A0257
Title: Exploratory factor analysis of data on a sphere
Authors: Fan Dai - Michigan Technological University (United States) [presenting]
Karin Dorman - Iowa State University (United States)
Somak Dutta - Iowa State University (United States)
Ranjan Maitra - Iowa State University (United States)
Abstract: Data on high-dimensional spheres arise frequently in many disciplines either naturally or as a consequence of preliminary processing and can have intricate dependence structures that need to be understood. Exploratory factor analysis of the projected normal distribution is developed to explain the variability in such data using a few easily interpreted latent factors. The methodology provides maximum likelihood estimates through a novel fast alternating expectation profile conditional maximization algorithm. Outputs on simulation experiments in a wide range of settings are uniformly excellent. The method gives interpretable and insightful results when applied to tweets with the "me too" hashtag in 2018, to time-course functional magnetic resonance images of the average pre-teen brain at rest, to characterize handwritten digits, and to gene expression data from cancerous cells in the cancer genome atlas.
