Home > Research > Publications & Outputs > A wavelet-based approach for imputation in nons...

Research

Associated organisational units

Electronic data

  • mvLSW_imputation_accepted

    Accepted author manuscript, 954 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

A wavelet-based approach for imputation in nonstationary multivariate time series

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

A wavelet-based approach for imputation in nonstationary multivariate time series. / Wilson, Rebecca; Eckley, Idris; Nunes, Matthew et al.
In: Statistics and Computing, Vol. 31, 18, 17.02.2021.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Wilson, R, Eckley, I, Nunes, M & Park, TA 2021, 'A wavelet-based approach for imputation in nonstationary multivariate time series', Statistics and Computing, vol. 31, 18. https://doi.org/10.1007/s11222-021-09998-2

APA

Wilson, R., Eckley, I., Nunes, M., & Park, T. A. (2021). A wavelet-based approach for imputation in nonstationary multivariate time series. Statistics and Computing, 31, Article 18. https://doi.org/10.1007/s11222-021-09998-2

Vancouver

Wilson R, Eckley I, Nunes M, Park TA. A wavelet-based approach for imputation in nonstationary multivariate time series. Statistics and Computing. 2021 Feb 17;31:18. doi: 10.1007/s11222-021-09998-2

Author

Wilson, Rebecca ; Eckley, Idris ; Nunes, Matthew et al. / A wavelet-based approach for imputation in nonstationary multivariate time series. In: Statistics and Computing. 2021 ; Vol. 31.

Bibtex

@article{c33ed30d02b244ff927fa64852eb4cad,
title = "A wavelet-based approach for imputation in nonstationary multivariate time series",
abstract = "Many multivariate time series observed in practice are second order nonstationary, i.e. their covariance properties vary over time. In addition, missing observations in such data are encountered in many applications of interest, due to recording failures or sensor dropout, hindering successful analysis. This article introduces a novel method for data imputation in multivariate nonstationary time series, based on the so-called locally stationary wavelet modelling paradigm. Our methodology is shown to perform well across a range of simulation scenarios, with a variety of missingness structures, as well as being competitive in the stationary time series setting. We also demonstrate our technique on data arising in a health monitoring application.",
author = "Rebecca Wilson and Idris Eckley and Matthew Nunes and Park, {Timothy Alexander}",
year = "2021",
month = feb,
day = "17",
doi = "10.1007/s11222-021-09998-2",
language = "English",
volume = "31",
journal = "Statistics and Computing",
issn = "0960-3174",
publisher = "Springer Netherlands",

}

RIS

TY - JOUR

T1 - A wavelet-based approach for imputation in nonstationary multivariate time series

AU - Wilson, Rebecca

AU - Eckley, Idris

AU - Nunes, Matthew

AU - Park, Timothy Alexander

PY - 2021/2/17

Y1 - 2021/2/17

N2 - Many multivariate time series observed in practice are second order nonstationary, i.e. their covariance properties vary over time. In addition, missing observations in such data are encountered in many applications of interest, due to recording failures or sensor dropout, hindering successful analysis. This article introduces a novel method for data imputation in multivariate nonstationary time series, based on the so-called locally stationary wavelet modelling paradigm. Our methodology is shown to perform well across a range of simulation scenarios, with a variety of missingness structures, as well as being competitive in the stationary time series setting. We also demonstrate our technique on data arising in a health monitoring application.

AB - Many multivariate time series observed in practice are second order nonstationary, i.e. their covariance properties vary over time. In addition, missing observations in such data are encountered in many applications of interest, due to recording failures or sensor dropout, hindering successful analysis. This article introduces a novel method for data imputation in multivariate nonstationary time series, based on the so-called locally stationary wavelet modelling paradigm. Our methodology is shown to perform well across a range of simulation scenarios, with a variety of missingness structures, as well as being competitive in the stationary time series setting. We also demonstrate our technique on data arising in a health monitoring application.

U2 - 10.1007/s11222-021-09998-2

DO - 10.1007/s11222-021-09998-2

M3 - Journal article

VL - 31

JO - Statistics and Computing

JF - Statistics and Computing

SN - 0960-3174

M1 - 18

ER -