Hierarchical Time-Frequency Functional Data Models

• Activity Number: 618
• Type: Contributed
• Date/Time: Thursday, August 4, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Wen-Hsi Yang*+ and Scott H. Holan and Christopher K. Wikle
• Companies: University of Missouri at Columbia and University of Missouri and University of Missouri
• Keywords: Bayesian hierarchical models ; functional data ; time-frequency

Abstract

Time-frequency analysis has become a fundamental component of many scientific inquiries. In this domain, crucial aspects of the underlying process of interest often become apparent that would otherwise go undetected. Consequently, time-frequency representations can often as serve as powerful predictors in modeling complex processes. In order to facilitate the use of these representations within a statistical modeling framework, we propose class of flexible Bayesian hierarchical time-frequency functional data models. Importantly, our approach extracts features of the original signal that improve prediction rather than explaining variation. Finally, we illustrate the effectiveness of our approach through simulation and by applying our model to a real-world data example.