Causal machine learning
A PhD-level course. Practical classes are taught in R, Python and MATLAB. Participants are asked to install the software before the course.
- Software
- R, Python and MATLAB
- Contact hours
- 18 hours
- Previous edition
- 21–23 January 2025, daily 15:00–21:30 GMT+1 (Warsaw, Madrid, Berlin, Rome), 9:00–15:30 EST (Boston, New York, Washington)
- Next edition
- Dates will be announced on the PhD courses page.
Detailed course description
- Group average treatment effects, conditional average treatment effects
- Causal forest
- Double-lasso
- Double machine learning
- Partialling-out, partially linear regression, interactive regression model, IV model
- Overfitting, regularisation bias
- Neyman orthogonality, sample-splitting
- Hyperparameter optimisation
- Sensitivity analysis
- Quantile treatment effects
- Mediation analysis
- Sample selection models, dynamic treatment effects
- Cluster-robust DML
- Double machine learning for DiD
- Policy trees
- Deep IV
- Empirical Bayes
- Bayesian adjustment for confounding
- Bayesian networks
- Estimating CATE from satellite images and other kinds of images
- Large language models for ATE estimation
Registration and fees
After registration, each participant receives an email with an invoice and payment details. Discounts and the cancellation policy are described on the payments page. Questions: contact@slawomirkonopa.com.