CMStatistics 2021: Start Registration
View Submission - CMStatistics
Title: Robust approaches for sufficient dimension reduction Authors:  Andreas Artemiou - Cardiff University (United Kingdom) [presenting]
Abstract: Sufficient Dimension Reduction (SDR) is a supervised dimension reduction framework to address dimension reduction mainly in regression and classification settings. Classic methods in SDR involve the use of inverse moments. We will discuss new methods to address the outliers in SDR methodology by using multivariate medians.