Robust factor modelling for high-dimensional time series: An application to air pollution data

Abstract : This paper considers the factor modelling for high-dimensional time series contaminated by additive outliers. We propose a robust variant of the estimation method given in Lam and Yao [10]. The estimator of the number of factors is obtained by an eigen analysis of a robust non-negative definite covariance matrix. Asymptotic properties of the robust eigenvalues are derived and we show that the resulting estimators have the same convergence rates as those found for the standard eigenvalues estimators. Simulations are carried out to analyse the finite sample size performance of the robust estimator of the number of factors under the scenarios of multivariate time series with and without additive outliers. As an application, the robust factor analysis is performed to reduce the dimensionality of the data and, therefore, to identify the pollution behaviour of the pollutant PM10.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02183227
Contributor : Céline Lévy-Leduc <>
Submitted on : Monday, July 15, 2019 - 10:59:12 AM
Last modification on : Wednesday, July 17, 2019 - 1:24:58 AM

Identifiers

Citation

Valderio Anselmo Reisen, Adriano Sgrancio, Céline Levy-Leduc, Pascal Bondon, Edson Zambon Monte, et al.. Robust factor modelling for high-dimensional time series: An application to air pollution data. Applied Numerical Analysis and Computational Mathematics, Wiley-VCH Verlag: No OnlineOpen, 2019, ⟨10.1016/j.amc.2018.09.062⟩. ⟨hal-02183227⟩

Share

Metrics

Record views

26