Extracting spatial structure and dynamics from data

Emily Stone, Department of Mathematics and Statistics, Utah State University, Logan, Utah

Archetypal analysis is a new statistical technique for extracting ``archetypal patterns" from data sets (Cutler and Breiman, 1996). It is related to principal component analysis (a.k.a. P.O.D., K.L.), though its objectives are different; it finds data points on the convex hull of the data set, rather than eigendirections in the data space. This talk will be a survey of recent results on the application of archetypal analysis to data sets from spatially extended dynamical systems, both numerical and experimental.