In the afternoon of July 23, Prof. Hong gave a lecture in the Asian Summer School in Econometrics and Statistics. Xingbai Xu, Associate Professor from Xiamen University, moderated the session.
Prof. Hong Yongmiao is Executive Director of Center for Forecasting Science of Chinese Academy of Sciences and Dean of School of Economics and Management of University of Chinese Academy of Sciences. He is a Academician of the Academy of Sciences for Developing Countries, a Fellow of International Association of Applied Econometrics(IAAE) and a Senior Fellow of The Rimini Centre for Economic Analysis (RCEA). Prof. Hong’s researches focus on model identification testing, non-linear time series analysis, financial econometrics and empirical studies of the Chinese economy and financial markets, and his researches have been published in top international journals in economics, finance and statistics, such as Econometrica, Journal of Political Economy, Quarterly Journal of Economics, Review of Economic Studies, Review of Economics and Statistics, Annals of Statistics, Journal of American Statistical Association Association, Journal of the Royal Statistical Society (Series B) and Review of Financial Studies, etc.
Prof. Hong gave a lecture “Nonparametric Statistics and Machine Learning”. Prof. Hong started with three questions: (1) What is a Taylor series expansion? (2) What is the Fourier series expansion? (3) What is the sample mean? Taking Keynes’(1936) Multiplier Effect theory and Cobb Douglas’ parametric models as examples, pointed out the limitations of traditional parametric methods and revealed the importance of non-parametric analysis. On this basis, Prof. Hong systematically introduced the development of non-parametric analysis methods and the two major methods of non-parametric analysis. They are Global Smoothing and Local Smoothing. Prof. Hong used Sieve Regression and Spline Smoothing as examples of global smoothing, and illustrated the importance of the smoothing parameter in terms of trade-offs between Bias and Variance, interspersed with an introduction to the primary functions.
At the end of the course, Prof. Hong gave a high-level summary of the methods, relationships, similarities and differences and applications of Non-parametric Estimation and Machine learning, broadening the participants’ horizons and patiently answering their doubts. The Summer School course ended with the enthusiastic of the participants.
