My research draws on two complementary types of resources. I apply advanced econometric methods to develop rigorous causal analyses, and I build novel datasets from a range of sources — including remote sensing, GIS, web-scraping, census records, and surveys. The resources listed below have been particularly valuable to my work.
For researchers at the intersection of machine learning and domain science, I also recommend Knowledge-Guided Machine Learning (KGML): Accelerating Discovery using Scientific Knowledge and Data, edited by Karpatne, Kannan & Kumar (Chapman Hall/CRC, 2022). The book offers a compelling framework for integrating scientific knowledge into ML models — especially useful when working with limited data or seeking to move beyond purely data-driven approaches. It is available here.
If you have questions about my research or any of these tools, feel free to get in touch.
1. DID reading group, here
2. Online Causal Inference Seminar, here
3. Applied Empirical Methods, here
4. Causal Inference Mixtapes, here
5. Discrete Choice Methods with Simulation, here
6. Python Econ Tools, here, here
Online learning and references
1. Automatic Download and Processing of Demographic and Health Surveys, here
2. Econometrics in R, here
3. Ujjwal's Spatial Thought blog, here
4. Machine learning in economics, resource here
5. Economics and Data Science, here
Coding tools
1. Big data processing in STATA, here
2. Fast fixed effects, in OLS and Poisson in STATA
3. Library of Statistical Techniques (LOST)! here
GIS database
1.AID database, here
2.geoBoundaries, here