Data and Computation II

Catalog description

This course is the sequel to Data and Computation 1, and in the same spirit brings students up to speed with modern tools to manage economic data at a graduate level. The course is centered on the Python/numpy ecosystem, and has five parts. A first part introduces topics such as replicability through containerization, high performance computing, and cloud computing. A second part covers regression and model selection. A third part covers computational market design. A fourth part covers network problems. A fifth part covers dynamic discrete choice problems.