2019/01/31 by Ursula Laa, Dianne Cook, Laa, Ursula +1
Computer Science · Earth and Planetary Sciences · #Computational Physics and Python Applications #Data Analysis #FOS: Computer and information sciences #FOS: Physical sciences #Geophysics and Gravity Measurements #High Energy Physics - Experiment (hep-ex) #High Energy Physics - Phenomenology (hep-ph) #Instrumentation and Methods for Astrophysics (astro-ph.IM) #Meteorological Phenomena and Simulations #Methodology (stat.ME) #Statistics and Probability (physics.data-an)
paper · pdf · doi:10.48550/arxiv.1902.00181
openalex publication_date 2019/01/31 · openalex created_date 2022/07/30 · openalex updated_date 2026/07/28
Projection pursuit is used to find interesting low-dimensional projections of\nhigh-dimensional data by optimizing an index over all possible projections.\nMost indexes have been developed to detect departure from known distributions,\nsuch as normality, or to find separations between known groups. Here, we are\ninterested in finding projections revealing potentially complex bivariate\npatterns, using new indexes constructed from scagnostics and a maximum\ninformation coefficient, with a purpose to detect unusual relationships between\nmodel parameters describing physics phenomena. The performance of these indexes\nis examined with respect to ideal behaviour, using simulated data, and then\napplied to problems from gravitational wave astronomy. The implementation\nbuilds upon the projection pursuit tools available in the R package, tourr,\nwith indexes constructed from code in the R packages, scagnostics, minerva and\nmbgraphic.\n