Lecture Schedule

Basics of Causal Inference

Jan 6

Intro Lecture Course Overview: [PPTX]; [PDF]

Reading Materials

Textbook

Jan 8

Lecture 1 Potential Outcomes & Causal Estimands: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Sections 2.1
Hernan, Robins (2025). Causal Inference: What If, Chapter 1
Rubin (1974), Estimating causal effects of treatments in randomized and nonrandomized studies (classic)

Coding Materials

NSW (Lalonde) Analysis Demo Code

Jan 12

Homework HW1 Released

Jan 13

Lecture 2 Observational Studies: Conditional Ignorability I: [Slides]; [Notes]; [NotebookLM]

Identification by Conditioning

Reading Materials

Textbook: Chapter 5

Coding Materials

NSW (Lalonde) Analysis: Identification by Conditioning

Jan 15

Lecture 3 Observational Studies: Conditional Ignorability II: [Slides]; [Notes]; [NotebookLM]

Identification by propensity weighting

Reading Materials

Textbook: Chapter 5
Rosenbaum & Rubin (1983), The central role of the propensity score

Coding Materials

NSW (Lalonde) Analysis: Identification by Propensity

Jan 20

Homework HW1 Due

Causal Estimation with Machine Learning

Jan 20

Lecture 4 Flexible Causal Estimation with Machine Learning I: Doubly Robust Learning and Debiasing: [Slides]; [Notes]; [NotebookLM]

Confidence intervals and asymptotic normality, why naive ML is problematic for confidence intervals of causal quantities, cross-fitting, debiasing, the doubly robust estimator.

Reading Materials

Textbook: Chapter 9
Chernozhukov et al. (2018), Double/debiased machine learning for treatment and structural parameters (optional)
Bang & Robins (2005), Doubly robust estimation in missing data and causal inference (optional)

Coding Materials

g-estimator, g-estimator with crossfitting, DR estimator with crossfitting on Synthetic Example

Jan 21

Homework HW2 Released, Wednesday (Doubly Robust Estimation)

Jan 22

Lecture 5 Flexible Causal Estimation with Machine Learning II: ML Predictive Modeling: [Slides]; [Notes]; [NotebookLM]

Solving prediction problems with ML, cross-validation, AutoML, semi-cross-fitting, stacking.

Reading Materials

Textbook: Chapters 1, 3, 8

Coding Materials

Overview of ML Methods + AutoML + Stacking

Jan 27

Lecture 6 Analyzing Experiments with Precision: [Slides]; [Notes]; [NotebookLM]

Variance of Doubly Robust Estimator, Linear Regression under mis-specification, Linear Regression for RCTs, Precision Improvement

In Class Activity Results

Table of Pros and Cons of each ATE Estimator

Reading Materials

Coding Materials

Variance of DR Estimator

Jan 28

Homework HW2 Due, Wednesday

Jan 28

Homework HW3 Released, Wednesday (Analyzing Experiments with Precision)

Jan 29

Lecture 7 Analyzing Experiments with Precision II: [Slides]; [Notes]; [NotebookLM]

Linear Regression under mis-specification, Linear Regression for RCTs, Precision Improvement, Continuous Treatments and Partial Linearity

Reading Materials

Textbook: Chapter 1
Textbook: Chapter 2
Angrist & Pischke, Mostly Harmless Econometrics (optional background)
Lin (2013), Agnostic notes on regression adjustments to experimental data (optional)

Coding Materials

Feb 3

Lecture 8 Continuous Treatments and the Double Machine Learning Estimator: [Slides]; [Notes]; [NotebookLM]

FWL Theorem, Partially Linear Models, Continuous Treatments, Generalized FWL theorem

Reading Materials

Textbook: Sections 1, 4, 9

Coding Materials

DML for Price Elasticity: Synthetic and Real Data

Feb 4

Homework HW3 Due, Wednesday

Feb 4

Homework HW4 Released, Wednesday (Partially Linear Models)

Feb 5

Lecture 9 Double Machine Learning in Practice: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Coding Materials

Heterogeneous Treatment Effects

Feb 10

Lecture 14 Heterogeneous Treatment Effects I: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapter 14
EconML User Guide
Athey, Tibshirani, Wager (2019), Generalized random forests (optional)

Coding Materials

Feb 11

Homework HW4 Due, Wednesday

Feb 11

Homework HW5 Released, Wednesday(Heterogeneous Effects)

Feb 12

Lecture 15 Heterogeneous Treatment Effects II: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapter 15

Coding Materials

Causal Identification with DAGs

Feb 17

Lecture 10 Structural Causal Models & DAGs: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapters 7, 11
Richardson & Robins (2013), Single World Intervention Graphs (optional)

Feb 18

Homework HW5 Due, Wednesday

Feb 18

Homework HW6 Released, Wednesday (DAGs and Unobserved Confounding)

Feb 19

Lecture 10 Good and Bad Controls (via DAGs and SWIGs): [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapters 7, 11
Richardson & Robins (2013), Single World Intervention Graphs (optional)

Unobserved Confounding

Feb 24

Lecture 11 Unobserved Confounding & Sensitivity Analysis: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapters 12.1, 12.2
Cinelli & Hazlett (2020), Making sense of sensitivity: extending omitted variable bias (optional)
Victor Chernozhukov, Carlos Cinelli, Whitney Newey, Amit Sharma, Vasilis Syrgkanis (2021), Long Story Short: Omitted Variable Bias in Causal Machine Learning (optional)

Coding Materials

Feb 25

Homework HW6 Due, Wednesday

Feb 26

Lecture 12 Instrumental Variables: LATE, Partially Linear IV models, Debiased ML: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapters 12, 13
Imbens & Angrist (1994), Identification and estimation of LATE (classic)

Feb 27

Homework HW7 Released, Friday (Instrumental Variables)

Mar 3

Lecture 16 Proximal Causal Inference: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Textbook: Chapter 16
Textbook: Chapter 17
Tchetgen Tchetgen et al., Proximal causal learning (optional, advanced)

Mar 5

Lecture 17 Difference-in-Differences and Regression Discontinuity: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Callaway & Sant’Anna (2021) or Sun & Abraham (2021) (optional modern DiD)
Imbens & Lemieux (2008), Regression Discontinuity Designs (A guide to practice) (optional)
Calonico, Cattaneo & Titiunik (2014), Robust bias-corrected RDD inference (optional)

Mar 6

Homework HW7 Due, Friday

Dynamic and Long-Term Effects

Mar 9

Homework HW8 Released, Monday

Mar 10

Lecture 18 Dynamic Treatment Effects with ML, Surrogates for Long-Term Effects: [Slides]; [Notes]; [NotebookLM]

Reading Materials

Mar 12

Lecture 19 Surrogates and Long Term Effects + Discussion and Recap: [Slides]; [Notes]; [NotebookLM]; [Outro Slides]

Reading Materials

Mar 18

Homework HW8 Due, Wednesday of exam week