Econometrics: The Application of Data Analysis and Statistical Machine Learning in Economic Policy Making

Course 5: Econometrics: The Application of Data Analysis and Statistical Machine Learning in Economic Policy Making

I. Course Description

In todays age of globalization, digitalization and information, economic decision-making has become more complex and critical. Econometrics increasingly relies on data analysis and statistical learning methods to provide in-depth insights and more accurate decision support. The purpose of data analysis is to concentrate and extract the information hidden in a large number of seemingly chaotic data, so as to find out the internal law of the research object. In practice, data analysis and statistics can help managers to make judgments in order to make appropriate economic decisions.

This course aims to explore the application of data analysis and statistical learning methods in the field of econometrics to improve the precision and effectiveness of economic decision making. Students will examine how big data and advanced analytic tools are used to address key issues in the economy, including forecasting economic trends, optimizing resource allocation, reducing risk, and improving the quality of decision making for policy making and business management.

II. Professor Introduction

Donald Robertson – Tenured Professor at Cambridge University

Donald Robertson He is a professor at the School of Economics, University of Cambridge, and is known for his extensive research contributions in various fields of economics. His research topics include forecasting technology, taxation, career choices, and macroeconomic shocks. He attended Trinity College, Cambridge from 1980 to 1983, earning a BA in mathematics in 1983. He then studied for a masters degree in mathematical economics and econometrics at the London School of Economics, and received a doctorate in economics in 1989.

Professor Robertson is an assistant research fellow at the Centre for International Macroeconomics and Finance and the Centre for Economic Performance Research at the London School of Economics. He is also a Jean-Monet fellow at the Institute of European University in Florence, Italy. and has served as an external examiner at several academic institutions. The professor has published many influential articles in well-known journals such as Journal of Econometrics, Journal of Economics and Journal of Applied Econometrics, and has received substantial funding from prestigious institutions such as the Economic and Social Research Council (ESRC) and the British Academy of Sciences.

III. Syllabus

1. Statistical review: histograms and scatter plots
2. Variable relationship and prediction: nearest neighbor method and curve fitting
3. Least squares and multiple linear regression
4. Classical linear regression model and Gaussian Markov theorem
5. 5 of the classical linear regression model bias
6. Robust estimation method: minimum absolute deviation LAD and M estimation
7. Model selection; R square, information criterion, and mean square error
8. Penalized regression and regularization: LASSO and elastic net
9. Setting of binary and multiple Logit model
10. Causal inference and time-series model: RCTs and treatment effects