A Review on Semiparametric Model Averaging for Dynamic Time Series Forecasting: Methodology and Applications

Seminar abstract

Forecasting is the process of making predictions of the future based on past and present data. In the modern data science age, a large amount of data is easily available.

How to deal with high-dimensional modelling is no doubt a common challenge, in particular for time series dynamic forecasting.

Partial information based modelling and combination methods provide a useful way to handle a large number of variables (including dynamic lag variables), in particular when delving into nonlinear extraction of information from a large number of variables for forecasting.

In this talk, Professor Lu will review some of the ideas and progresses that my collaborators that he has developed with semiparametric model averaging for dynamic time series forecasting, and present some of our recent developments in methodology and applications in economic and financial modelling.

How to attend this seminar

This seminar is free to attend however entry is password protected. Please contact the organisers for the password.

Speaker bio

Professor Zudi Lu is Professor/Chair in Statistics in Mathematical Sciences and Southampton Statistical Sciences Research Institute (S3RI) at University of Southampton, UK.

Prior to that, he had worked at several international academic institutions, including

• University of Adelaide (2009-2013) and Curtin University (2006-2009) in Australia,
• London School of Economics (2003-2006) in the UK,
• Academy of Mathematics and Systems Science (1997-2003) in Beijing, China, a
• Universite Catholique de Louvain (1996-1997) in Louvain-la-Neuve, Belgium,

after he received his PhD degree from the Chinese Academy of Sciences in 1996.

He was a recipient of the Australian Research Council Future Fellowship in its 2010 round and other national/international grants from China, Australia and Europe, and is an elected member of the International Statistical Institute.

His current research interests range from nonlinear time series to nonlinear spatial and spatiotemporal data modelling and machine learning with applications to economic, financial and environmental modelling etc..