TrendLSW: trend and spectral estimation of nonstationary time series in R
TrendLSW: trend and spectral estimation of nonstationary time series in R
The TrendLSW R package has been developed to provide users with a suite of wavelet-based techniques to analyze the statistical properties of nonstationary time series. The key components of the package are (a) two approaches for the estimation of the evolutionary wavelet spectrum in the presence of trend; and (b) wavelet-based trend estimation in the presence of locally stationary wavelet errors via both linear and nonlinear wavelet thresholding; and (c) the calculation of associated pointwise confidence intervals. Lastly, the package directly implements boundary handling methods that enable the methods to be performed on data of arbitrary length, not just dyadic length as is common for wavelet-based methods, ensuring no preprocessing of data is necessary. The key functionality of the package is demonstrated through two data examples, arising from biology and activity monitoring.
R, TrendLSW, evolutionary wavelet spectrum, locally stationary time series, trend estimation
Mcgonigle, Euan T.
1eec7a96-1343-4bf5-a131-432fe50842cd
Killick, Rebecca
c954436d-0b66-4ceb-bc63-bdf247ebee48
Nunes, Matthew A.
925d2e9f-8185-4479-aaf4-55fa45b83e1f
22 December 2025
Mcgonigle, Euan T.
1eec7a96-1343-4bf5-a131-432fe50842cd
Killick, Rebecca
c954436d-0b66-4ceb-bc63-bdf247ebee48
Nunes, Matthew A.
925d2e9f-8185-4479-aaf4-55fa45b83e1f
Mcgonigle, Euan T., Killick, Rebecca and Nunes, Matthew A.
(2025)
TrendLSW: trend and spectral estimation of nonstationary time series in R.
Journal of Statistical Software, 115 (10), [10].
(doi:10.18637/jss.v115.i10).
Abstract
The TrendLSW R package has been developed to provide users with a suite of wavelet-based techniques to analyze the statistical properties of nonstationary time series. The key components of the package are (a) two approaches for the estimation of the evolutionary wavelet spectrum in the presence of trend; and (b) wavelet-based trend estimation in the presence of locally stationary wavelet errors via both linear and nonlinear wavelet thresholding; and (c) the calculation of associated pointwise confidence intervals. Lastly, the package directly implements boundary handling methods that enable the methods to be performed on data of arbitrary length, not just dyadic length as is common for wavelet-based methods, ensuring no preprocessing of data is necessary. The key functionality of the package is demonstrated through two data examples, arising from biology and activity monitoring.
Text
v115i10
- Version of Record
More information
Accepted/In Press date: 1 November 2024
Published date: 22 December 2025
Keywords:
R, TrendLSW, evolutionary wavelet spectrum, locally stationary time series, trend estimation
Identifiers
Local EPrints ID: 509637
URI: http://eprints.soton.ac.uk/id/eprint/509637
ISSN: 1548-7660
PURE UUID: 534014e2-b503-4d09-bd57-69eccf39c3f9
Catalogue record
Date deposited: 27 Feb 2026 17:39
Last modified: 07 Mar 2026 04:16
Export record
Altmetrics
Contributors
Author:
Euan T. Mcgonigle
Author:
Rebecca Killick
Author:
Matthew A. Nunes
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics