Salvato in:
Dettagli Bibliografici
Autori principali: Ghosh, Dhrubajyoti, McElroy, Tucker, Lahiri, Soumendra
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.15187
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916448567296000
author Ghosh, Dhrubajyoti
McElroy, Tucker
Lahiri, Soumendra
author_facet Ghosh, Dhrubajyoti
McElroy, Tucker
Lahiri, Soumendra
contents Higher-order spectra (or polyspectra), defined as the Fourier Transform of a stationary process' autocumulants, are useful in the analysis of nonlinear and non Gaussian processes. Polyspectral means are weighted averages over Fourier frequencies of the polyspectra, and estimators can be constructed from analogous weighted averages of the higher-order periodogram (a statistic computed from the data sample's discrete Fourier Transform). We derive the asymptotic distribution of a class of polyspectral mean estimators, obtaining an exact expression for the limit distribution that depends on both the given weighting function as well as on higher-order spectra. Secondly, we use bispectral means to define a new test of the linear process hypothesis. Simulations document the finite sample properties of the asymptotic results. Two applications illustrate our results' utility: we test the linear process hypothesis for a Sunspot time series, and for the Gross Domestic Product we conduct a clustering exercise based on bispectral means with different weight functions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Polyspectral Mean Estimation of General Nonlinear Processes
Ghosh, Dhrubajyoti
McElroy, Tucker
Lahiri, Soumendra
Statistics Theory
Higher-order spectra (or polyspectra), defined as the Fourier Transform of a stationary process' autocumulants, are useful in the analysis of nonlinear and non Gaussian processes. Polyspectral means are weighted averages over Fourier frequencies of the polyspectra, and estimators can be constructed from analogous weighted averages of the higher-order periodogram (a statistic computed from the data sample's discrete Fourier Transform). We derive the asymptotic distribution of a class of polyspectral mean estimators, obtaining an exact expression for the limit distribution that depends on both the given weighting function as well as on higher-order spectra. Secondly, we use bispectral means to define a new test of the linear process hypothesis. Simulations document the finite sample properties of the asymptotic results. Two applications illustrate our results' utility: we test the linear process hypothesis for a Sunspot time series, and for the Gross Domestic Product we conduct a clustering exercise based on bispectral means with different weight functions.
title Polyspectral Mean Estimation of General Nonlinear Processes
topic Statistics Theory
url https://arxiv.org/abs/2410.15187