Saving computer time in constructing consistent bootstrap prediction intervals for autoregressive processes

被引：32

作者：

Cao, R

FebreroBande, M

GonzalezManteiga, W

PradaSanchez, JM

GarciaJurado, I

机构：

[1] UNIV A CORUNA, FAC INFORMAT, DEPT MATEMAT, LA CORUNA 15071, SPAIN

[2] UNIV SANTIAGO COMPOSTELA, FAC MATEMAT, DEPT ESTADIST & INVEST OPERAT, SANTIAGO DE COMPOSTELA 15171, SPAIN

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 1997年 / 26卷 / 03期

关键词：

smoothed bootstrap; time series;

D O I：

10.1080/03610919708813420

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This paper presents consistent and fast bootstrap methods for constructing nonparametric prediction intervals for autoregressive processes. These methods are compared, in a simulation study, with the Box-Jenkins approach and Thombs-Schucany's bootstrap method.

引用

页码：961 / 978

页数：18

共 13 条

[1]

[Anonymous], 1976, TIME SERIES ANAL

[2]

[Anonymous], 1995, J TIME SER ANAL

[3] A NOTE ON THE ESTIMATION OF A DISTRIBUTION FUNCTION AND QUANTILES BY A KERNEL-METHOD [J].