Bootstrap for almost cyclostationary processes with jitter effect

Dominique Dehay (1) , Anna Dudek (1, 2) , Mohamed El Badaoui (3, 4)

1 IRMAR - Institut de Recherche Mathématique de Rennes
2 AGH UST - AGH University of Science and Technology [Krakow, PL]
3 SAFRAN Technofan
4 LASPI - Laboratoire d'Analyse des Signaux et des Processus Industriels

In this paper we consider almost cyclostationary processes with jitter effect. We propose a boot-strap approach based on the Moving Block Bootstrap method to construct pointwise and simultaneous confidence intervals for the Fourier coefficients of the autocovariance function of such processes. In the simulation study we show how our results can be used for second-order frequency detection. We compare behavior of our approach for jitter effects caused by perturbations from two distributions, namely uniform and truncated normal. Finally, we present a real data application of our methodology.

Mots clés: almost cyclostationarity; jitter; bootstrap; significance frequency detection

Domaines: Statistiques [stat]

Dominique Dehay, Anna Dudek, Mohamed El Badaoui. Bootstrap for almost cyclostationary processes with jitter effect. Digital Signal Processing, 2018, 73, pp.93-105. ⟨10.1016/j.dsp.2017.11.002⟩. ⟨hal-01430394v3⟩