Bayesian Model Search for Nonstationary Periodic Time Series

• 成果类型: Article
• 署名作者: Hadj-Amar, Beniamino; Rand, Barbel Finkenstadt; Fiecas, Mark; Levi, Francis; Huckstepp, Robert
• 署名单位: University of Warwick; University of Minnesota System; University of Minnesota Twin Cities; University of Warwick; University of Warwick
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2019.1623043
• 发表日期: 2020
• 页码: 1320-1335
• 关键词: spectral-analysis; parameter-estimation; circadian-rhythm; sleep-apnea; heart-rate; temperature; sinusoids; population; PREVALENCE; mechanisms

摘要

We propose a novel Bayesian methodology for analyzing nonstationary time series that exhibit oscillatory behavior. We approximate the time series using a piecewise oscillatory model with unknown periodicities, where our goal is to estimate the change-points while simultaneously identifying the potentially changing periodicities in the data. Our proposed methodology is based on a trans-dimensional Markov chain Monte Carlo algorithm that simultaneously updates the change-points and the periodicities relevant to any segment between them. We show that the proposed methodology successfully identifies time changing oscillatory behavior in two applications which are relevant to e-Health and sleep research, namely the occurrence of ultradian oscillations in human skin temperature during the time of night rest, and the detection of instances of sleep apnea in plethysmographic respiratory traces.for this article are available online.