A frequency domain test for propriety of complex-valued vector time series
This paper proposes a frequency domain approach to test the hypothesis that a stationary complexvalued vector time series is proper, i.e., for testing whether the vector time series is uncorrelated with its complex conjugate. If the hypothesis is rejected, frequency bands causing the rejection will...
Published in: | IEEE Transactions on Signal Processing |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE) Publishing
2016
|
Subjects: | |
Online Access: | https://eprints.bbk.ac.uk/id/eprint/20645/ https://eprints.bbk.ac.uk/id/eprint/20645/1/FINALVERSION_corrected_REF.pdf https://doi.org/10.1109/TSP.2016.2639459 |
id |
ftbirkbeckcoll:oai:eprints.bbk.ac.uk.oai2:20645 |
---|---|
record_format |
openpolar |
spelling |
ftbirkbeckcoll:oai:eprints.bbk.ac.uk.oai2:20645 2023-05-15T17:06:11+02:00 A frequency domain test for propriety of complex-valued vector time series Chandna, Swati Walden, A. 2016-12-14 text https://eprints.bbk.ac.uk/id/eprint/20645/ https://eprints.bbk.ac.uk/id/eprint/20645/1/FINALVERSION_corrected_REF.pdf https://doi.org/10.1109/TSP.2016.2639459 en eng Institute of Electrical and Electronics Engineers (IEEE) Publishing https://eprints.bbk.ac.uk/id/eprint/20645/1/FINALVERSION_corrected_REF.pdf Chandna, Swati and Walden, A. (2016) A frequency domain test for propriety of complex-valued vector time series. IEEE Transactions on Signal Processing 65 (6), pp. 1425-1436. ISSN 1053-587X. Economics Mathematics and Statistics Article PeerReviewed 2016 ftbirkbeckcoll https://doi.org/10.1109/TSP.2016.2639459 2022-01-09T09:01:52Z This paper proposes a frequency domain approach to test the hypothesis that a stationary complexvalued vector time series is proper, i.e., for testing whether the vector time series is uncorrelated with its complex conjugate. If the hypothesis is rejected, frequency bands causing the rejection will be identified and might usefully be related to known properties of the physical processes. The test needs the associated spectral matrix which can be estimated by multitaper methods using, say, K tapers. Standard asymptotic distributions for the test statistic are of no use since they would require K → ∞, but, as K increases so does resolution bandwidth which causes spectral blurring. In many analyses K is necessarily kept small, and hence our efforts are directed at practical and accurate methodology for hypothesis testing for small K. Our generalized likelihood ratio statistic combined with exact cumulant matching gives very accurate rejection percentages. We also prove that the statistic on which the test is based is comprised of canonical coherencies arising from our complex-valued vector time series. Frequency specific tests are combined using multiple hypothesis testing to give an overall test. Our methodology is demonstrated on ocean current data collected at different depths in the Labrador Sea. Overall this work extends results on propriety testing for complex-valued vectors to the complex-valued vector time series setting. Article in Journal/Newspaper Labrador Sea BIROn - Birkbeck Institutional Research Online (Birkbeck University of London) IEEE Transactions on Signal Processing 65 6 1425 1436 |
institution |
Open Polar |
collection |
BIROn - Birkbeck Institutional Research Online (Birkbeck University of London) |
op_collection_id |
ftbirkbeckcoll |
language |
English |
topic |
Economics Mathematics and Statistics |
spellingShingle |
Economics Mathematics and Statistics Chandna, Swati Walden, A. A frequency domain test for propriety of complex-valued vector time series |
topic_facet |
Economics Mathematics and Statistics |
description |
This paper proposes a frequency domain approach to test the hypothesis that a stationary complexvalued vector time series is proper, i.e., for testing whether the vector time series is uncorrelated with its complex conjugate. If the hypothesis is rejected, frequency bands causing the rejection will be identified and might usefully be related to known properties of the physical processes. The test needs the associated spectral matrix which can be estimated by multitaper methods using, say, K tapers. Standard asymptotic distributions for the test statistic are of no use since they would require K → ∞, but, as K increases so does resolution bandwidth which causes spectral blurring. In many analyses K is necessarily kept small, and hence our efforts are directed at practical and accurate methodology for hypothesis testing for small K. Our generalized likelihood ratio statistic combined with exact cumulant matching gives very accurate rejection percentages. We also prove that the statistic on which the test is based is comprised of canonical coherencies arising from our complex-valued vector time series. Frequency specific tests are combined using multiple hypothesis testing to give an overall test. Our methodology is demonstrated on ocean current data collected at different depths in the Labrador Sea. Overall this work extends results on propriety testing for complex-valued vectors to the complex-valued vector time series setting. |
format |
Article in Journal/Newspaper |
author |
Chandna, Swati Walden, A. |
author_facet |
Chandna, Swati Walden, A. |
author_sort |
Chandna, Swati |
title |
A frequency domain test for propriety of complex-valued vector time series |
title_short |
A frequency domain test for propriety of complex-valued vector time series |
title_full |
A frequency domain test for propriety of complex-valued vector time series |
title_fullStr |
A frequency domain test for propriety of complex-valued vector time series |
title_full_unstemmed |
A frequency domain test for propriety of complex-valued vector time series |
title_sort |
frequency domain test for propriety of complex-valued vector time series |
publisher |
Institute of Electrical and Electronics Engineers (IEEE) Publishing |
publishDate |
2016 |
url |
https://eprints.bbk.ac.uk/id/eprint/20645/ https://eprints.bbk.ac.uk/id/eprint/20645/1/FINALVERSION_corrected_REF.pdf https://doi.org/10.1109/TSP.2016.2639459 |
genre |
Labrador Sea |
genre_facet |
Labrador Sea |
op_relation |
https://eprints.bbk.ac.uk/id/eprint/20645/1/FINALVERSION_corrected_REF.pdf Chandna, Swati and Walden, A. (2016) A frequency domain test for propriety of complex-valued vector time series. IEEE Transactions on Signal Processing 65 (6), pp. 1425-1436. ISSN 1053-587X. |
op_doi |
https://doi.org/10.1109/TSP.2016.2639459 |
container_title |
IEEE Transactions on Signal Processing |
container_volume |
65 |
container_issue |
6 |
container_start_page |
1425 |
op_container_end_page |
1436 |
_version_ |
1766061201028022272 |