On Bootstrapping Kernel Spectral Estimates

An approach to bootstrapping kernel spectral density estimates is described which is based on resampling from the periodogram of the original data. We show that it is asymptotically valid under suitable conditions, and we illustrate its performance for a medium-sized time series sample with a small...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	The Annals of statistics 1992-03, Vol.20 (1), p.121-145
Hauptverfasser:	Franke, J., Hardle, W.
Format:	Artikel
Sprache:	eng
Schlagworte:	62G05 62M15 Approximation bandwidth selection Bootstrap Bootstrap resampling Density estimation Exact sciences and technology Inference from stochastic processes time series analysis kernel spectral estimate Mathematics Perceptron convergence procedure periodogram Preliminary estimates Probability and statistics Random variables Sciences and techniques of general use Signal bandwidth Spectral bands Spectral energy distribution Statistical variance Statistics time series
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	An approach to bootstrapping kernel spectral density estimates is described which is based on resampling from the periodogram of the original data. We show that it is asymptotically valid under suitable conditions, and we illustrate its performance for a medium-sized time series sample with a small simulation study.
ISSN:	0090-5364 2168-8966
DOI:	10.1214/aos/1176348515