A0629
Title: Signal detection under unknown background when only one unlabeled data is available
Authors: Aritra Banerjee - University of Minnesota (United States) [presenting]
Sara Algeri - University of Minnesota (United States)
Lydia Brenner - Nikhef (Netherlands)
Oliver Rieger - Nikhef (Netherlands)
Abstract: Searches for new physics involve detecting the presence of a specific signal in data that is contaminated by a background arising from several other sources. This task is particularly challenging when a reliable description of the background is unavailable. The aim is to develop a statistical method to test the presence of the signal of interest in the data and to estimate the signal proportion even when the background is unknown or misspecified. Moreover, a signal search is proposed only using a single physics dataset generated from the experiments that may or may not contain the signal of interest. The approach relies on using orthonormal expansion to model the deviation between a proposal density and the unknown density generating the data. It is proposed to choose the proposal density in such a way that one can ensure a conservative estimate of the signal proportion to avoid false discovery. Reliability of this approach is demonstrated through simulation studies, application on realistic simulated data from the Fermi Large Area Telescope, and on data from the ATLAS experiment. A comparative analysis is also performed of the proposed method with the spurious signal method commonly employed in particle physics, and cases are explored where the latter leads to false discoveries.
