TY - JOUR
T1 - Bayesian Model Search for Nonstationary Periodic Time Series
AU - Hadj-Amar, Beniamino
AU - Rand, Bärbel Finkenstädt
AU - Fiecas, Mark
AU - Lévi, Francis
AU - Huckstepp, Robert
N1 - Publisher Copyright:
© 2019 The Author(s). Published with license by Taylor & Francis Group, LLC.
PY - 2020/7/2
Y1 - 2020/7/2
N2 - 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. Supplementary materials for this article are available online.
AB - 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. Supplementary materials for this article are available online.
KW - Bayesian spectral analysis
KW - Change-points
KW - Reversible-jump MCMC
KW - Sleep apnea
KW - Ultradian sleep cycles
UR - http://www.scopus.com/inward/record.url?scp=85068719765&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068719765&partnerID=8YFLogxK
U2 - 10.1080/01621459.2019.1623043
DO - 10.1080/01621459.2019.1623043
M3 - Article
C2 - 33814652
AN - SCOPUS:85068719765
SN - 0162-1459
VL - 115
SP - 1320
EP - 1335
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 531
ER -