DaSSWeb | Principal Axis Analysis: an exploratory data analysis tool

Speaker
Conceição Amado
Department of Mathematics and CEMAT (IST, ULisboa)

Abstract
Principal Axis Analysis is a statistical technique that rotates standardised principal components in order to effectively identify subgroup patterns. This rotation is performed based on the preferred directions found in the spherised data. Therefore, it is a highly effective computer technique for analysing data in order to identify combinations of elliptically contoured distributions. We outline the methodology and illustrate it with examples.

(Joint work with Frank Critchley and Ana M. Pires)

Short Bio
Conceição Amado received a B.Sc. and an M.Sc. in Statistics and Operational Research from the University of Lisboa, Faculdade de Ciências, and a Ph.D. in Mathematics from the University of Lisboa, Instituto Superior Técnico (IST). She is an associate professor at IST, University of Lisboa, where she has been lecturing for the past three decades. She has been involved in national and international research projects, and she has supervised several Ph.D. and M.Sc. students. Her research work is mainly focused on multivariate analysis, robust methods, applied statistics, and data mining. In recent years, the engineering application of these methodologies has been of growing interest, with attested results that led to some of her recent publications in co-development with engineers and industry.

Link Zoom