ON BOOTSTRAPPING KERNEL SPECTRAL ESTIMATES

• 成果类型: Article
• 署名作者: FRANKE, J; HARDLE, W
• 署名单位: Universite Catholique Louvain
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/aos/1176348515
• 发表日期: 1992
• 页码: 121-145
• 关键词: Nonparametric regression; jackknife; models

摘要

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.