Autoregressive aided periodogram bootstrap for time series

Arbeitspapier

A bootstrap methodology for the periodogram of a stationary process is proposed which is based on a combination of a time domain parametric and a frequency domain nonparametric bootstrap. The parametric fit is used to generate periodogram ordinates and imitate the essential features of the data and the weak dependence structure of the periodogram while a nonparametric (kernel based) correction is applied in order to catch features not represented by the parametric fit. The asymptotic theory developed shows validity of the proposed bootstrap procedure for a large class of periodogram statistics. For important classes of stochastie processes, validity of the new procedure is established also for periodogram statistics not captured by existing frequency domain bootstrap methods based on independent periodogram replicates.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: SFB 373 Discussion Paper ; No. 2001,60

Classification and Topics

• Classification: Wirtschaft
• Subject: Bootstrap ; periodogram ; nonparametric estimators ; ratio statisties, speetral means

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Kreiss, Jens-Peter ; Paparoditis, Efstathios
• Event: Veröffentlichung
• (who): Humboldt University of Berlin, Interdisciplinary Research Project 373: Quantification and Simulation of Economic Processes
• (where): Berlin
• (when): 2001

Further information

• Handle: http://hdl.handle.net/10419/62745
• URN: urn:nbn:de:kobv:11-10050164
• Last update: 10.03.2025, 11:41 AM CET