Large-scale data set has become increasingly available in many fields of economics. This presents challenges to statistical inference and even merely “understanding” the data. Meanwhile, it offers abundant opportunities for new inquiries and answers. In this course, we introduce the core statistical methods to work with big data (structured and unstructured) and show how these techniques can be combined with econometric tools in economics research. While we cover major machine learning tools, including supervised learning methods, unsupervised learning and dimensionality reduction, we will focus on their concrete applications in current empirical research. Examples will be drawn from various lines of research, including text as data, relevant prediction problems in economics, and causal inference.


1st Term
2nd Term
ECON5181 (M.Sc.) Teacher: Prof. CAO Siying [Course Outline]