This course offers a unified introduction to the principles and methods of statistical modeling and causal inference – two areas essential to data analysis in economics. The first part of this course introduces learning theory and a number of modern machine learning methods used for pattern recognition and predictive modeling. The second part introduces the theory of causal inference and surveys frequently used econometric techniques for causal effect learning and program evaluation. Finally, we discuss structural estimation and offer a unified perspective on the use of reduced-form and structural econometric methods.
The goal of this course is to equip students with both a solid theoretical foundation, and the tools they need to conduct hands-on empirical research using state-of-the-art technology. The lecture materials are written to be both deep conceptually and easy to follow technically. Throughout the course, methods are demonstrated with applications to actual and simulated problems in various fields of applied economics, such as labor economics, industrial organization, finance, and marketing. Students will learn how to explore and analyze large high-dimensional datasets, choose appropriate methods for answering different types of queries, including associational, causal, and counterfactual, as well as gaining valuable computational skills.
The course spans the fields of econometrics, statistics, and computer science. Although the focus is on the analysis of economic data, the theories and the tools presented should be useful for a wide range of research areas in business and the social sciences.
- Instructor: Jiaming Mao
- Email: [email protected]
- Course Website: jiamingmao.github.io/data-analysis
- Course Information: syllabus (pdf, slides)
- Review Session: github.com/trustxiaoqinwang/Microeconometrics_TA_Session