AI-Era Skills
Causal Inference
Potential outcomes, selection bias, DAGs, and the full quasi-experimental toolkit — matching, diff-in-diff, regression discontinuity, instrumental variables, synthetic control — in plain English, grounded in the canonical texts. Ends with the AI-era skillset: ML meets causal inference, and auditing causal claims with AI as your skeptic.
Track curriculum
The Core Problem
14% of track · 5 sections
The Causal Mechanism
10% of track · 3 sections
DAGs and What to Control
12% of track · 4 sections
Regression as a Causal Tool
10% of track · 3 sections
Experiments and Their Limits
9% of track · 3 sections
When You Can’t Randomize
14% of track · 6 sections
Robustness and Sensitivity
10% of track · 2 sections
Doing It With AI
11% of track · 4 sections
Start studying
About the Causal Inference track
From "X drives Y" to knowing whether it actually does. Potential outcomes, selection bias, DAGs, and the full quasi-experimental toolkit — matching, diff-in-diff, regression discontinuity, instrumental variables, synthetic control — in plain English, grounded in the canonical texts. Ends with the AI-era skillset: ML meets causal inference, and auditing causal claims with AI as your skeptic.
AskBoudin covers all 8 topic areas with an AI tutor and unlimited AI-generated practice exercises. Start free — the first chapter is on us. Study at your own pace and check your mastery with full-length mock assessments.
Topics & weighting
- The Core Problem14%
- The Causal Mechanism10%
- DAGs and What to Control12%
- Regression as a Causal Tool10%
- Experiments and Their Limits9%
- When You Can’t Randomize14%
- Robustness and Sensitivity10%
- Doing It With AI11%
Causal Inference — Frequently asked questions
What does the Causal Inference track cover?
The track covers 8 topic areas across 30 lessons: The Core Problem, The Causal Mechanism, DAGs and What to Control, Regression as a Causal Tool, Experiments and Their Limits, When You Can’t Randomize, Robustness and Sensitivity, Doing It With AI. Every topic ends in a "Doing It With AI" arc — directing AI to do the work and verifying the result.
How much practice does the Causal Inference track include?
Around 300 practice exercises (roughly 4 hours of focused practice), plus AI-generated fresh questions on demand, so you never run out of material.
Who is the Causal Inference track for?
Product managers, marketing analysts, and product analysts who consume this kind of analysis — and increasingly generate it with AI — but don't do it professionally. No prior coding or statistics background is assumed.
Is the Causal Inference track free to start?
Yes. The first chapter is always free — study with the AI tutor and take practice questions before paying anything.
How does the AI tutor help with Causal Inference?
Ask the tutor any concept in plain English and get an instant explanation, then generate a fresh practice set on the same topic. It is available 24/7, so you are never stuck waiting for an instructor.
Aligned to the Cunningham’s Mixtape, Facure’s Brave and True, Shalizi’s ADAfaEPoV, and Chernozhukov et al.’s CausalML · last reviewed 2026-07-08.
Free Causal Inference cheat sheets
Quick-reference summaries for each Causal Inference topic — key facts, formulas, and rules at a glance. Free to read.