Teaching
Courses and workshops on economics, econometrics, data science, and R programming.
Short, intensive R leveling course for incoming Master's students: R and RStudio fundamentals, reproducible workflows, data wrangling with the tidyverse, visualization and descriptives on real GEIH microdata, basic regressions, and a critical, verified use of AI in every unit.
Impact-evaluation methods for public policy and development economics — RCT, IV, regression discontinuity, difference-in-differences, event studies and matching — each paired with a canonical paper and applied in R.
Data analysis and machine learning for business decision-making, with generative AI across the whole course: R and the tidyverse, exploratory data analysis and data quality, LLMs and AI coding agents (Claude Code, Cursor, VS Code), classification and regression with trees, random forests and the Lasso, and k-means clustering.
Hands-on workshops on spatial data analysis in R for applied research: vector data with sf (geocoding, OpenStreetMap, distances, maps), rasters and night lights with terra (crop and mask, raster–vector joins with census blocks), and satellite applications — Sentinel-2 vegetation and built-up indices and the monthly VIIRS night-lights series — plus class notes and paper commentaries.
A hands-on R programming seminar: programming fundamentals and data structures, projects and version control with Git, data wrangling and dataset joins, visualization with ggplot2, loops and the apply family, web scraping, spatial (GIS) data, regressions, text mining, and reproducible reports with R Markdown.
Applied big data and machine learning for real-estate problems — predicting housing prices from large and spatial data — covering the full prediction workflow and model evaluation in R.
Graduate course on big data and machine learning for applied economics: the prediction workflow, overfitting and cross-validation, regularization, web scraping, Bayesian sampling methods, and spatial data and models.