Econometrics I Linear Algebra

This course aims to provide the student with advanced econometric skills used in empirical microeconometric research. The course places particular emphasis on the implementation of estimation using modern computational methods. Students will learn about classical and state-of-the-art ML methods with a focus on high-dimensionality and interpretability. Economic applications are used to illustrate the advantages and limitations of each methodology.

1. Generalized Method of Moments Estimation. 2. Models for Panel Data. 3. Linear Regression in High Dimensions Model Selection, Ridge, Lasso, Principal Component Regression, and their variants. 4. Modern Nonlinear Regression. Additive Models, Trees, Random Forests, Bagging, Boosting. 5. Deep Learning Perceptron, Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Long-Short Term Memory. 6. ML for Treatment Effect Estimation CATE via LASSO, Honest Trees, Causal Forests. 7. Double Machine Learning Partially Linear Model, ATE estimation and inference, Neyman Orthogonality, Cross-Fitting, DML for IV, DML for LATE.

Lectures. Overview of concepts and development of their properties. Practical classes focused on economic applications implemented in the Python language.