Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets
International audience Singular spectrum analysis (SSA) along with its multivariate extension (M-SSA) provides an efficient way to identify weak oscillatory behavior in high-dimensional data. To prevent the misinterpretation of stochastic fluctuations in short time series as oscillations, Monte Carl...
Published in: | Journal of Climate |
---|---|
Main Authors: | , |
Other Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2015
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132/document https://hal.archives-ouvertes.fr/hal-01701132/file/Procrustes_JCLI-reprint.pdf https://doi.org/10.1175/JCLI-D-15-0100.1 |
id |
ftccsdartic:oai:HAL:hal-01701132v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-01701132v1 2023-05-15T17:33:39+02:00 Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets Groth, Andreas Ghil, Michael Institute of Geophysics and Planetary Physics Los Angeles (IGPP) University of California Los Angeles (UCLA) University of California-University of California Department of Atmospheric and Oceanic Sciences Los Angeles (AOS) École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL) 2015 https://hal.archives-ouvertes.fr/hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132/document https://hal.archives-ouvertes.fr/hal-01701132/file/Procrustes_JCLI-reprint.pdf https://doi.org/10.1175/JCLI-D-15-0100.1 en eng HAL CCSD American Meteorological Society info:eu-repo/semantics/altIdentifier/doi/10.1175/JCLI-D-15-0100.1 hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132/document https://hal.archives-ouvertes.fr/hal-01701132/file/Procrustes_JCLI-reprint.pdf doi:10.1175/JCLI-D-15-0100.1 info:eu-repo/semantics/OpenAccess ISSN: 0894-8755 EISSN: 1520-0442 Journal of Climate https://hal.archives-ouvertes.fr/hal-01701132 Journal of Climate, American Meteorological Society, 2015, 28 (19), pp.7873-7893. ⟨10.1175/JCLI-D-15-0100.1⟩ [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] [STAT.AP]Statistics [stat]/Applications [stat.AP] [STAT.ME]Statistics [stat]/Methodology [stat.ME] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere info:eu-repo/semantics/article Journal articles 2015 ftccsdartic https://doi.org/10.1175/JCLI-D-15-0100.1 2021-11-21T02:11:27Z International audience Singular spectrum analysis (SSA) along with its multivariate extension (M-SSA) provides an efficient way to identify weak oscillatory behavior in high-dimensional data. To prevent the misinterpretation of stochastic fluctuations in short time series as oscillations, Monte Carlo (MC)–type hypothesis tests provide objective criteria for the statistical significance of the oscillatory behavior. Procrustes target rotation is introduced here as a key method for refining previously available MC tests. The proposed modification helps reduce the risk of type-I errors, and it is shown to improve the test’s discriminating power. The reliability of the proposed methodology is examined in an idealized setting for a cluster of harmonic oscillators immersed in red noise. Furthermore, the common method of data compression into a few leading principal components, prior to M-SSA, is reexamined, and its possibly negative effects are discussed. Finally, the generalized Procrustes test is applied to the analysis of interannual variability in the North Atlantic’s sea surface temperature and sea level pressure fields. The results of this analysis provide further evidence for shared mechanisms of variability between the Gulf Stream and the North Atlantic Oscillation in the interannual frequency band. Article in Journal/Newspaper North Atlantic North Atlantic oscillation Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) Journal of Climate 28 19 7873 7893 |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] [STAT.AP]Statistics [stat]/Applications [stat.AP] [STAT.ME]Statistics [stat]/Methodology [stat.ME] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere |
spellingShingle |
[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] [STAT.AP]Statistics [stat]/Applications [stat.AP] [STAT.ME]Statistics [stat]/Methodology [stat.ME] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere Groth, Andreas Ghil, Michael Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
topic_facet |
[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] [STAT.AP]Statistics [stat]/Applications [stat.AP] [STAT.ME]Statistics [stat]/Methodology [stat.ME] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere |
description |
International audience Singular spectrum analysis (SSA) along with its multivariate extension (M-SSA) provides an efficient way to identify weak oscillatory behavior in high-dimensional data. To prevent the misinterpretation of stochastic fluctuations in short time series as oscillations, Monte Carlo (MC)–type hypothesis tests provide objective criteria for the statistical significance of the oscillatory behavior. Procrustes target rotation is introduced here as a key method for refining previously available MC tests. The proposed modification helps reduce the risk of type-I errors, and it is shown to improve the test’s discriminating power. The reliability of the proposed methodology is examined in an idealized setting for a cluster of harmonic oscillators immersed in red noise. Furthermore, the common method of data compression into a few leading principal components, prior to M-SSA, is reexamined, and its possibly negative effects are discussed. Finally, the generalized Procrustes test is applied to the analysis of interannual variability in the North Atlantic’s sea surface temperature and sea level pressure fields. The results of this analysis provide further evidence for shared mechanisms of variability between the Gulf Stream and the North Atlantic Oscillation in the interannual frequency band. |
author2 |
Institute of Geophysics and Planetary Physics Los Angeles (IGPP) University of California Los Angeles (UCLA) University of California-University of California Department of Atmospheric and Oceanic Sciences Los Angeles (AOS) École normale supérieure - Paris (ENS Paris) Université Paris sciences et lettres (PSL) |
format |
Article in Journal/Newspaper |
author |
Groth, Andreas Ghil, Michael |
author_facet |
Groth, Andreas Ghil, Michael |
author_sort |
Groth, Andreas |
title |
Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
title_short |
Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
title_full |
Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
title_fullStr |
Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
title_full_unstemmed |
Monte Carlo Singular Spectrum Analysis (SSA) Revisited: Detecting Oscillator Clusters in Multivariate Datasets |
title_sort |
monte carlo singular spectrum analysis (ssa) revisited: detecting oscillator clusters in multivariate datasets |
publisher |
HAL CCSD |
publishDate |
2015 |
url |
https://hal.archives-ouvertes.fr/hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132/document https://hal.archives-ouvertes.fr/hal-01701132/file/Procrustes_JCLI-reprint.pdf https://doi.org/10.1175/JCLI-D-15-0100.1 |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_source |
ISSN: 0894-8755 EISSN: 1520-0442 Journal of Climate https://hal.archives-ouvertes.fr/hal-01701132 Journal of Climate, American Meteorological Society, 2015, 28 (19), pp.7873-7893. ⟨10.1175/JCLI-D-15-0100.1⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1175/JCLI-D-15-0100.1 hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132 https://hal.archives-ouvertes.fr/hal-01701132/document https://hal.archives-ouvertes.fr/hal-01701132/file/Procrustes_JCLI-reprint.pdf doi:10.1175/JCLI-D-15-0100.1 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1175/JCLI-D-15-0100.1 |
container_title |
Journal of Climate |
container_volume |
28 |
container_issue |
19 |
container_start_page |
7873 |
op_container_end_page |
7893 |
_version_ |
1766132233478864896 |