Abstract
Steve Marron, University of North Carolina
"High dimension low sample size asymptotics"
The asymptotics of growing sample size are the foundation of classical mathematical statistics. But modern big data challenges suggest consideration of growing dimension as well. A perhaps extreme case of this, first seriously explored by Hall, Marron and Neeman (2005), has fixed sample size. That context was shown there, and in a series of following papers, to have some counter-intuitive mathematical structure. These non-standard ways of thinking about data are seen to be the key to understanding important aspects of real genomic data.