & expected value
• Non-parametric tests
• Residual analysis & diagnostics
• Regularization (Lasso / Ridge / Elastic Net)
• Diagnostic test evaluation & ROC

Compatible notation

Mathematical sample in LaTeX

The expression is rendered accessibly, with its LaTeX source preserved below.