Home > Research > Publications & Outputs > The sparse dynamic factor model

Research

Associated organisational units

Electronic data

  • Sparse_DFM_SAC-6

    Accepted author manuscript, 3.45 MB, PDF document

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

Links

Text available via DOI:

View graph of relations

The sparse dynamic factor model: a regularised quasi-maximum likelihood approach

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

Published

Standard

The sparse dynamic factor model: a regularised quasi-maximum likelihood approach. / Mosley, Luke; Chan, Tak-Shing; Gibberd, Alex.
In: Statistics and Computing, Vol. 34, 68, 22.01.2024.

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

Harvard

Mosley, L, Chan, T-S & Gibberd, A 2024, 'The sparse dynamic factor model: a regularised quasi-maximum likelihood approach', Statistics and Computing, vol. 34, 68. https://doi.org/10.1007/s11222-023-10378-1

APA

Mosley, L., Chan, T-S., & Gibberd, A. (2024). The sparse dynamic factor model: a regularised quasi-maximum likelihood approach. Statistics and Computing, 34, Article 68. https://doi.org/10.1007/s11222-023-10378-1

Vancouver

Mosley L, Chan T-S, Gibberd A. The sparse dynamic factor model: a regularised quasi-maximum likelihood approach. Statistics and Computing. 2024 Jan 22;34:68. doi: 10.1007/s11222-023-10378-1

Author

Mosley, Luke ; Chan, Tak-Shing ; Gibberd, Alex. / The sparse dynamic factor model : a regularised quasi-maximum likelihood approach. In: Statistics and Computing. 2024 ; Vol. 34.

Bibtex

@article{b3a804b549d94858a0b5c094a115c73e,
title = "The sparse dynamic factor model: a regularised quasi-maximum likelihood approach",
abstract = "The concepts of sparsity, and regularised estimation, have proven useful in many high-dimensional statistical applications. Dynamic factor models (DFMs) provide a parsimonious approach to modelling high-dimensional time series, however, it is often hard to interpret the meaning of the latent factors. This paper formally introduces a class of sparse DFMs whereby the loading matrices are constrained to have few non-zero entries, thus increasing interpretability of factors. We present a regularised M-estimator for the model parameters, and construct an efficient expectation maximisation algorithm to enable estimation. Synthetic experiments demonstrate consistency in terms of estimating the loading structure, and superior predictive performance where a low-rank factor structure may be appropriate. The utility of the method is further illustrated in an application forecasting electricity consumption across a large set of smart meters.",
author = "Luke Mosley and Tak-Shing Chan and Alex Gibberd",
year = "2024",
month = jan,
day = "22",
doi = "10.1007/s11222-023-10378-1",
language = "English",
volume = "34",
journal = "Statistics and Computing",
issn = "0960-3174",
publisher = "Springer Netherlands",

}

RIS

TY - JOUR

T1 - The sparse dynamic factor model

T2 - a regularised quasi-maximum likelihood approach

AU - Mosley, Luke

AU - Chan, Tak-Shing

AU - Gibberd, Alex

PY - 2024/1/22

Y1 - 2024/1/22

N2 - The concepts of sparsity, and regularised estimation, have proven useful in many high-dimensional statistical applications. Dynamic factor models (DFMs) provide a parsimonious approach to modelling high-dimensional time series, however, it is often hard to interpret the meaning of the latent factors. This paper formally introduces a class of sparse DFMs whereby the loading matrices are constrained to have few non-zero entries, thus increasing interpretability of factors. We present a regularised M-estimator for the model parameters, and construct an efficient expectation maximisation algorithm to enable estimation. Synthetic experiments demonstrate consistency in terms of estimating the loading structure, and superior predictive performance where a low-rank factor structure may be appropriate. The utility of the method is further illustrated in an application forecasting electricity consumption across a large set of smart meters.

AB - The concepts of sparsity, and regularised estimation, have proven useful in many high-dimensional statistical applications. Dynamic factor models (DFMs) provide a parsimonious approach to modelling high-dimensional time series, however, it is often hard to interpret the meaning of the latent factors. This paper formally introduces a class of sparse DFMs whereby the loading matrices are constrained to have few non-zero entries, thus increasing interpretability of factors. We present a regularised M-estimator for the model parameters, and construct an efficient expectation maximisation algorithm to enable estimation. Synthetic experiments demonstrate consistency in terms of estimating the loading structure, and superior predictive performance where a low-rank factor structure may be appropriate. The utility of the method is further illustrated in an application forecasting electricity consumption across a large set of smart meters.

U2 - 10.1007/s11222-023-10378-1

DO - 10.1007/s11222-023-10378-1

M3 - Journal article

VL - 34

JO - Statistics and Computing

JF - Statistics and Computing

SN - 0960-3174

M1 - 68

ER -