Teaching

UCLA

NEW  Causal Inference for Health Data (Winter 2026)

In Winter 2026, I will teach a new course on Causal Inference for Health Data, focusing on modern causal inference methods and their applications to biomedical and health data. The course will emphasize identification, estimation, fairness in medical prediction, and reproducible workflows in R and Python.

Department of Statistics & Data Science, UCLA.

Columbia University

Fair Machine Learning (Spring 2023)

A 4-week (8-lecture) module within Causal Inference II (E. Bareinboim), covering causal fairness analysis, bias detection, fair prediction, and fair decision-making. Materials include slides, lecture videos, and reproducible software vignettes.

Week 1 — Lectures 1–2

(L1) Theory of decomposing variations within the total-variation fairness measure TVx₀, x₁(y). Introducing contrasts, structural basis expansion, and the Explainability Plane.
(L2) Measures in the TV family and their structure; organizing existing causal fairness measures into the Fairness Map.

L1 Slides L2 Slides L1 Video L2 Video
Week 2 — Lectures 3–4

(L3) Identification and estimation of causal fairness measures via doubly-robust and double-debiased ML methods.
(L4) Relationship to existing fairness notions: counterfactual fairness, predictive parity, and calibration.

Slides 3–4 Video 3–4
Week 3 — Lectures 5–6

(L5) Bias detection using real and synthetic datasets (US Census 2018, COMPAS).
(L6) Fair prediction: proving the Fair Prediction Theorem showing limits of statistical fairness.

L5 Slides L6 Slides L5 Video L6 Video Census T1 COMPAS T1 COMPAS T3
Week 4 — Lectures 7–8

(L7) Extending causal fairness to arbitrary causal diagrams; variable- and path-specific indirect effects.
(L8) Decompositions of spurious effects and partial-abduction procedures in Markovian and semi-Markovian models.

Slides 7–8 Video 7–8

ETH Zürich

Teaching Assistant (2019 – 2022)

  • Applied Multivariate Statistics (Spring 2022, 2019)
  • Applied Statistical Regression (Autumn 2020)
  • Computational Statistics (Spring 2020)
  • Statistical Modelling (Autumn 2019)