Spectral density estimation for nonstationary data with nonzero mean function

Anna E. Dudek (1, 2) , Lukasz Lenart

1 AGH UST - AGH University of Science and Technology [Krakow, PL]
2 IRMAR - Institut de Recherche Mathématique de Rennes

We introduce a new approach for nonparametric spectral density estimation based on the subsampling technique, which we apply to the important class of nonstation-ary time series. These are almost periodically correlated sequences. In contrary to existing methods our technique does not require demeaning of the data. On the simulated data examples we compare our estimator of spectral density function with the classical one. Additionally, we propose a modified estimator, which allows to reduce the leakage effect. Moreover, we provide two real data economic applications.

Mots clés: subsampling; almost periodically correlated; covariance matrix estimation; mixing; mix- ing

Domaines: Mathématiques [math]; Statistiques [math.ST]

Anna E. Dudek, Lukasz Lenart. Spectral density estimation for nonstationary data with nonzero mean function. 2020. ⟨hal-02442913v1⟩