Uncertainty Quantification for Object Boundaries Extracted from Spatial Point Patterns

• Activity Number: 190 - Synergy of Bayesian, Frequentist, and Fiducial Approaches in Addressing Modern Statistical Problems in Data Science
• Type: Invited
• Date/Time: Tuesday, August 10, 2021 : 1:30 PM to 3:20 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Thomas C. M. Lee*
• Companies: University of California at Davis
• Keywords: bootstrapping; confidence region; Fourier descriptor; hypothesis testing; image segmentation

Abstract

One common problem in astronomy is reconstructing various astronomical objects from photon counts detected by telescopes and determining if such objects change over time. This motivates the current work to recover objects hidden in noisy spatial point patterns, quantify uncertainties for these objects' boundaries and finally determine if they have changed over time. This talk reports our on-going work for solving this problem.

This is joint work with Vinay Kashyap, Jue Wang and Andreas Zezas