Special Lecture Series:
Dimension Reduction in Regression
by
Visiting Prof. Lixing Zhu
Chair Professor and Department Head
Department of Mathematics
Hong Kong Baptist University
This lecture series consists of three lectures to introduce high-dimensional semiparametric regression estimation procedures as follows.
September 22, 2014- Lecture 1
Why dimension reduction and how dimension reduction: some basic concepts
In regression modelling, data visualization plays an important role and some useful tools have been developed such as residual plots when we do not have specific model structure at hand. In low-dimensional paradigms, these tools are very useful to get ideas about underlying regression models. However, in high-dimensional paradigms, residual plots can only get the profiles of the whole picture of underlying models and the information may mislead further modelling. Therefore, if we explore and identify dimension reduction structure first and then the further modelling can be proceeded such that the classical visualization tools can be satisfactorily performed. In this lecture, the sufficient dimension reduction concept, particularly the dimension reduction subspace called the central subspace will be introduced as the preparation for us for dimension reduction estimation in lectures 2 and 3 later.
TIME AND PLACE
4:40 – 5:30 p.m.
Philip E. Austin Building – Room 344
Coffee will be served at 4:10 in room 326
For complete lecture series notice visit www.stat.uconn.edu
For more information, contact: Tracy Burke at tracy.burke@uconn.edu